586 observations · 586 standings · first ingest Oct 2, 2026
Source record artificial-analysis-gpqa-diamond · higher is better
| Subject | Value | Instrument | Protocol | Measured by | Reported | Document |
|---|---|---|---|---|---|---|
| Grok 4.6 (high) | 0.95 | – | – | Artificial Analysis | Aug 12, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Gemini 3.7 Flash (high) | 0.95 | – | – | Artificial Analysis |
| Aug 13, 2026(model_announcement) |
| //artificialanalysis.ai/evaluations/gpqa-diamond |
| Gemini 3.1 Pro Preview | 0.94 | – | – | Artificial Analysis | Feb 19, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| GPT-5.6 Sol (max) | 0.94 | – | – | Artificial Analysis | Jul 9, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | 0.94 | – | – | Artificial Analysis | Jul 24, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Claude Opus 5 (Adaptive Reasoning, High Effort) | 0.94 | – | – | Artificial Analysis | Jul 24, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| GPT-5.5 (xhigh) | 0.94 | – | – | Artificial Analysis | Apr 23, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Grok 4.6 (medium) | 0.94 | – | – | Artificial Analysis | Aug 12, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Qwen3.8 2.4T A95B | 0.94 | – | – | Artificial Analysis | Aug 12, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Grok 4.6 (xhigh) | 0.94 | – | – | Artificial Analysis | Aug 12, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Kimi K3 (max) | 0.94 | – | – | Artificial Analysis | Jul 16, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| GPT-5.5 (high) | 0.93 | – | – | Artificial Analysis | Apr 23, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Claude Opus 5 (Adaptive Reasoning, Max Effort) | 0.93 | – | – | Artificial Analysis | Jul 24, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Grok 4.5 (high) | 0.93 | – | – | Artificial Analysis | Jul 8, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| GPT-5.6 Sol (xhigh) | 0.93 | – | – | Artificial Analysis | Jul 9, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| MiniMax-M3 | 0.93 | – | – | Artificial Analysis | Jun 1, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Gemini 3.6 Flash (high) | 0.93 | – | – | Artificial Analysis | Jul 21, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| DeepSeek V4 Pro 0813 (Reasoning, Max Effort) | 0.93 | – | – | Artificial Analysis | Aug 13, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| GPT-5.6 Sol (high) | 0.93 | – | – | Artificial Analysis | Jul 9, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Qwen3.8 Max | 0.93 | – | – | Artificial Analysis | Aug 3, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| GPT-5.5 (medium) | 0.93 | – | – | Artificial Analysis | Apr 23, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| GPT-5.6 Sol (medium) | 0.93 | – | – | Artificial Analysis | Jul 9, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | 0.93 | – | – | Artificial Analysis | Jun 9, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| GPT-5.6 Terra (max) | 0.93 | – | – | Artificial Analysis | Jul 9, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Qwen3.7 Max | 0.92 | – | – | Artificial Analysis | May 19, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Gemini 3.5 Flash (high) | 0.92 | – | – | Artificial Analysis | May 19, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Gemini 3.5 Flash (medium) | 0.92 | – | – | Artificial Analysis | May 19, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Gemini 3.7 Flash (medium) | 0.92 | – | – | Artificial Analysis | Aug 13, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | 0.92 | – | – | Artificial Analysis | May 28, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| GPT-5.4 (xhigh) | 0.92 | – | – | Artificial Analysis | Mar 5, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Claude Opus 5 (Adaptive Reasoning, Medium Effort) | 0.92 | – | – | Artificial Analysis | Jul 24, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| GLM-5.3 (max) | 0.92 | – | – | Artificial Analysis | Aug 18, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| GPT-5.3 Codex (xhigh) | 0.92 | – | – | Artificial Analysis | Feb 5, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | 0.91 | – | – | Artificial Analysis | Apr 16, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| DeepSeek V4 Flash Vision (Reasoning, Max Effort) | 0.91 | – | – | Artificial Analysis | Aug 21, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Kimi K2.6 | 0.91 | – | – | Artificial Analysis | Apr 20, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | 0.91 | – | – | Artificial Analysis | Jun 30, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| GPT-5.6 Luna (max) | 0.91 | – | – | Artificial Analysis | Jul 9, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Grok 4.20 0309 v2 (Reasoning) | 0.91 | – | – | Artificial Analysis | Apr 7, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| GPT-5.5 (low) | 0.91 | – | – | Artificial Analysis | Apr 23, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| GPT-5.6 Terra (xhigh) | 0.91 | – | – | Artificial Analysis | Jul 9, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Gemini 3 Pro Preview (high) | 0.91 | – | – | Artificial Analysis | Nov 18, 2025(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| DeepSeek V4 Flash 0731 (Reasoning, Max Effort) | 0.91 | – | – | Artificial Analysis | Jul 31, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| DeepSeek V4 Pro (Reasoning, High Effort) | 0.91 | – | – | Artificial Analysis | Apr 24, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Qwen3.8 27B (xhigh) | 0.91 | – | – | Artificial Analysis | Aug 14, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Muse Spark 1.2 (xhigh) | 0.90 | – | – | Artificial Analysis | Aug 5, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| GPT-5.2 (xhigh) | 0.90 | – | – | Artificial Analysis | Dec 11, 2025(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Grok 4.3 (high) | 0.90 | – | – | Artificial Analysis | Apr 30, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Gemini 3.7 Flash (low) | 0.90 | – | – | Artificial Analysis | Aug 13, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
| Qwen3.7 Plus | 0.90 | – | – | Artificial Analysis | Jun 1, 2026(model_announcement) | //artificialanalysis.ai/evaluations/gpqa-diamond |
Showing the top 50 of 586 standings — the complete set ships through the public API.
| Subject | Value | Reported | Kind | Ingested |
|---|---|---|---|---|
| DeepSeek V4 Flash Vision (Reasoning, Max Effort) | 0.91 | Aug 21, 2026 | unspecified | Oct 2, 2026 |
| G9v3-39A5B | 0.81 | Aug 20, 2026 | unspecified | Oct 2, 2026 |
| GLM-5.3 (max) | 0.92 | Aug 18, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.8 27B (xhigh) | 0.91 | Aug 14, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.8 27B (medium) | 0.85 | Aug 14, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.8 27B (low) | 0.85 | Aug 14, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.8 27B (Non-reasoning) | 0.82 | Aug 14, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.7 Flash (high) | 0.95 | Aug 13, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek V4 Pro 0813 (Reasoning, Max Effort) | 0.93 | Aug 13, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.7 Flash (medium) | 0.92 | Aug 13, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.7 Flash (low) | 0.90 | Aug 13, 2026 | unspecified | Oct 2, 2026 |
| Grok 4.6 (high) | 0.95 | Aug 12, 2026 | unspecified | Oct 2, 2026 |
| Grok 4.6 (medium) | 0.94 | Aug 12, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.8 2.4T A95B | 0.94 | Aug 12, 2026 | unspecified | Oct 2, 2026 |
| Grok 4.6 (xhigh) | 0.94 | Aug 12, 2026 | unspecified | Oct 2, 2026 |
| Grok 4.6 (low) | 0.88 | Aug 12, 2026 | unspecified | Oct 2, 2026 |
