LLM Stats leaderboard
33 scores · 33 models · first recorded Oct 2, 2026
higher is better · scale 0–1 · record MCP Atlas
Best reported score
88.1%Muse Spark 1.1 · LLM Stats leaderboard
36 models tested · 2 sources · 9 source documents · latest report Aug 28, 2026
MCP Atlas
Scores stay separate per source — never merged into one cross-source ranking.
33 scores · 33 models · first recorded Oct 2, 2026
higher is better · scale 0–1 · record MCP Atlas
| Model | Value (%) | Reported | Score type | Recorded |
|---|---|---|---|---|
| Muse Glimmer-30B | 75.5% | Aug 10, 2026 | unspecified | Oct 2, 2026 |
| Inkling-Small | 79.6% | Jul 30, 2026 | unspecified | Oct 2, 2026 |
| Kimi K3 | 84.2% | Jul 16, 2026 | unspecified | Oct 2, 2026 |
| Muse Spark 1.1 | 88.1% | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| Hy3 | 79.1% | Jul 6, 2026 | unspecified | Oct 2, 2026 |
| Seed 2.1 Pro | 83.8% | Jun 24, 2026 | unspecified | Oct 2, 2026 |
| Seed 2.1 Turbo | 80.3% | Jun 24, 2026 | unspecified | Oct 2, 2026 |
| GLM-5.2 | 76.8% | Jun 16, 2026 | unspecified | Oct 2, 2026 |
| Kimi K2.7 Code | 76% | Jun 12, 2026 | unspecified | Oct 2, 2026 |
| MiniMax M3 | 74.2% | Jun 1, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.7-Plus | 73.2% | May 31, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 4.8 | 82.2% | May 28, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.5 Flash | 83.6% | May 19, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.7 Max | 76.4% | May 19, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.5 | 75.3% | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek-V4-Pro-Max | 73.6% | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek-V4-Flash-Max | 69% | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek-V4-Flash-0423 | 67.4% | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6-35B-A3B | 62.8% | Apr 16, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 4.7 | 77.3% | Apr 16, 2026 | unspecified | Oct 2, 2026 |
| GLM-5.1 | 71.8% | Apr 7, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6 Plus | 74.1% | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 mini | 57.7% | Mar 17, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 nano | 56.1% | Mar 17, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 | 67.2% | Mar 5, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.1 Pro | 69.2% | Feb 19, 2026 | unspecified | Oct 2, 2026 |
| Claude Sonnet 4.6 | 61.3% | Feb 17, 2026 | unspecified | Oct 2, 2026 |
| GLM-5 | 67.8% | Feb 11, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 4.6 | 62.7% | Feb 5, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3 Flash | 57.4% | Dec 17, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.2 | 60.6% | Dec 11, 2025 | unspecified | Oct 2, 2026 |
| Nova 2 Lite | 24.6% | Dec 2, 2025 | unspecified | Oct 2, 2026 |
| Claude Opus 4.5 | 62.3% | Nov 24, 2025 | unspecified | Oct 2, 2026 |
8 scores · 8 models · first recorded Oct 2, 2026
higher is better · accuracy · scale 0–100 · record MCP Atlas
| Model | Value (%) | Subset / variant | Test conditions | Reported by | Reported | Document |
|---|---|---|---|---|---|---|
| Kimi K3 | 84.2% | mcp_atlas | reasoning=max | Moonshot AI | Jun 13, 2026 | moonshot_kimi_k3_model_card |
| Hy4 preview | 83.7% | mcp_atlas | as printed in Table 3 (Large Models) | Tencent | Aug 28, 2026 | tencent_hy4_preview |
| GLM-5.2 | 76.8% | mcp_atlas | think mode, 500-task public subset, 10-min timeout, Gemini-3.0-Pro judge | Z.ai | Jun 16, 2026 | zai_glm_5_2_model_card |
| DeepSeek-V4-Pro | 73.6% | mcp_atlas_public | think max, pass@1 | DeepSeek | Apr 22, 2026 | deepseek_v4_model_card |
| GLM-5.1 | 71.8% | mcp_atlas | as reported | Z.ai | Apr 3, 2026 | zai_glm_5_1_model_card |
| Gemini 3.1 Pro | 69.2% | mcp_atlas | Thinking (High) | Feb 19, 2026 | google_gemini_3_1_pro_model_card | |
| DeepSeek-V4-Flash | 69% | mcp_atlas_public | think max, pass@1 | DeepSeek | Jun 25, 2026 | deepseek_v4_technical_report |
| GLM-5 | 67.8% | mcp_atlas | think mode, 500-task public subset, 10-min timeout, Gemini 3 Pro judge | Z.ai | Feb 11, 2026 | zai_glm_5_model_card |
| Model | Value (%) | Reported | Score type | Recorded |
|---|---|---|---|---|
| Hy4 preview | 83.7% | Aug 28, 2026 | self-reported | Oct 2, 2026 |
| DeepSeek-V4-Flash | 69% | Jun 25, 2026 | self-reported | Oct 2, 2026 |
| GLM-5.2 | 76.8% | Jun 16, 2026 | self-reported | Oct 2, 2026 |
| Kimi K3 | 84.2% | Jun 13, 2026 | self-reported | Oct 2, 2026 |
every document that defines or reports scores
| other | – | MCP Atlas– |
| other | DeepSeek | DeepSeek-V4-ProApr 22, 2026 |
| tech report | DeepSeek | DeepSeek-V4Jun 25, 2026 |
| other | Gemini 3.1 ProFeb 19, 2026 | |
| other | Moonshot AI | Kimi K3Jun 13, 2026 |
| tech report | Tencent | Hy4 previewAug 28, 2026 |
| other | Z.ai | GLM-5.1Apr 3, 2026 |
| other | Z.ai | GLM-5.2Jun 16, 2026 |
| other | Z.ai | GLM-5Feb 11, 2026 |
Records are located via the tracking corpus (ktwu01/benchmark-radar live dataset). Every row cites its source document.
| DeepSeek-V4-Pro | 73.6% | Apr 22, 2026 | self-reported | Oct 2, 2026 |
| GLM-5.1 | 71.8% | Apr 3, 2026 | self-reported | Oct 2, 2026 |
| Gemini 3.1 Pro | 69.2% | Feb 19, 2026 | self-reported | Oct 2, 2026 |
| GLM-5 | 67.8% | Feb 11, 2026 | self-reported | Oct 2, 2026 |