33 observations · 33 standings · first ingest Oct 2, 2026
Source record llm-stats-mcp-atlas · higher is better · declared max 1
| Subject | Value | Instrument | Protocol | Measured by | Reported | Document |
|---|---|---|---|---|---|---|
| Muse Spark 1.1 | 0.88 | – | – | Meta | Jul 9, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Kimi K3 | 0.84 | – | – | Moonshot AI | Jul 16, 2026 |
| //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Seed 2.1 Pro | 0.84 | – | – | ByteDance | Jun 24, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Gemini 3.5 Flash | 0.84 | – | – | May 19, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Claude Opus 4.8 | 0.82 | – | – | Anthropic | May 28, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Seed 2.1 Turbo | 0.80 | – | – | ByteDance | Jun 24, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Inkling-Small | 0.80 | – | – | Thinking Machines Lab | Jul 30, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Hy3 | 0.79 | – | – | Tencent | Jul 6, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Claude Opus 4.7 | 0.77 | – | – | Anthropic | Apr 16, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| GLM-5.2 | 0.77 | – | – | Z.ai | Jun 16, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Qwen3.7 Max | 0.76 | – | – | Qwen | May 19, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Kimi K2.7 Code | 0.76 | – | – | Moonshot AI | Jun 12, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Muse Glimmer-30B | 0.76 | – | – | Meta | Aug 10, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| GPT-5.5 | 0.75 | – | – | OpenAI | Apr 23, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| MiniMax M3 | 0.74 | – | – | MiniMax | Jun 1, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Qwen3.6 Plus | 0.74 | – | – | Qwen | Apr 2, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| DeepSeek-V4-Pro-Max | 0.74 | – | – | DeepSeek | Apr 23, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Qwen3.7-Plus | 0.73 | – | – | Qwen | May 31, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| GLM-5.1 | 0.72 | – | – | Z.ai | Apr 7, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Gemini 3.1 Pro | 0.69 | – | – | Feb 19, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| DeepSeek-V4-Flash-Max | 0.69 | – | – | DeepSeek | Apr 23, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| GLM-5 | 0.68 | – | – | Z.ai | Feb 11, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| DeepSeek-V4-Flash-0423 | 0.67 | – | – | DeepSeek | Apr 23, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| GPT-5.4 | 0.67 | – | – | OpenAI | Mar 5, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Qwen3.6-35B-A3B | 0.63 | – | – | Qwen | Apr 16, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Claude Opus 4.6 | 0.63 | – | – | Anthropic | Feb 5, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Claude Opus 4.5 | 0.62 | – | – | Anthropic | Nov 24, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Claude Sonnet 4.6 | 0.61 | – | – | Anthropic | Feb 17, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| GPT-5.2 | 0.61 | – | – | OpenAI | Dec 11, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| GPT-5.4 mini | 0.58 | – | – | OpenAI | Mar 17, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Gemini 3 Flash | 0.57 | – | – | Dec 17, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| GPT-5.4 nano | 0.56 | – | – | OpenAI | Mar 17, 2026(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Nova 2 Lite | 0.25 | – | – | Amazon | Dec 2, 2025(model_announcement) | //api.zeroeval.com/leaderboard/benchmarks/mcp-atlas?top_n=500 |
| Subject | Value | Reported | Kind | Ingested |
|---|---|---|---|---|
| Muse Glimmer-30B | 0.76 | Aug 10, 2026 | unspecified | Oct 2, 2026 |