| Solar Open2 250B | 0.86 | Aug 12, 2026 | unspecified | Oct 2, 2026 |
| A.X-K2 | 0.86 | Aug 12, 2026 | unspecified | Oct 2, 2026 |
| Motif 3 | 0.83 | Aug 12, 2026 | unspecified | Oct 2, 2026 |
| K-EXAONE 2.0 0803 | 0.83 | Aug 12, 2026 | unspecified | Oct 2, 2026 |
| Nemotron 3.5 Lightning | 0.74 | Aug 11, 2026 | unspecified | Oct 2, 2026 |
| Muse Glimmer (high) | 0.84 | Aug 10, 2026 | unspecified | Oct 2, 2026 |
| Solar Pro 4 | 0.89 | Aug 6, 2026 | unspecified | Oct 2, 2026 |
| Ling 3.0 Tiny | 0.73 | Aug 6, 2026 | unspecified | Oct 2, 2026 |
| Muse Spark 1.2 (xhigh) | 0.90 | Aug 5, 2026 | unspecified | Oct 2, 2026 |
| Ling 3.0 Flash | 0.85 | Aug 4, 2026 | unspecified | Oct 2, 2026 |
| LFM2.5-2.6B | 0.56 | Aug 4, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.8 Max | 0.93 | Aug 3, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek V4 Flash 0731 (Reasoning, Max Effort) | 0.91 | Jul 31, 2026 | unspecified | Oct 2, 2026 |
| Inkling Small | 0.89 | Jul 30, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 5 (Adaptive Reasoning, Xhigh Effort) | 0.94 | Jul 24, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 5 (Adaptive Reasoning, High Effort) | 0.94 | Jul 24, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 5 (Adaptive Reasoning, Max Effort) | 0.93 | Jul 24, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 5 (Adaptive Reasoning, Medium Effort) | 0.92 | Jul 24, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 5 (Adaptive Reasoning, Low Effort) | 0.89 | Jul 24, 2026 | unspecified | Oct 2, 2026 |
| Agnes 2.5 Pro Alpha | 0.88 | Jul 24, 2026 | unspecified | Oct 2, 2026 |
| Celeris-1 | 0.63 | Jul 24, 2026 | unspecified | Oct 2, 2026 |
| G9v3-3B | 0.44 | Jul 23, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.6 Flash (high) | 0.93 | Jul 21, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.5 Flash-Lite | 0.84 | Jul 21, 2026 | unspecified | Oct 2, 2026 |
| Kimi K3 (max) | 0.94 | Jul 16, 2026 | unspecified | Oct 2, 2026 |
| Kimi K3 (low) | 0.84 | Jul 16, 2026 | unspecified | Oct 2, 2026 |
| Inkling (xhigh) | 0.87 | Jul 15, 2026 | unspecified | Oct 2, 2026 |
| Motif 3 (Beta) | 0.87 | Jul 14, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Sol (max) | 0.94 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Sol (xhigh) | 0.93 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Sol (high) | 0.93 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Sol (medium) | 0.93 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Terra (max) | 0.93 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Luna (max) | 0.91 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Terra (xhigh) | 0.91 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Sol (low) | 0.90 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| Muse Spark 1.1 (xhigh) | 0.90 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Terra (high) | 0.90 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Luna (xhigh) | 0.89 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Luna (high) | 0.89 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Terra (medium) | 0.87 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Luna (medium) | 0.86 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| JT-4.1 Flash 236B A21B | 0.85 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Terra (low) | 0.84 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Luna (low) | 0.84 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Sol (Non-reasoning) | 0.79 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Terra (Non-reasoning) | 0.75 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Luna (Non-reasoning) | 0.65 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| Grok 4.5 (high) | 0.93 | Jul 8, 2026 | unspecified | Oct 2, 2026 |
| Hy3 | 0.90 | Jul 6, 2026 | unspecified | Oct 2, 2026 |
| Claude Sonnet 5 (Adaptive Reasoning, Max Effort) | 0.91 | Jun 30, 2026 | unspecified | Oct 2, 2026 |
| Claude Sonnet 5 (Non-reasoning, High Effort) | 0.80 | Jun 30, 2026 | unspecified | Oct 2, 2026 |
| LongCat 2.0 | 0.78 | Jun 29, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.5 Instant (June 2026) | 0.82 | Jun 25, 2026 | unspecified | Oct 2, 2026 |
| Grok Build 0.1 0616 | 0.89 | Jun 16, 2026 | unspecified | Oct 2, 2026 |
| GLM-5.2 (max) | 0.89 | Jun 16, 2026 | unspecified | Oct 2, 2026 |
| GLM-5.2 (Non-reasoning) | 0.69 | Jun 16, 2026 | unspecified | Oct 2, 2026 |
| Kimi K2.7 Code | 0.90 | Jun 12, 2026 | unspecified | Oct 2, 2026 |
| DiffusionGemma 26B A4B | 0.67 | Jun 10, 2026 | unspecified | Oct 2, 2026 |
| Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | 0.93 | Jun 9, 2026 | unspecified | Oct 2, 2026 |
| North Mini Code | 0.76 | Jun 9, 2026 | unspecified | Oct 2, 2026 |
| Nemotron 3 Ultra 550B A55B (Reasoning) | 0.87 | Jun 4, 2026 | unspecified | Oct 2, 2026 |
| Gemma 4 12B (Reasoning) | 0.75 | Jun 3, 2026 | unspecified | Oct 2, 2026 |
| Gemma 4 12B (Non-reasoning) | 0.66 | Jun 3, 2026 | unspecified | Oct 2, 2026 |
| Nex-N2-Pro | 0.89 | Jun 2, 2026 | unspecified | Oct 2, 2026 |
| MiniMax-M3 | 0.93 | Jun 1, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.7 Plus | 0.90 | Jun 1, 2026 | unspecified | Oct 2, 2026 |
| Step 3.7 Flash | 0.81 | May 29, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 4.8 (Adaptive Reasoning, Max Effort) | 0.92 | May 28, 2026 | unspecified | Oct 2, 2026 |
| LFM2.5-8B-A1B | 0.51 | May 28, 2026 | unspecified | Oct 2, 2026 |
| HyperNova 60B 2605 | 0.73 | May 26, 2026 | unspecified | Oct 2, 2026 |
| MiniCPM5-1B (Reasoning) | 0.28 | May 25, 2026 | unspecified | Oct 2, 2026 |
| MiniCPM5-1B (Non-reasoning) | 0.27 | May 25, 2026 | unspecified | Oct 2, 2026 |
| Command A+ | 0.76 | May 20, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.7 Max | 0.92 | May 19, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.5 Flash (high) | 0.92 | May 19, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.5 Flash (medium) | 0.92 | May 19, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.5 Flash (minimal) | 0.83 | May 19, 2026 | unspecified | Oct 2, 2026 |
| JT-35B-Flash | 0.83 | May 14, 2026 | unspecified | Oct 2, 2026 |
| MiniCPM-V 4.6 1.3B | 0.31 | May 11, 2026 | unspecified | Oct 2, 2026 |
| Ring-2.6-1T | 0.86 | May 8, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.5 Instant (May 2026) | 0.85 | May 5, 2026 | unspecified | Oct 2, 2026 |
| Grok 4.3 (high) | 0.90 | Apr 30, 2026 | unspecified | Oct 2, 2026 |
| Grok 4.3 (medium) | 0.89 | Apr 30, 2026 | unspecified | Oct 2, 2026 |
| Grok 4.3 (low) | 0.84 | Apr 30, 2026 | unspecified | Oct 2, 2026 |
| Grok 4.3 (Non-reasoning) | 0.66 | Apr 30, 2026 | unspecified | Oct 2, 2026 |
| Mistral Medium 3.5 | 0.75 | Apr 29, 2026 | unspecified | Oct 2, 2026 |
| Granite 4.1 30B | 0.48 | Apr 29, 2026 | unspecified | Oct 2, 2026 |
| Nemotron 3 Nano Omni 30B A3B Reasoning | 0.47 | Apr 29, 2026 | unspecified | Oct 2, 2026 |
| Granite 4.1 8B | 0.43 | Apr 29, 2026 | unspecified | Oct 2, 2026 |
| Granite 4.1 3B | 0.31 | Apr 29, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek V4 Pro (Reasoning, High Effort) | 0.91 | Apr 24, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek V4 Flash (Reasoning, Max Effort) | 0.89 | Apr 24, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek V4 Pro (Reasoning, Max Effort) | 0.89 | Apr 24, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek V4 Flash (Reasoning, High Effort) | 0.87 | Apr 24, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek V4 Pro (Non-reasoning) | 0.72 | Apr 24, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek V4 Flash (Non-reasoning) | 0.72 | Apr 24, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.5 (xhigh) | 0.94 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.5 (high) | 0.93 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.5 (medium) | 0.93 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.5 (low) | 0.91 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| Hy3-preview (Reasoning) | 0.87 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.5 (Non-reasoning) | 0.77 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| Ling-2.6-1T | 0.75 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| Hy3-preview (Non-reasoning) | 0.73 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| MiMo-V2.5-Pro | 0.87 | Apr 22, 2026 | unspecified | Oct 2, 2026 |
