Models scored
42
evaluated
Modality
text
Category
agents
+4 more
Published
—
Search
| # | Model | Lab | Score |
|---|---|---|---|
| 01 | Claude Opus 5 | Anthropic | 62 |
| 02 | Claude Fable 5 | Anthropic | 61 |
| 03 | GPT-5.6 Sol | OpenAI | 58 |
| 04 | Kimi K3 | Moonshot AI | 56 |
| 05 | Claude Opus 4.8 | Anthropic | 55 |
| 06 | Claude Sonnet 5 | Anthropic | 54 |
| 07 | Claude Opus 4.6 | Anthropic | 54 |
| 08 | GPT-5.6 Terra | OpenAI | 53 |
| 09 | GPT-5.6 Luna | OpenAI | 53 |
| 10 | Grok 4.5 | xAI | 51 |
| 11 | Claude Opus 4.7 | Anthropic | 51 |
| 12 | MiniMax M3 | MiniMax | 48 |
| 13 | GPT-5.4 | OpenAI | 48 |
| 14 | MiMo-V2-Pro | Xiaomi | 48 |
| 15 | Gemini 3.6 Flash | 47 | |
| 16 | Claude Sonnet 4.6 | Anthropic | 47 |
| 17 | MiMo-V2-Omni | Xiaomi | 47 |
| 18 | Gemini 3.5 Flash | 46 | |
| 19 | DeepSeek-V4-Pro-Max | DeepSeek | 44 |
| 20 | Qwen3.7 Max | Alibaba Cloud / Qwen Team | 44 |
| 21 | MiMo-V2.5-Pro | Xiaomi | 43 |
| 22 | GLM-5.1 | Zhipu AI | 43 |
| 23 | DeepSeek-V4-Flash-Max | DeepSeek | 40 |
| 24 | Kimi K2.6 | Moonshot AI | 40 |
| 25 | GPT-5.4 mini | OpenAI | 40 |
| 26 | Nemotron 3 Ultra (550B A55B) | NVIDIA | 39 |
| 27 | MiniMax M2.7 | MiniMax | 39 |
| 28 | Muse Spark | Meta | 39 |
| 29 | Qwen3.6 Plus | Alibaba Cloud / Qwen Team | 39 |
| 30 | Qwen3.6-27B | Alibaba Cloud / Qwen Team | 39 |
| 31 | Gemini 3.5 Flash-Lite | 38 | |
| 32 | GPT-5.5 | OpenAI | 38 |
| 33 | GPT-5.4 nano | OpenAI | 37 |
| 34 | Grok 4.3 | xAI | 37 |
| 35 | Qwen3.6-35B-A3B | Alibaba Cloud / Qwen Team | 35 |
| 36 | Qwen3.5-122B-A10B | Alibaba Cloud / Qwen Team | 33 |
| 37 | Gemini 3.1 Pro | 33 | |
| 38 | Qwen3.5-397B-A17B | Alibaba Cloud / Qwen Team | 32 |
| 39 | Qwen3.7-Plus | Alibaba Cloud / Qwen Team | 32 |
| 40 | Mistral Medium 3.5 | Mistral AI | 31 |
| 41 | Claude Haiku 4.5 | Anthropic | 30 |
| 42 | Gemma 4 31B | 26 |
42 of 42 models · score normalized 0–100 where available