No valid scored ECI row in the current public dataset. The lab remains in the tracked scope and will appear when comparable data becomes available.
Model roster · 46 tracked systems
Every major contender, on one field.
This roster covers OpenAI, Anthropic, Google, xAI, Meta, Mistral, Microsoft, Moonshot, Alibaba/Qwen, Zhipu, DeepSeek, MiniMax, 01.AI, Baichuan, ByteDance and other tracked labs.
See roster and deduplication rules →Comparable ECI records
Model leaderboard
“Open weights” follows the source’s access label. It does not automatically mean unrestricted, commercially usable, or fully open-source.
Showing 46 of 46 tracked models
| Model | Ecosystem | Lab | Access | Released | ECI |
|---|---|---|---|---|---|
| GPT-5.6 Sol (pro, max) Confident source confidence | Western | OpenAI | API | 161.7 rank 1 | |
| GPT-5.5 Pro (xhigh) Likely source confidence | Western | OpenAI | API | 160.9 rank 2 | |
| Claude Fable 5 (max) Confident source confidence | Western | Anthropic | API | 160.7 rank 3 | |
| Claude Opus 5 Confident source confidence | Western | Anthropic | API | 159.4 rank 4 | |
| GPT-5.5 (xhigh) Likely source confidence | Western | OpenAI | API | 158.5 rank 5 | |
| Claude Opus 4.8 Confident source confidence | Western | Anthropic | API | 158.0 rank 7 | |
| Kimi K3 (max) Confident source confidence | Chinese | Moonshot AI | API | 155.6 rank 11 | |
| Gemini 3.1 Pro Preview Likely source confidence | Western | Google DeepMind | API | 154.9 rank 15 | |
| Gemini 3.5 Flash (high) Confident source confidence | Western | Google DeepMind | API | 154.6 rank 17 | |
| Muse Spark Confident source confidence | Western | Meta AI | API | 154.3 rank 18 | |
| Grok 4.5 (high) Likely source confidence | Western | xAI | API | 153.6 rank 20 | |
| Gemini 3 Pro Preview Unknown source confidence | Western | Google DeepMind | API | 153.3 rank 22 | |
| Qwen3.7-Max Confident source confidence | Chinese | Alibaba / Qwen | API | 153.1 rank 24 | |
| Grok 4.20 Likely source confidence | Western | xAI | API | 152.6 rank 25 | |
| GLM-5.2 Confident source confidence | Chinese | Zhipu AI / Z.ai | Open weights · unrestricted | 151.4 rank 26 | |
| Kimi K2.6 Confident source confidence | Chinese | Moonshot AI | Open weights · unrestricted | 151.0 rank 27 | |
| GLM-5.1 Confident source confidence | Chinese | Zhipu AI / Z.ai | Not reported | 150.4 rank 29 | |
| Kimi K2.7 Code Confident source confidence | Chinese | Moonshot AI | Open weights · unrestricted | 149.7 rank 33 | |
| Qwen 3.6 Max (Preview) Unverified source confidence | Chinese | Alibaba / Qwen | Not reported | 149.7 rank 34 | |
| Qwen 3.6 Plus (2026-04-02) Confident source confidence | Chinese | Alibaba / Qwen | API | 149.2 rank 36 | |
| Grok 4.3 Beta Likely source confidence | Western | xAI | Hosted access (no API) | 149.0 rank 37 | |
| DeepSeek v4 Pro (max) Likely source confidence | Chinese | DeepSeek | Open weights · unrestricted | 148.7 rank 39 | |
| MiniMax-M2.5 Likely source confidence | Chinese | MiniMax | Open weights · unrestricted | 147.1 rank 42 | |
| MiniMax-M3 Confident source confidence | Chinese | MiniMax | API | 147.0 rank 45 | |
| DeepSeek-V3.2 (Thinking; Fireworks) Likely source confidence | Chinese | DeepSeek | Open weights · unrestricted | 146.6 rank 49 | |
| GLM-5 Likely source confidence | Chinese | Zhipu AI / Z.ai | Open weights · unrestricted | 146.4 rank 51 | |
| MiniMax-M2.7 Confident source confidence | Chinese | MiniMax | Open weights · non-commercial | 145.7 rank 55 | |
| DeepSeek-V3.2-Exp Confident source confidence | Chinese | DeepSeek | Open weights · unrestricted | 144.9 rank 56 | |
| Qwen3-235B-A22B (Jul 2025) Likely source confidence | Chinese | Alibaba / Qwen | Open weights · unrestricted | 144.8 rank 58 | |
| Gemma 4 31B IT Likely source confidence | Western | Google DeepMind | Open weights · restricted use | 141.9 rank 74 | |
| gpt-oss-120b Confident source confidence | Western | OpenAI | Open weights · unrestricted | 140.6 rank 80 | |
| Mistral Medium 3 Unknown source confidence | Western | Mistral AI | API | 135.3 rank 94 | |
| Magistral Small 1.1 Confident source confidence | Western | Mistral AI | Open weights · unrestricted | 133.1 rank 97 | |
| Llama 4 Maverick (FP8) Likely source confidence | Western | Meta AI | Open weights · restricted use | 133.0 rank 98 | |
| Phi-4 Confident source confidence | Western | Microsoft | Open weights · unrestricted | 131.1 rank 101 | |
| Llama 4 Scout Likely source confidence | Western | Meta AI | Open weights · restricted use | 130.5 rank 105 | |
| Mistral Large 2 Likely source confidence | Western | Mistral AI | Open weights · non-commercial | 128.8 rank 111 | |
| phi-3-small 7.4B Confident source confidence | Western | Microsoft | Open weights · unrestricted | 121.6 rank 127 | |
| phi-3-medium 14B Likely source confidence | Western | Microsoft | Open weights · unrestricted | 121.0 rank 130 | |
| Yi-34B Confident source confidence | Chinese | 01.AI | Open weights · restricted use | 117.1 rank 141 | |
| Yi 6B Confident source confidence | Chinese | 01.AI | Open weights · restricted use | 104.5 rank 160 | |
| Baichuan2-13B Confident source confidence | Chinese | Baichuan | Open weights · restricted use | 102.9 rank 161 | |
| Baichuan 2-7B Confident source confidence | Chinese | Baichuan | Open weights · restricted use | 96.0 rank 168 | |
| Baichuan1-7B Confident source confidence | Chinese | Baichuan | Open weights · non-commercial | 90.0 rank 175 | |
| Yi-Lightning Confident source confidence | Chinese | 01.AI | API | 0.0 rank 234 | |
| video-SALMONN 2+ Likely source confidence | Chinese | ByteDance | Not reported | 0.0 rank 205 |
Coverage gaps
Popular labs missing a comparable score
No valid scored ECI row in the current public dataset. The lab remains in the tracked scope and will appear when comparable data becomes available.
No valid scored ECI row in the current public dataset. The lab remains in the tracked scope and will appear when comparable data becomes available.