| MiMo-V2.5 | 0.85 | Apr 22, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6 27B (Reasoning) | 0.84 | Apr 22, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6 27B (Non-reasoning) | 0.83 | Apr 22, 2026 | unspecified | Oct 2, 2026 |
| MiMo-V2.5-Pro (Non-reasoning) | 0.76 | Apr 22, 2026 | unspecified | Oct 2, 2026 |
| Ling 2.6 Flash | 0.59 | Apr 21, 2026 | unspecified | Oct 2, 2026 |
| Kimi K2.6 | 0.91 | Apr 20, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6 Max Preview | 0.89 | Apr 20, 2026 | unspecified | Oct 2, 2026 |
| Kimi K2.6 (Non-reasoning) | 0.79 | Apr 20, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 4.7 (Adaptive Reasoning, Max Effort) | 0.91 | Apr 16, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 4.7 (Non-reasoning, High Effort) | 0.88 | Apr 16, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6 35B A3B (Reasoning) | 0.84 | Apr 16, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6 35B A3B (Non-reasoning) | 0.82 | Apr 16, 2026 | unspecified | Oct 2, 2026 |
| JT-MINI | 0.68 | Apr 15, 2026 | unspecified | Oct 2, 2026 |
| EXAONE 4.5 33B | 0.79 | Apr 9, 2026 | unspecified | Oct 2, 2026 |
| Muse Spark | 0.88 | Apr 8, 2026 | unspecified | Oct 2, 2026 |
| Grok 4.20 0309 v2 (Reasoning) | 0.91 | Apr 7, 2026 | unspecified | Oct 2, 2026 |
| GLM-5.1 (Reasoning) | 0.87 | Apr 7, 2026 | unspecified | Oct 2, 2026 |
| GLM-5.1 (Non-reasoning) | 0.84 | Apr 7, 2026 | unspecified | Oct 2, 2026 |
| Grok 4.20 0309 v2 (Non-reasoning) | 0.78 | Apr 7, 2026 | unspecified | Oct 2, 2026 |
| Solar Pro 3 | 0.72 | Apr 6, 2026 | unspecified | Oct 2, 2026 |
| Gemma 4 E4B (Reasoning) | 0.58 | Apr 3, 2026 | unspecified | Oct 2, 2026 |
| Gemma 4 E4B (Non-reasoning) | 0.55 | Apr 3, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6 Plus | 0.88 | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| Gemma 4 31B (Reasoning) | 0.86 | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| Step 3.5 Flash 2603 | 0.83 | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| Gemma 4 26B A4B (Reasoning) | 0.79 | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| Gemma 4 31B (Non-reasoning) | 0.76 | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| Gemma 4 26B A4B (Non-reasoning) | 0.71 | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| Gemma 4 E2B (Reasoning) | 0.43 | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| Gemma 4 E2B (Non-reasoning) | 0.41 | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| GLM 5V Turbo (Reasoning) | 0.81 | Apr 1, 2026 | unspecified | Oct 2, 2026 |
| Trinity Large Thinking | 0.75 | Apr 1, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 Omni Plus | 0.83 | Mar 30, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 Omni Flash | 0.74 | Mar 30, 2026 | unspecified | Oct 2, 2026 |
| MiMo-V2-Omni-0327 | 0.85 | Mar 27, 2026 | unspecified | Oct 2, 2026 |
| KAT Coder Pro V2 | 0.85 | Mar 27, 2026 | unspecified | Oct 2, 2026 |
| MiMo-V2-Omni | 0.83 | Mar 19, 2026 | unspecified | Oct 2, 2026 |
| Nemotron Cascade 2 30B A3B | 0.76 | Mar 19, 2026 | unspecified | Oct 2, 2026 |
| MiniMax-M2.7 | 0.87 | Mar 18, 2026 | unspecified | Oct 2, 2026 |
| MiMo-V2-Pro | 0.87 | Mar 18, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 mini (xhigh) | 0.87 | Mar 17, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 mini (medium) | 0.82 | Mar 17, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 nano (xhigh) | 0.82 | Mar 17, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 nano (medium) | 0.76 | Mar 17, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 mini (Non-Reasoning) | 0.61 | Mar 17, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 nano (Non-Reasoning) | 0.56 | Mar 17, 2026 | unspecified | Oct 2, 2026 |
| Mistral Small 4 (Reasoning) | 0.77 | Mar 16, 2026 | unspecified | Oct 2, 2026 |
| Mistral Small 4 (Non-reasoning) | 0.57 | Mar 16, 2026 | unspecified | Oct 2, 2026 |
| NVIDIA Nemotron 3 Nano 4B | 0.51 | Mar 16, 2026 | unspecified | Oct 2, 2026 |
| GLM-5-Turbo | 0.85 | Mar 15, 2026 | unspecified | Oct 2, 2026 |
| Nemotron 3 Super 120B A12B (Reasoning) | 0.80 | Mar 11, 2026 | unspecified | Oct 2, 2026 |
| Grok 4.20 0309 (Reasoning) | 0.88 | Mar 10, 2026 | unspecified | Oct 2, 2026 |
| Grok 4.20 0309 (Non-reasoning) | 0.78 | Mar 10, 2026 | unspecified | Oct 2, 2026 |
| Sarvam 105B (high) | 0.74 | Mar 6, 2026 | unspecified | Oct 2, 2026 |
| Sarvam 30B (high) | 0.63 | Mar 6, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 (xhigh) | 0.92 | Mar 5, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 (low) | 0.87 | Mar 5, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 (Non-reasoning) | 0.75 | Mar 5, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.1 Flash-Lite | 0.82 | Mar 3, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 9B (Reasoning) | 0.81 | Mar 2, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 9B (Non-reasoning) | 0.79 | Mar 2, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 4B (Reasoning) | 0.77 | Mar 2, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 4B (Non-reasoning) | 0.71 | Mar 2, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 2B (Reasoning) | 0.46 | Mar 2, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 2B (Non-reasoning) | 0.44 | Mar 2, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 0.8B (Non-reasoning) | 0.24 | Mar 2, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 0.8B (Reasoning) | 0.11 | Mar 2, 2026 | unspecified | Oct 2, 2026 |
| LFM2 24B A2B | 0.47 | Feb 25, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 27B (Reasoning) | 0.86 | Feb 24, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 122B A10B (Reasoning) | 0.86 | Feb 24, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 35B A3B (Reasoning) | 0.85 | Feb 24, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 27B (Non-reasoning) | 0.84 | Feb 24, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 122B A10B (Non-reasoning) | 0.83 | Feb 24, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 35B A3B (Non-reasoning) | 0.82 | Feb 24, 2026 | unspecified | Oct 2, 2026 |
| Mercury 2 | 0.77 | Feb 20, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.1 Pro Preview | 0.94 | Feb 19, 2026 | unspecified | Oct 2, 2026 |
| Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort) | 0.87 | Feb 17, 2026 | unspecified | Oct 2, 2026 |
| Claude Sonnet 4.6 (Non-reasoning, High Effort) | 0.80 | Feb 17, 2026 | unspecified | Oct 2, 2026 |
| Claude Sonnet 4.6 (Non-reasoning, Low Effort) | 0.80 | Feb 17, 2026 | unspecified | Oct 2, 2026 |
| Tiny Aya Global | 0.31 | Feb 17, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 397B A17B (Reasoning) | 0.89 | Feb 16, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5 397B A17B (Non-reasoning) | 0.86 | Feb 16, 2026 | unspecified | Oct 2, 2026 |
| MiniMax-M2.5 | 0.85 | Feb 12, 2026 | unspecified | Oct 2, 2026 |
| Nanbeige4.1-3B | 0.85 | Feb 11, 2026 | unspecified | Oct 2, 2026 |
| GLM-5 (Reasoning) | 0.82 | Feb 11, 2026 | unspecified | Oct 2, 2026 |
| GLM-5 (Non-reasoning) | 0.67 | Feb 11, 2026 | unspecified | Oct 2, 2026 |
| Tri-21B-Think | 0.60 | Feb 10, 2026 | unspecified | Oct 2, 2026 |