| Inkling-Small | 0.80 | Jul 30, 2026 | unspecified | Oct 2, 2026 |
| Kimi K3 | 0.84 | Jul 16, 2026 | unspecified | Oct 2, 2026 |
| Muse Spark 1.1 | 0.88 | Jul 9, 2026 | unspecified | Oct 2, 2026 |
| Hy3 | 0.79 | Jul 6, 2026 | unspecified | Oct 2, 2026 |
| Seed 2.1 Pro | 0.84 | Jun 24, 2026 | unspecified | Oct 2, 2026 |
| Seed 2.1 Turbo | 0.80 | Jun 24, 2026 | unspecified | Oct 2, 2026 |
| GLM-5.2 | 0.77 | Jun 16, 2026 | unspecified | Oct 2, 2026 |
| Kimi K2.7 Code | 0.76 | Jun 12, 2026 | unspecified | Oct 2, 2026 |
| MiniMax M3 | 0.74 | Jun 1, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.7-Plus | 0.73 | May 31, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 4.8 | 0.82 | May 28, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.5 Flash | 0.84 | May 19, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.7 Max | 0.76 | May 19, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.5 | 0.75 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek-V4-Pro-Max | 0.74 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek-V4-Flash-Max | 0.69 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| DeepSeek-V4-Flash-0423 | 0.67 | Apr 23, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 4.7 | 0.77 | Apr 16, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6-35B-A3B | 0.63 | Apr 16, 2026 | unspecified | Oct 2, 2026 |
| GLM-5.1 | 0.72 | Apr 7, 2026 | unspecified | Oct 2, 2026 |
| Qwen3.6 Plus | 0.74 | Apr 2, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 mini | 0.58 | Mar 17, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 nano | 0.56 | Mar 17, 2026 | unspecified | Oct 2, 2026 |
| GPT-5.4 | 0.67 | Mar 5, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3.1 Pro | 0.69 | Feb 19, 2026 | unspecified | Oct 2, 2026 |
| Claude Sonnet 4.6 | 0.61 | Feb 17, 2026 | unspecified | Oct 2, 2026 |
| GLM-5 | 0.68 | Feb 11, 2026 | unspecified | Oct 2, 2026 |
| Claude Opus 4.6 | 0.63 | Feb 5, 2026 | unspecified | Oct 2, 2026 |
| Gemini 3 Flash | 0.57 | Dec 17, 2025 | unspecified | Oct 2, 2026 |
| GPT-5.2 | 0.61 | Dec 11, 2025 | unspecified | Oct 2, 2026 |
| Nova 2 Lite | 0.25 | Dec 2, 2025 | unspecified | Oct 2, 2026 |
| Claude Opus 4.5 | 0.62 | Nov 24, 2025 | unspecified | Oct 2, 2026 |
8 observations · 8 standings · first ingest Oct 2, 2026
Source record mcp_atlas · higher is better · metric accuracy
| Subject | Value | Instrument | Protocol | Measured by | Reported | Document |
|---|---|---|---|---|---|---|
| Kimi K3 | 84.2% | mcp_atlas | reasoning=max | Moonshot AI | Jun 13, 2026(publication date) | moonshot_kimi_k3_model_card |
| Hy4 preview | 83.7% | mcp_atlas | as printed in Table 3 (Large Models) | Tencent | Aug 28, 2026(publication date) | 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(publication date) | zai_glm_5_2_model_card |
| DeepSeek-V4-Pro | 73.6% | mcp_atlas_public | think max, pass@1 | DeepSeek | Apr 22, 2026(publication date) | deepseek_v4_model_card |
| GLM-5.1 | 71.8% | mcp_atlas | as reported | Z.ai | Apr 3, 2026(publication date) | zai_glm_5_1_model_card |
| Gemini 3.1 Pro | 69.2% | mcp_atlas | Thinking (High) | Feb 19, 2026(publication date) | google_gemini_3_1_pro_model_card | |
| DeepSeek-V4-Flash | 69% | mcp_atlas_public | think max, pass@1 | DeepSeek | Jun 25, 2026(publication date) | 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(publication date) | zai_glm_5_model_card |
| Subject | Value | Reported | Kind | Ingested |
|---|---|---|---|---|
| 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 |
documents that define or report scores for this benchmark
| 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 |
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.
| 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 |