| Tri-21B-think Preview | 0.54 | Feb 10, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.3 Codex (xhigh) | 0.92 | Feb 5, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 4.6 (Adaptive Reasoning, Max Effort) | 0.90 | Feb 5, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 4.6 (Non-reasoning, High Effort) | 0.84 | Feb 5, 2026 | unspecified | Oct 2, 2026 |
| Qwen3 Coder Next | 0.74 | Feb 3, 2026 | unspecified | Oct 2, 2026 |
| Step 3.5 Flash | 0.83 | Feb 2, 2026 | unspecified | Oct 2, 2026 |
| LongCat Flash Lite | 0.64 | Jan 28, 2026 | unspecified | Oct 2, 2026 |
| Kimi K2.5 (Reasoning) | 0.88 | Jan 27, 2026 | unspecified | Oct 2, 2026 |
| Kimi K2.5 (Non-reasoning) | 0.79 | Jan 27, 2026 | unspecified | Oct 2, 2026 |
| Qwen3 Max Thinking | 0.86 | Jan 26, 2026 | unspecified | Oct 2, 2026 |
| Step3 VL 10B | 0.69 | Jan 20, 2026 | unspecified | Oct 2, 2026 |
| LFM2.5-1.2B-Thinking | 0.34 | Jan 20, 2026 | unspecified | Oct 2, 2026 |
| GLM-4.7-Flash (Reasoning) | 0.58 | Jan 19, 2026 | unspecified | Oct 2, 2026 |
| GLM-4.7-Flash (Non-reasoning) | 0.45 | Jan 19, 2026 | unspecified | Oct 2, 2026 |
| Olmo 3.1 32B Instruct | 0.54 | Jan 13, 2026 | unspecified | Oct 2, 2026 |
| LFM2.5-1.2B-Instruct | 0.33 | Jan 5, 2026 | unspecified | Oct 2, 2026 |
| LFM2.5-VL-1.6B | 0.29 | Jan 5, 2026 | unspecified | Oct 2, 2026 |
| Falcon-H1R-7B | 0.66 | Jan 4, 2026 | unspecified | Oct 2, 2026 |
| K-EXAONE (Reasoning) | 0.78 | Dec 31, 2025 | unspecified | Oct 2, 2026 |
| K-EXAONE (Non-reasoning) | 0.69 | Dec 31, 2025 | unspecified | Oct 2, 2026 |
| HyperCLOVA X SEED Think (32B) | 0.62 | Dec 26, 2025 | unspecified | Oct 2, 2026 |
| MiniMax-M2.1 | 0.83 | Dec 23, 2025 | unspecified | Oct 2, 2026 |
| GLM-4.7 (Reasoning) | 0.86 | Dec 22, 2025 | unspecified | Oct 2, 2026 |
| GLM-4.7 (Non-reasoning) | 0.66 | Dec 22, 2025 | unspecified | Oct 2, 2026 |
| Gemini 3 Flash Preview (Reasoning) | 0.90 | Dec 17, 2025 | unspecified | Oct 2, 2026 |
| Gemini 3 Flash Preview (Non-reasoning) | 0.81 | Dec 17, 2025 | unspecified | Oct 2, 2026 |
| Solar Open 100B (Reasoning) | 0.66 | Dec 17, 2025 | unspecified | Oct 2, 2026 |
| MiMo-V2-Flash (Reasoning) | 0.85 | Dec 16, 2025 | unspecified | Oct 2, 2026 |
| MiMo-V2-Flash (Feb 2026) | 0.84 | Dec 16, 2025 | unspecified | Oct 2, 2026 |
| MiMo-V2-Flash (Non-reasoning) | 0.66 | Dec 16, 2025 | unspecified | Oct 2, 2026 |
| NVIDIA Nemotron 3 Nano 30B A3B (Reasoning) | 0.76 | Dec 15, 2025 | unspecified | Oct 2, 2026 |
| K2 Think V2 | 0.71 | Dec 15, 2025 | unspecified | Oct 2, 2026 |
| NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) | 0.40 | Dec 15, 2025 | unspecified | Oct 2, 2026 |
| Olmo 3.1 32B Think | 0.59 | Dec 12, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.2 (xhigh) | 0.90 | Dec 11, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.2 Codex (xhigh) | 0.90 | Dec 11, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.2 (medium) | 0.86 | Dec 11, 2025 | unspecified | Oct 2, 2026 |
| Mi:dm K 2.5 Pro Preview | 0.72 | Dec 11, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.2 (Non-reasoning) | 0.71 | Dec 11, 2025 | unspecified | Oct 2, 2026 |
| Mi:dm K 2.5 Pro | 0.70 | Dec 11, 2025 | unspecified | Oct 2, 2026 |
| Molmo2-8B | 0.43 | Dec 11, 2025 | unspecified | Oct 2, 2026 |
| Devstral 2 | 0.59 | Dec 9, 2025 | unspecified | Oct 2, 2026 |
| Devstral Small 2 | 0.53 | Dec 9, 2025 | unspecified | Oct 2, 2026 |
| GLM-4.6V (Reasoning) | 0.72 | Dec 8, 2025 | unspecified | Oct 2, 2026 |
| GLM-4.6V (Non-reasoning) | 0.57 | Dec 8, 2025 | unspecified | Oct 2, 2026 |
| K2-V2 (high) | 0.68 | Dec 5, 2025 | unspecified | Oct 2, 2026 |
| K2-V2 (medium) | 0.60 | Dec 5, 2025 | unspecified | Oct 2, 2026 |
| K2-V2 (low) | 0.54 | Dec 5, 2025 | unspecified | Oct 2, 2026 |
| Motif-2-12.7B-Reasoning | 0.69 | Dec 4, 2025 | unspecified | Oct 2, 2026 |
| Mistral Large 3 | 0.68 | Dec 2, 2025 | unspecified | Oct 2, 2026 |
| Ministral 3 14B | 0.57 | Dec 2, 2025 | unspecified | Oct 2, 2026 |
| Ministral 3 8B | 0.47 | Dec 2, 2025 | unspecified | Oct 2, 2026 |
| Ministral 3 3B | 0.36 | Dec 2, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek V3.2 Speciale | 0.87 | Dec 1, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek V3.2 (Reasoning) | 0.84 | Dec 1, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek V3.2 (Non-reasoning) | 0.75 | Dec 1, 2025 | unspecified | Oct 2, 2026 |
| Nova 2.0 Pro Preview (medium) | 0.78 | Nov 27, 2025 | unspecified | Oct 2, 2026 |
| INTELLECT-3 | 0.76 | Nov 27, 2025 | unspecified | Oct 2, 2026 |
| Nova 2.0 Pro Preview (low) | 0.75 | Nov 27, 2025 | unspecified | Oct 2, 2026 |
| Nova 2.0 Pro Preview (Non-reasoning) | 0.64 | Nov 27, 2025 | unspecified | Oct 2, 2026 |
| Nova 2.0 Omni (medium) | 0.76 | Nov 26, 2025 | unspecified | Oct 2, 2026 |
| Nova 2.0 Omni (low) | 0.70 | Nov 26, 2025 | unspecified | Oct 2, 2026 |
| Nova 2.0 Omni (Non-reasoning) | 0.55 | Nov 26, 2025 | unspecified | Oct 2, 2026 |
| Apriel-v1.6-15B-Thinker | 0.73 | Nov 25, 2025 | unspecified | Oct 2, 2026 |
| Claude Opus 4.5 (Reasoning) | 0.87 | Nov 24, 2025 | unspecified | Oct 2, 2026 |
| Claude Opus 4.5 (Non-reasoning) | 0.81 | Nov 24, 2025 | unspecified | Oct 2, 2026 |
| Olmo 3 32B Think | 0.61 | Nov 20, 2025 | unspecified | Oct 2, 2026 |
| Olmo 3 7B Think | 0.52 | Nov 20, 2025 | unspecified | Oct 2, 2026 |
| Olmo 3 7B Instruct | 0.40 | Nov 20, 2025 | unspecified | Oct 2, 2026 |
| Grok 4.1 Fast (Reasoning) | 0.85 | Nov 19, 2025 | unspecified | Oct 2, 2026 |
| Grok 4.1 Fast (Non-reasoning) | 0.64 | Nov 19, 2025 | unspecified | Oct 2, 2026 |
| Gemini 3 Pro Preview (high) | 0.91 | Nov 18, 2025 | unspecified | Oct 2, 2026 |
| Gemini 3 Pro Preview (low) | 0.89 | Nov 18, 2025 | unspecified | Oct 2, 2026 |
| Cogito v2.1 (Reasoning) | 0.77 | Nov 18, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.1 (high) | 0.87 | Nov 13, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.1 Codex (high) | 0.86 | Nov 13, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.1 Codex mini (high) | 0.81 | Nov 13, 2025 | unspecified | Oct 2, 2026 |
| ERNIE 5.0 Thinking Preview | 0.78 | Nov 13, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.1 (Non-reasoning) | 0.64 | Nov 13, 2025 | unspecified | Oct 2, 2026 |
| Doubao Seed Code | 0.76 | Nov 11, 2025 | unspecified | Oct 2, 2026 |
| KAT-Coder-Pro V1 | 0.76 | Nov 11, 2025 | unspecified | Oct 2, 2026 |
| Kimi K2 Thinking | 0.84 | Nov 6, 2025 | unspecified | Oct 2, 2026 |
| Qwen3 Max Thinking (Preview) | 0.78 | Nov 3, 2025 | unspecified | Oct 2, 2026 |
| Kimi Linear 48B A3B Instruct | 0.41 | Oct 30, 2025 | unspecified | Oct 2, 2026 |
| Nova 2.0 Lite (high) | 0.81 | Oct 29, 2025 | unspecified | Oct 2, 2026 |
| Nova 2.0 Lite (medium) | 0.77 | Oct 29, 2025 | unspecified | Oct 2, 2026 |
| Nova 2.0 Lite (low) | 0.70 | Oct 29, 2025 | unspecified | Oct 2, 2026 |
| Nova 2.0 Lite (Non-reasoning) | 0.60 | Oct 29, 2025 | unspecified | Oct 2, 2026 |
| NVIDIA Nemotron Nano 12B v2 VL (Reasoning) | 0.57 | Oct 28, 2025 | unspecified | Oct 2, 2026 |
| NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) | 0.44 | Oct 28, 2025 | unspecified | Oct 2, 2026 |
| Granite 4.0 1B | 0.28 | Oct 28, 2025 | unspecified | Oct 2, 2026 |
Showing the newest 300 of 586 observations.
239 observations · 237 standings · first ingest Oct 2, 2026
Source record llm-stats-gpqa · higher is better · declared max 1
2 tracked observations
2 tracked observations
| Subject | Value | Instrument | Protocol | Measured by | Reported | Document |
|---|---|---|---|---|---|---|
| GPT-5.6 Sol | 0.95 | – | – | OpenAI | Jul 9, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Claude Mythos Preview | 0.95 | – | – | Anthropic | Apr 7, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Gemini 3.1 Pro | 0.94 | – | – | Feb 19, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
Showing the top 50 of 237 standings — the complete set ships through the public API.
| Subject | Value | Reported | Kind | Ingested |
|---|---|---|---|---|
| Qwen3.8-27B | 0.89 | Aug 14, 2026 | unspecified | Oct 2, 2026 |
| Nemotron 3.5 Lightning (30B A3B) | 0.75 | Aug 11, 2026 | unspecified | Oct 2, 2026 |
| Muse Glimmer-30B | 0.83 | Aug 10, 2026 | unspecified | Oct 2, 2026 |
| Solar Pro 4 | 0.89 | Aug 6, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.8 Max | 0.93 |
26 observations · 24 standings · first ingest Oct 2, 2026
Source record gpqa · higher is better · metric accuracy
| Subject | Value | Instrument | Protocol | Measured by | Reported | Document |
|---|---|---|---|---|---|---|
| Gemini 3.1 Pro | 94.3% | gpqa_diamond | Thinking (High), No tools | Feb 19, 2026(publication date) | google_gemini_3_1_pro_model_card | |
| Kimi K3 | 93.5% | gpqa_diamond | reasoning=max, top-p 0.95 | Moonshot AI | Jun 13, 2026(publication date) | moonshot_kimi_k3_model_card |
| Hy4 preview | 92.3% | gpqa_diamond | as printed in Table 3 (Large Models) | Tencent | Aug 28, 2026(publication date) | tencent_hy4_preview |
| GLM-5.2 | 91.2% | gpqa_diamond | reasoning-tasks settings, temp 1.0, top_p 0.95, max gen 163840 tokens | Z.ai | Jun 16, 2026(publication date) | zai_glm_5_2_model_card |
| DeepSeek-V4.1-Flash | 90.9% | gpqa_diamond | think max, Pass@1 | DeepSeek | Sep 10, 2026(publication date) | deepseek_v4_1_flash_technical_report |
| DeepSeek-V4-Pro | 90.1% | gpqa_diamond | think max, pass@1 | DeepSeek | Apr 22, 2026(publication date) | deepseek_v4_model_card |
| Seed2.0 Pro | 88.9% | gpqa_diamond | as printed in Table 3 (Large Models) | ByteDance | Feb 14, 2026(publication date) | bytedance_seed2_0_model_card |
| Qwen3.5-397B-A17B | 88.4% | gpqa | thinking (temp 0.6, top_p 0.95, top_k 20) | Qwen | Feb 16, 2026(publication date) | qwen3_5_model_card |
| DeepSeek-V4-Flash | 88.1% | gpqa_diamond | think max, pass@1 | DeepSeek | Jun 25, 2026(publication date) | deepseek_v4_technical_report |
| Gemini 2.5 Pro | 86.4% | gpqa_diamond | single attempt, pass@1 | Jun 17, 2025(publication date) | google_gemini_2_5_report | |
| GLM-5.1 | 86.2% | gpqa_diamond | as reported | Z.ai | Apr 3, 2026(publication date) | zai_glm_5_1_model_card |
| GLM-5 | 86% | gpqa_diamond | reasoning-tasks settings, temp 1.0, top_p 0.95 | Z.ai | Feb 11, 2026(publication date) | zai_glm_5_model_card |
| Gemma 4 (31B) | 84.3% | gpqa_diamond | as reported | Mar 11, 2026(publication date) | google_gemma_4_model_card | |
| o3 high | 83.3% | gpqa_diamond | single attempt, pass@1 | Jun 17, 2025(publication date) | google_gemini_2_5_report | |
| Grok 3 Beta Extended Thinking | 80.2% | gpqa_diamond | single attempt, pass@1 | Jun 17, 2025(publication date) | google_gemini_2_5_report | |
| Claude Opus 4 | 79.6% | gpqa_diamond | extended thinking up to 64K tokens, no parallel test-time compute | Anthropic | May 22, 2025(publication date) | anthropic_claude_4_system_card |
| Claude 4 Opus | 79.6% | gpqa_diamond | single attempt, pass@1 | Jun 17, 2025(publication date) | google_gemini_2_5_report | |
| Claude Sonnet 4 | 75.4% | gpqa_diamond | extended thinking up to 64K tokens, no parallel test-time compute | Anthropic | May 22, 2025(publication date) | anthropic_claude_4_system_card |
| Claude 4 Sonnet | 75.4% | gpqa_diamond | single attempt, pass@1 | Jun 17, 2025(publication date) | google_gemini_2_5_report | |
| DeepSeek-R1 | 71.5% | gpqa_diamond | Pass@1, averaged over k=64 samples, temperature 0.6, top-p 0.95, 32K output limit | DeepSeek | Jan 22, 2025(publication date) | deepseek_r1_report |
| Qwen3-235B-A22B (Thinking) | 71.1% | gpqa_diamond | averaged over 10 samples | Qwen | May 14, 2025(publication date) | qwen3_technical_report |
| Seed2.0 Lite | 66.1% | gpqa_diamond | as printed in Table 4 (Efficient Models) | ByteDance | Feb 14, 2026(publication date) | bytedance_seed2_0_model_card |
| DeepSeek-V3 | 59.1% | gpqa_diamond | Pass@1, 8K output limit | DeepSeek | Dec 27, 2024(publication date) | deepseek_v3_report |
| Seed2.0 Mini | 58.1% | gpqa_diamond | as printed in Table 4 (Efficient Models) | ByteDance | Feb 14, 2026(publication date) | bytedance_seed2_0_model_card |
| Subject | Value | Reported | Kind | Ingested |
|---|---|---|---|---|
| DeepSeek-V4.1-Flash | 90.9% | Sep 10, 2026 | self-reported | Oct 2, 2026 |
| Hy4 preview | 92.3% | Aug 28, 2026 | self-reported | Oct 2, 2026 |
| DeepSeek-V4-Flash | 88.1% | Jun 25, 2026 | self-reported | Oct 2, 2026 |
| GLM-5.2 | 91.2% | Jun 16, 2026 | self-reported | Oct 2, 2026 |
documents that define or report scores for this benchmark
| other | – | GPQA Diamond– |
| other | – | GPQA– |
| release post | Ai2 | Olmo 3 (7B and 32B)Nov 20, 2025 |
| system card | Anthropic | Claude 3.7 SonnetFeb 24, 2025 |
| system card | Anthropic | Claude Opus 4 and Sonnet 4May 22, 2025 |
| other | ByteDance | Seed2.0 (Pro / Lite / Mini)Feb 14, 2026 |
| tech report | DeepSeek | DeepSeek-R1Jan 22, 2025 |
| tech report | DeepSeek | DeepSeek-V3Dec 27, 2024 |
| tech report | DeepSeek | DeepSeek-V4.1-FlashSep 10, 2026 |
| other | DeepSeek | DeepSeek-V4-ProApr 22, 2026 |
| tech report | DeepSeek | DeepSeek-V4Jun 25, 2026 |
| tech report | Gemini 2.5 ProJun 17, 2025 | |
| other | Gemini 3.1 ProFeb 19, 2026 | |
| other | Gemma 4 (31B)Mar 11, 2026 | |
| other | Meta | Llama 3.1 405BJul 23, 2024 |
| other | Meta | Llama 4Apr 5, 2025 |
| other | Mistral | Mistral Large 3 (675B)Nov 28, 2025 |
| release post | Mistral | Mistral Medium 3May 7, 2025 |
| other | Moonshot AI | Kimi K3Jun 13, 2026 |
| release post | OpenAI | GPT-4.1Apr 14, 2025 |
| release post | OpenAI | GPT-5.6Jun 26, 2026 |
| system card | OpenAI | GPT-5Aug 7, 2025 |
| system card | OpenAI | o3 and o4-miniApr 16, 2025 |
| other | Qwen | Qwen3.5-397B-A17BFeb 16, 2026 |
| other | Qwen | Qwen3.8-27BAug 5, 2026 |
| tech report | Qwen | Qwen3May 14, 2025 |
| tech report | Tencent | Hy4 previewAug 28, 2026 |
| release post | xAI | Grok 4.5Jul 8, 2026 |
| other | xAI | Grok 4Jul 9, 2025 |
| other | Z.ai | GLM-5.1Apr 3, 2026 |
| other | Z.ai | GLM-5.2Jun 16, 2026 |
| other | Z.ai | GLM-5Feb 11, 2026 |
| tech report | Z.ai | GLM-5Feb 11, 2026 |
Observations and source documents are located via the tracking corpus. Every row cites its primary source document; observations from different sources stay in separate partitions and are never merged into a cross-source ranking.
| Claude Opus 4.7 | 0.94 | – | – | Anthropic | Apr 16, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Claude Opus 4.8 | 0.94 | – | – | Anthropic | May 28, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| GPT-5.5 | 0.94 | – | – | OpenAI | Apr 23, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Kimi K3 | 0.94 | – | – | Moonshot AI | Jul 16, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| GPT-5.2 Pro | 0.93 | – | – | OpenAI | Dec 11, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Grok 4.5 | 0.93 | – | – | xAI | Jul 16, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| GPT-5.6 Terra | 0.93 | – | – | OpenAI | Jul 9, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| GPT-5.4 | 0.93 | – | – | OpenAI | Mar 5, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Qwen3.8 Max | 0.93 | – | – | Qwen | Aug 2, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Qwen3.7 Max | 0.92 | – | – | Qwen | May 19, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| GPT-5.2 | 0.92 | – | – | OpenAI | Dec 11, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| GPT-5.6 Luna | 0.92 | – | – | OpenAI | Jul 9, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Gemini 3 Pro | 0.92 | – | – | Nov 18, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Claude Opus 4.6 | 0.91 | – | – | Anthropic | Feb 5, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| GLM-5.2 | 0.91 | – | – | Z.ai | Jun 16, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Kimi K2.6 | 0.91 | – | – | Moonshot AI | Apr 20, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Hy3 | 0.90 | – | – | Tencent | Jul 6, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Qwen3.6 Plus | 0.90 | – | – | Qwen | Apr 2, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Gemini 3 Flash | 0.90 | – | – | Dec 17, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Qwen3.7-Plus | 0.90 | – | – | Qwen | May 31, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| DeepSeek-V4-Pro-Max | 0.90 | – | – | DeepSeek | Apr 23, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Claude Sonnet 4.6 | 0.90 | – | – | Anthropic | Feb 17, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Inkling-Small | 0.90 | – | – | Thinking Machines Lab | Jul 30, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Muse Spark | 0.90 | – | – | Meta | Apr 8, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Qwen3.8-27B | 0.89 | – | – | Qwen | Aug 14, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Solar Pro 4 | 0.89 | – | – | Upstage | Aug 6, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Seed 2.0 Pro | 0.89 | – | – | ByteDance | Feb 14, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Qwen3.5-397B-A17B | 0.88 | – | – | Qwen | Feb 16, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Grok-4 Heavy | 0.88 | – | – | xAI | Jul 9, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| DeepSeek-V4-Flash-Max | 0.88 | – | – | DeepSeek | Apr 23, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| GPT-5.1 | 0.88 | – | – | OpenAI | Nov 13, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| GPT-5.1 Thinking | 0.88 | – | – | OpenAI | Nov 12, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| GPT-5.1 High | 0.88 | – | – | OpenAI | Nov 12, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| GPT-5.1 Instant | 0.88 | – | – | OpenAI | Nov 12, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| GPT-5 Medium | 0.88 | – | – | OpenAI | Aug 7, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| GPT-5.4 mini | 0.88 | – | – | OpenAI | Mar 17, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Qwen3.6-27B | 0.88 | – | – | Qwen | Apr 21, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Kimi K2.5 | 0.88 | – | – | Moonshot AI | Jan 27, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Grok-4 | 0.88 | – | – | xAI | Jul 9, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| DeepSeek-V4-Flash-0423 | 0.87 | – | – | DeepSeek | Apr 23, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| GPT-5 High | 0.87 | – | – | OpenAI | Aug 7, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Nemotron 3 Ultra (550B A55B) | 0.87 | – | – | NVIDIA | Jun 4, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Claude Opus 4.5 | 0.87 | – | – | Anthropic | Nov 24, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Gemini 3.1 Flash-Lite | 0.87 | – | – | Mar 3, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Qwen3.5-122B-A10B | 0.87 | – | – | Qwen | Feb 24, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Gemini 2.5 Pro Preview 06-05 | 0.86 | – | – | Jun 5, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| GLM-5.1 | 0.86 | – | – | Z.ai | Apr 7, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/gpqa?top_n=500 |
| Aug 2, 2026 |
| unspecified |
| Oct 2, 2026 |
| Inkling-Small | 0.90 | Jul 30, 2026 | unspecified | Oct 2, 2026 |
| Kimi K3 | 0.94 | Jul 16, 2026 | unspecified | Oct 2, 2026 |
| Grok 4.5 | 0.93 | Jul 16, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Sol | 0.95 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Terra | 0.93 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.6 Luna | 0.92 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| Hy3 | 0.90 | Jul 6, 2026 | unspecified | Oct 2, 2026 |
| GLM-5.2 | 0.91 | Jun 16, 2026 | unspecified | Oct 2, 2026 |
| DiffusionGemma 26B-A4B | 0.73 | Jun 10, 2026 | unspecified | Oct 2, 2026 |
| Nemotron 3 Ultra (550B A55B) | 0.87 | Jun 4, 2026 | unspecified | Oct 2, 2026 |
| MAI-Code-1-Flash | 0.85 | Jun 2, 2026 | unspecified | Oct 2, 2026 |
| MAI-Thinking-1 | 0.84 | Jun 2, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.7-Plus | 0.90 | May 31, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 4.8 | 0.94 | May 28, 2026 | unspecified | Oct 2, 2026 |
| Gemma 4 12B | 0.79 | May 23, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.7 Max | 0.92 | May 19, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.5 Instant | 0.86 | May 5, 2026 | unspecified | Oct 2, 2026 |
| MiMo-V2.5-Pro | 0.67 | Apr 27, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.5 | 0.94 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek-V4-Pro-Max | 0.90 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek-V4-Flash-Max | 0.88 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek-V4-Flash-0423 | 0.87 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6-27B | 0.88 | Apr 21, 2026 | unspecified | Oct 2, 2026 |
| Kimi K2.6 | 0.91 | Apr 20, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 4.7 | 0.94 | Apr 16, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6-35B-A3B | 0.86 | Apr 16, 2026 | unspecified | Oct 2, 2026 |
| Muse Spark | 0.90 | Apr 8, 2026 | unspecified | Oct 2, 2026 |
| Claude Mythos Preview | 0.95 | Apr 7, 2026 | unspecified | Oct 2, 2026 |
| GLM-5.1 | 0.86 | Apr 7, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6 Plus | 0.90 | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| Gemma 4 31B | 0.84 | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| Gemma 4 26B-A4B | 0.82 | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| Gemma 4 E4B | 0.59 | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| Gemma 4 E2B | 0.43 | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 mini | 0.88 | Mar 17, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 nano | 0.83 | Mar 17, 2026 | unspecified | Oct 2, 2026 |
| Mistral Small 4 | 0.71 | Mar 16, 2026 | unspecified | Oct 2, 2026 |
| Nemotron 3 Super (120B A12B) | 0.83 | Mar 11, 2026 | unspecified | Oct 2, 2026 |
| Sarvam-105B | 0.79 | Mar 6, 2026 | unspecified | Oct 2, 2026 |
| Sarvam-30B | 0.67 | Mar 6, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 | 0.93 | Mar 5, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.1 Flash-Lite | 0.87 | Mar 3, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5-9B | 0.82 | Mar 2, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5-4B | 0.76 | Mar 2, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5-2B | 0.52 | Mar 2, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5-0.8B | 0.12 | Mar 2, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5-122B-A10B | 0.87 | Feb 24, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5-27B | 0.85 | Feb 24, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5-35B-A3B | 0.84 | Feb 24, 2026 | unspecified | Oct 2, 2026 |
| Mercury 2 | 0.74 | Feb 24, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.1 Pro | 0.94 | Feb 19, 2026 | unspecified | Oct 2, 2026 |
| Claude Sonnet 4.6 | 0.90 | Feb 17, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.5-397B-A17B | 0.88 | Feb 16, 2026 | unspecified | Oct 2, 2026 |
| Seed 2.0 Pro | 0.89 | Feb 14, 2026 | unspecified | Oct 2, 2026 |
| Seed 2.0 Lite | 0.85 | Feb 14, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 4.6 | 0.91 | Feb 5, 2026 | unspecified | Oct 2, 2026 |
| LongCat-Flash-Lite | 0.67 | Feb 5, 2026 | unspecified | Oct 2, 2026 |
| Kimi K2.5 | 0.88 | Jan 27, 2026 | unspecified | Oct 2, 2026 |
| ERNIE 5.0 | 0.85 | Jan 22, 2026 | unspecified | Oct 2, 2026 |
| GLM-4.7-Flash | 0.75 | Jan 19, 2026 | unspecified | Oct 2, 2026 |
| LongCat-Flash-Thinking-2601 | 0.81 | Jan 14, 2026 | unspecified | Oct 2, 2026 |
| MiniMax M2.1 | 0.81 | Dec 23, 2025 | unspecified | Oct 2, 2026 |
| GLM-4.7 | 0.86 | Dec 22, 2025 | unspecified | Oct 2, 2026 |
| Gemini 3 Flash | 0.90 | Dec 17, 2025 | unspecified | Oct 2, 2026 |
| MiMo-V2-Flash | 0.84 | Dec 16, 2025 | unspecified | Oct 2, 2026 |
| Nemotron 3 Nano (30B A3B) | 0.75 | Dec 15, 2025 | unspecified | Oct 2, 2026 |
| Qwen3 Max | 0.62 | Dec 15, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.2 Pro | 0.93 | Dec 11, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.2 | 0.92 | Dec 11, 2025 | unspecified | Oct 2, 2026 |
| Ministral 3 (14B Reasoning 2512) | 0.71 | Dec 4, 2025 | unspecified | Oct 2, 2026 |
| Ministral 3 (8B Reasoning 2512) | 0.67 | Dec 4, 2025 | unspecified | Oct 2, 2026 |
| Min istral 3 (3B Reasoning 2512) | 0.53 | Dec 4, 2025 | unspecified | Oct 2, 2026 |
| Mistral Large 3 (675B Instruct 2512 NVFP4) | 0.44 | Dec 4, 2025 | unspecified | Oct 2, 2026 |
| Mistral Large 3 (675B Instruct 2512) | 0.44 | Dec 4, 2025 | unspecified | Oct 2, 2026 |
| Mistral Large 3 (675B Instruct 2512 Eagle) | 0.44 | Dec 4, 2025 | unspecified | Oct 2, 2026 |
| Mistral Large 3 (675B Base) | 0.44 | Dec 4, 2025 | unspecified | Oct 2, 2026 |
| Nova 2 Pro | 0.81 | Dec 2, 2025 | unspecified | Oct 2, 2026 |
| Nova 2 Lite | 0.80 | Dec 2, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek-V3.2 (Thinking) | 0.82 | Dec 1, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek-V3.2 | 0.82 | Dec 1, 2025 | unspecified | Oct 2, 2026 |
| Claude Opus 4.5 | 0.87 | Nov 24, 2025 | unspecified | Oct 2, 2026 |
| Gemini 3 Pro | 0.92 | Nov 18, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.1 | 0.88 | Nov 13, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.1 Thinking | 0.88 | Nov 12, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.1 High | 0.88 | Nov 12, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.1 Instant | 0.88 | Nov 12, 2025 | unspecified | Oct 2, 2026 |
| MiniMax M2 | 0.78 | Oct 27, 2025 | unspecified | Oct 2, 2026 |
| Claude Haiku 4.5 | 0.73 | Oct 15, 2025 | unspecified | Oct 2, 2026 |
| GLM-4.6 | 0.81 | Sep 30, 2025 | unspecified | Oct 2, 2026 |
| Claude Sonnet 4.5 | 0.83 | Sep 29, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek-V3.2-Exp | 0.80 | Sep 29, 2025 | unspecified | Oct 2, 2026 |
| LongCat-Flash-Thinking | 0.81 | Sep 22, 2025 | unspecified | Oct 2, 2026 |
| Qwen3 VL 30B A3B Thinking | 0.74 | Sep 22, 2025 | unspecified | Oct 2, 2026 |
| Qwen3 VL 32B Thinking | 0.73 | Sep 22, 2025 | unspecified | Oct 2, 2026 |
| Qwen3 VL 30B A3B Instruct | 0.70 | Sep 22, 2025 | unspecified | Oct 2, 2026 |
| Qwen3 VL 8B Thinking | 0.70 | Sep 22, 2025 | unspecified | Oct 2, 2026 |
| Qwen3 VL 32B Instruct | 0.69 | Sep 22, 2025 | unspecified | Oct 2, 2026 |
| Qwen3 VL 4B Thinking | 0.64 | Sep 22, 2025 | unspecified | Oct 2, 2026 |
| Qwen3-Next-80B-A3B-Thinking | 0.77 | Sep 10, 2025 | unspecified | Oct 2, 2026 |
| Qwen3-Next-80B-A3B-Instruct | 0.73 | Sep 10, 2025 | unspecified | Oct 2, 2026 |
| Kimi K2-Thinking-0905 | 0.84 | Sep 5, 2025 | unspecified | Oct 2, 2026 |
| Kimi K2 0905 | 0.76 | Sep 5, 2025 | unspecified | Oct 2, 2026 |
| Kimi K2-Instruct-0905 | 0.75 | Sep 5, 2025 | unspecified | Oct 2, 2026 |
| LongCat-Flash-Chat | 0.73 | Aug 29, 2025 | unspecified | Oct 2, 2026 |
| Grok 4 Fast | 0.86 | Aug 28, 2025 | unspecified | Oct 2, 2026 |
| Nemotron Nano 9B v2 | 0.64 | Aug 18, 2025 | unspecified | Oct 2, 2026 |
| GPT-5 Medium | 0.88 | Aug 7, 2025 | unspecified | Oct 2, 2026 |
| GPT-5 High | 0.87 | Aug 7, 2025 | unspecified | Oct 2, 2026 |
| GPT-5 | 0.86 | Aug 7, 2025 | unspecified | Oct 2, 2026 |
| GPT-5 mini | 0.82 | Aug 7, 2025 | unspecified | Oct 2, 2026 |
| GPT-5 nano | 0.71 | Aug 7, 2025 | unspecified | Oct 2, 2026 |
| Claude Opus 4.1 | 0.81 | Aug 5, 2025 | unspecified | Oct 2, 2026 |
| GPT OSS 120B High | 0.81 | Aug 5, 2025 | unspecified | Oct 2, 2026 |
| GPT OSS 120B | 0.80 | Aug 5, 2025 | unspecified | Oct 2, 2026 |
| GPT OSS 20B High | 0.74 | Aug 5, 2025 | unspecified | Oct 2, 2026 |
| GPT OSS 20B | 0.71 | Aug 5, 2025 | unspecified | Oct 2, 2026 |
| GLM-4.5 | 0.79 | Jul 28, 2025 | unspecified | Oct 2, 2026 |
| GLM-4.5-Air | 0.75 | Jul 28, 2025 | unspecified | Oct 2, 2026 |
| Qwen3-235B-A22B-Thinking-2507 | 0.81 | Jul 25, 2025 | unspecified | Oct 2, 2026 |
| Qwen3-235B-A22B-Instruct-2507 | 0.78 | Jul 22, 2025 | unspecified | Oct 2, 2026 |
| Kimi K2 Instruct | 0.75 | Jul 11, 2025 | unspecified | Oct 2, 2026 |
| Kimi K2 Base | 0.48 | Jul 11, 2025 | unspecified | Oct 2, 2026 |
| Grok-4 Heavy | 0.88 | Jul 9, 2025 | unspecified | Oct 2, 2026 |
| Grok-4 | 0.88 | Jul 9, 2025 | unspecified | Oct 2, 2026 |
| Gemma 3n E2B Instructed | 0.25 | Jun 26, 2025 | unspecified | Oct 2, 2026 |
| Gemma 3n E4B Instructed | 0.24 | Jun 26, 2025 | unspecified | Oct 2, 2026 |
| ERNIE 4.5 | 0.74 | Jun 25, 2025 | unspecified | Oct 2, 2026 |
| Mistral Small 3.2 24B Instruct | 0.46 | Jun 20, 2025 | unspecified | Oct 2, 2026 |
| Gemini 2.5 Flash-Lite | 0.65 | Jun 17, 2025 | unspecified | Oct 2, 2026 |
| MiniMax M1 80K | 0.70 | Jun 16, 2025 | unspecified | Oct 2, 2026 |
| MiniMax M1 40K | 0.69 | Jun 16, 2025 | unspecified | Oct 2, 2026 |
| Magistral Medium | 0.71 | Jun 10, 2025 | unspecified | Oct 2, 2026 |
| Magistral Small 2506 | 0.68 | Jun 10, 2025 | unspecified | Oct 2, 2026 |
| Gemini 2.5 Pro Preview 06-05 | 0.86 | Jun 5, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek-R1-0528 | 0.81 | May 28, 2025 | unspecified | Oct 2, 2026 |
| Claude Opus 4 | 0.80 | May 22, 2025 | unspecified | Oct 2, 2026 |
| Claude Sonnet 4 | 0.75 | May 22, 2025 | unspecified | Oct 2, 2026 |
| Gemini 2.5 Pro | 0.83 | May 20, 2025 | unspecified | Oct 2, 2026 |
| Gemini 2.5 Flash | 0.83 | May 20, 2025 | unspecified | Oct 2, 2026 |
| Gemini Diffusion | 0.40 | May 20, 2025 | unspecified | Oct 2, 2026 |
| Gemma 3n E2B Instructed LiteRT (Preview) | 0.25 | May 20, 2025 | unspecified | Oct 2, 2026 |
| Gemma 3n E4B Instructed LiteRT Preview | 0.24 | May 20, 2025 | unspecified | Oct 2, 2026 |
| Phi 4 Reasoning Plus | 0.69 | Apr 30, 2025 | unspecified | Oct 2, 2026 |
| Phi 4 Reasoning | 0.66 | Apr 30, 2025 | unspecified | Oct 2, 2026 |
| Phi 4 Mini Reasoning | 0.52 | Apr 30, 2025 | unspecified | Oct 2, 2026 |
| Qwen3 30B A3B | 0.66 | Apr 29, 2025 | unspecified | Oct 2, 2026 |
| Qwen3 235B A22B | 0.47 | Apr 29, 2025 | unspecified | Oct 2, 2026 |
| o3 | 0.83 | Apr 16, 2025 | unspecified | Oct 2, 2026 |
| o4-mini | 0.81 | Apr 16, 2025 | unspecified | Oct 2, 2026 |
| GPT-4.1 | 0.66 | Apr 14, 2025 | unspecified | Oct 2, 2026 |
| GPT-4.1 mini | 0.65 | Apr 14, 2025 | unspecified | Oct 2, 2026 |
| GPT-4.1 nano | 0.50 | Apr 14, 2025 | unspecified | Oct 2, 2026 |
| Llama 3.1 Nemotron Ultra 253B v1 | 0.76 | Apr 7, 2025 | unspecified | Oct 2, 2026 |
| Llama 4 Maverick | 0.70 | Apr 5, 2025 | unspecified | Oct 2, 2026 |
| Llama 4 Scout | 0.57 | Apr 5, 2025 | unspecified | Oct 2, 2026 |
| Qwen2.5-Omni-7B | 0.31 | Mar 27, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek-V3 0324 | 0.68 | Mar 25, 2025 | unspecified | Oct 2, 2026 |
| Llama-3.3 Nemotron Super 49B v1 | 0.67 | Mar 18, 2025 | unspecified | Oct 2, 2026 |
| Llama 3.1 Nemotron Nano 8B V1 | 0.54 | Mar 18, 2025 | unspecified | Oct 2, 2026 |
| Mistral Small 3.1 24B Instruct | 0.46 | Mar 17, 2025 | unspecified | Oct 2, 2026 |
| Mistral Small 3.1 24B Base | 0.38 | Mar 17, 2025 | unspecified | Oct 2, 2026 |
| Gemma 3 27B | 0.42 | Mar 12, 2025 | unspecified | Oct 2, 2026 |
| Gemma 3 12B | 0.41 | Mar 12, 2025 | unspecified | Oct 2, 2026 |
| Gemma 3 4B | 0.31 | Mar 12, 2025 | unspecified | Oct 2, 2026 |
| Gemma 3 1B | 0.19 | Mar 12, 2025 | unspecified | Oct 2, 2026 |
| QwQ-32B | 0.65 | Mar 5, 2025 | unspecified | Oct 2, 2026 |
| Qwen2.5 VL 32B Instruct | 0.46 | Feb 28, 2025 | unspecified | Oct 2, 2026 |
| GPT-4.5 | 0.69 | Feb 27, 2025 | unspecified | Oct 2, 2026 |
| Claude 3.7 Sonnet | 0.85 | Feb 24, 2025 | unspecified | Oct 2, 2026 |
| Grok-3 | 0.85 | Feb 17, 2025 | unspecified | Oct 2, 2026 |
| Grok-3 Mini | 0.84 | Feb 17, 2025 | unspecified | Oct 2, 2026 |
| Gemini 2.0 Flash-Lite | 0.52 | Feb 5, 2025 | unspecified | Oct 2, 2026 |
| Phi 4 Mini | 0.25 | Feb 1, 2025 | unspecified | Oct 2, 2026 |
| o3-mini | 0.77 | Jan 30, 2025 | unspecified | Oct 2, 2026 |
| Mistral Small 3 24B Instruct | 0.45 | Jan 30, 2025 | unspecified | Oct 2, 2026 |
| Mistral Small 3 24B Base | 0.34 | Jan 30, 2025 | unspecified | Oct 2, 2026 |
| Gemini 2.0 Flash Thinking | 0.74 | Jan 21, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek R1 Zero | 0.73 | Jan 20, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek R1 Distill Llama 70B | 0.65 | Jan 20, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek R1 Distill Qwen 32B | 0.62 | Jan 20, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek R1 Distill Qwen 14B | 0.59 | Jan 20, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek R1 Distill Qwen 7B | 0.49 | Jan 20, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek R1 Distill Llama 8B | 0.49 | Jan 20, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek R1 Distill Qwen 1.5B | 0.34 | Jan 20, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek-V3.1 | 0.75 | Jan 10, 2025 | unspecified | Oct 2, 2026 |
| DeepSeek-V3 | 0.59 | Dec 25, 2024 | unspecified | Oct 2, 2026 |
| o1-pro | 0.79 | Dec 17, 2024 | unspecified | Oct 2, 2026 |
| o1 | 0.78 | Dec 17, 2024 | unspecified | Oct 2, 2026 |
| Phi 4 | 0.56 | Dec 12, 2024 | unspecified | Oct 2, 2026 |
| Llama 3.3 70B Instruct | 0.51 | Dec 6, 2024 | unspecified | Oct 2, 2026 |
| Gemini 2.0 Flash | 0.62 | Dec 1, 2024 | unspecified | Oct 2, 2026 |
| QwQ-32B-Preview | 0.65 | Nov 28, 2024 | unspecified | Oct 2, 2026 |
| Nova Pro | 0.47 | Nov 20, 2024 | unspecified | Oct 2, 2026 |
| Nova Lite | 0.42 | Nov 20, 2024 | unspecified | Oct 2, 2026 |
| Nova Micro | 0.40 | Nov 20, 2024 | unspecified | Oct 2, 2026 |
| Claude 3.5 Sonnet | 0.67 | Oct 22, 2024 | unspecified | Oct 2, 2026 |
| Claude 3.5 Haiku | 0.42 | Oct 22, 2024 | unspecified | Oct 2, 2026 |
| Llama 3.2 90B Instruct | 0.47 | Sep 25, 2024 | unspecified | Oct 2, 2026 |
| Llama 3.2 11B Instruct | 0.33 | Sep 25, 2024 | unspecified | Oct 2, 2026 |
| Llama 3.2 3B Instruct | 0.33 | Sep 25, 2024 | unspecified | Oct 2, 2026 |
| Qwen2.5 32B Instruct | 0.49 | Sep 19, 2024 | unspecified | Oct 2, 2026 |
| Qwen2.5 72B Instruct | 0.49 | Sep 19, 2024 | unspecified | Oct 2, 2026 |
| Qwen2.5 14B Instruct | 0.46 | Sep 19, 2024 | unspecified | Oct 2, 2026 |
| Qwen2.5 7B Instruct | 0.36 | Sep 19, 2024 | unspecified | Oct 2, 2026 |
| o1-preview | 0.73 | Sep 12, 2024 | unspecified | Oct 2, 2026 |
| o1-mini | 0.60 | Sep 12, 2024 | unspecified | Oct 2, 2026 |
| Phi-3.5-MoE-instruct | 0.37 | Aug 23, 2024 | unspecified | Oct 2, 2026 |
| Phi-3.5-mini-instruct | 0.30 | Aug 23, 2024 | unspecified | Oct 2, 2026 |
| Jamba 1.5 Large | 0.37 | Aug 22, 2024 | unspecified | Oct 2, 2026 |
| Jamba 1.5 Mini | 0.32 | Aug 22, 2024 | unspecified | Oct 2, 2026 |
| Hermes 3 70B | 0.66 | Aug 15, 2024 | unspecified | Oct 2, 2026 |
| Grok-2 | 0.56 | Aug 13, 2024 | unspecified | Oct 2, 2026 |
| Grok-2 mini | 0.51 | Aug 13, 2024 | unspecified | Oct 2, 2026 |
| GPT-4o | 0.70 | Aug 6, 2024 | unspecified | Oct 2, 2026 |
| Llama 3.1 405B Instruct | 0.51 | Jul 23, 2024 | unspecified | Oct 2, 2026 |
| Qwen2 72B Instruct | 0.42 | Jul 23, 2024 | unspecified | Oct 2, 2026 |
| Llama 3.1 70B Instruct | 0.42 | Jul 23, 2024 | unspecified | Oct 2, 2026 |
| Llama 3.1 8B Instruct | 0.30 | Jul 23, 2024 | unspecified | Oct 2, 2026 |
| Qwen2 7B Instruct | 0.25 | Jul 23, 2024 | unspecified | Oct 2, 2026 |
| GPT-4o mini | 0.40 | Jul 18, 2024 | unspecified | Oct 2, 2026 |
| Claude 3.5 Sonnet | 0.59 | Jun 21, 2024 | unspecified | Oct 2, 2026 |
| ChatGPT-4o Latest | 0.84 | May 13, 2024 | unspecified | Oct 2, 2026 |
| GPT-4o | 0.54 | May 13, 2024 | unspecified | Oct 2, 2026 |
| Gemini 1.5 Pro | 0.59 | May 1, 2024 | unspecified | Oct 2, 2026 |
| Gemini 1.5 Flash | 0.51 | May 1, 2024 | unspecified | Oct 2, 2026 |
| GPT-4 Turbo | 0.48 | Apr 9, 2024 | unspecified | Oct 2, 2026 |
| Grok-1.5 | 0.36 | Mar 28, 2024 | unspecified | Oct 2, 2026 |
| Gemini 1.5 Flash 8B | 0.38 | Mar 15, 2024 | unspecified | Oct 2, 2026 |
| Claude 3 Haiku | 0.33 | Mar 13, 2024 | unspecified | Oct 2, 2026 |
| Claude 3 Opus | 0.50 | Feb 29, 2024 | unspecified | Oct 2, 2026 |
| Claude 3 Sonnet | 0.40 | Feb 29, 2024 | unspecified | Oct 2, 2026 |
| Gemini 1.0 Pro | 0.28 | Feb 15, 2024 | unspecified | Oct 2, 2026 |
| GPT-4 | 0.36 | Jun 13, 2023 | unspecified | Oct 2, 2026 |
| GPT-3.5 Turbo | 0.31 | Mar 21, 2023 | unspecified | Oct 2, 2026 |
| Kimi K3 | 93.5% | Jun 13, 2026 | self-reported | Oct 2, 2026 |
| DeepSeek-V4-Pro | 72.9% | Apr 22, 2026 | self-reported | Oct 2, 2026 |
| DeepSeek-V4-Pro | 89.1% | Apr 22, 2026 | self-reported | Oct 2, 2026 |
| DeepSeek-V4-Pro | 90.1% | Apr 22, 2026 | self-reported | Oct 2, 2026 |
| GLM-5.1 | 86.2% | Apr 3, 2026 | self-reported | Oct 2, 2026 |
| Gemma 4 (31B) | 84.3% | Mar 11, 2026 | self-reported | Oct 2, 2026 |
| Gemini 3.1 Pro | 94.3% | Feb 19, 2026 | self-reported | Oct 2, 2026 |
| Qwen3.5-397B-A17B | 88.4% | Feb 16, 2026 | self-reported | Oct 2, 2026 |
| Seed2.0 Pro | 88.9% | Feb 14, 2026 | self-reported | Oct 2, 2026 |
| Seed2.0 Lite | 66.1% | Feb 14, 2026 | self-reported | Oct 2, 2026 |
| Seed2.0 Mini | 58.1% | Feb 14, 2026 | self-reported | Oct 2, 2026 |
| GLM-5 | 86% | Feb 11, 2026 | self-reported | Oct 2, 2026 |
| Claude 4 Opus | 79.6% | Jun 17, 2025 | self-reported | Oct 2, 2026 |
| Claude 4 Sonnet | 75.4% | Jun 17, 2025 | self-reported | Oct 2, 2026 |
| Gemini 2.5 Pro | 86.4% | Jun 17, 2025 | self-reported | Oct 2, 2026 |
| Grok 3 Beta Extended Thinking | 80.2% | Jun 17, 2025 | self-reported | Oct 2, 2026 |
| o3 high | 83.3% | Jun 17, 2025 | self-reported | Oct 2, 2026 |
| Claude Opus 4 | 79.6% | May 22, 2025 | self-reported | Oct 2, 2026 |
| Claude Sonnet 4 | 75.4% | May 22, 2025 | self-reported | Oct 2, 2026 |
| Qwen3-235B-A22B (Thinking) | 71.1% | May 14, 2025 | self-reported | Oct 2, 2026 |
| DeepSeek-R1 | 71.5% | Jan 22, 2025 | self-reported | Oct 2, 2026 |
| DeepSeek-V3 | 59.1% | Dec 27, 2024 | self-reported | Oct 2, 2026 |