Models scored
43
evaluated
Modality
text
Category
agents
+2 more
Published
—
Search
| # | Model | Lab | Score |
|---|---|---|---|
| 01 | Claude Fable 5 | Anthropic | 80 |
| 02 | Claude Mythos Preview | Anthropic | 78 |
| 03 | Claude Opus 4.8 | Anthropic | 69 |
| 04 | Grok 4.5 | xAI | 65 |
| 05 | GPT-5.6 Sol | OpenAI | 65 |
| 06 | Claude Opus 4.7 | Anthropic | 64 |
| 07 | GPT-5.6 Terra | OpenAI | 63 |
| 08 | Claude Sonnet 5 | Anthropic | 63 |
| 09 | GPT-5.6 Luna | OpenAI | 63 |
| 10 | GLM-5.2 | Zhipu AI | 62 |
| 11 | Muse Spark 1.1 | Meta | 62 |
| 12 | Qwen3.7 Max | Alibaba Cloud / Qwen Team | 61 |
| 13 | MiniMax M3 | MiniMax | 59 |
| 14 | Gemini 3.6 Flash | 59 | |
| 15 | GPT-5.5 | OpenAI | 59 |
| 16 | Kimi K2.6 | Moonshot AI | 59 |
| 17 | GLM-5.1 | Zhipu AI | 58 |
| 18 | Hy3 | Tencent | 58 |
| 19 | GPT-5.4 | OpenAI | 58 |
| 20 | Qwen3.7-Plus | Alibaba Cloud / Qwen Team | 58 |
| 21 | Seed 2.1 Pro | ByteDance | 57 |
| 22 | MiMo-V2.5-Pro | Xiaomi | 57 |
| 23 | Seed 2.1 Turbo | ByteDance | 57 |
| 24 | GPT-5.3 Codex | OpenAI | 57 |
| 25 | Qwen3.6 Plus | Alibaba Cloud / Qwen Team | 57 |
| 26 | GPT-5.2 Codex | OpenAI | 56 |
| 27 | MiniMax M2.7 | MiniMax | 56 |
| 28 | MiMo-V2.5 | Xiaomi | 56 |
| 29 | DeepSeek-V4-Pro-Max | DeepSeek | 55 |
| 30 | MiniMax M2.5 | MiniMax | 55 |
| 31 | Gemini 3.5 Flash | 55 | |
| 32 | GPT-5.4 mini | OpenAI | 54 |
| 33 | Gemini 3.1 Pro | 54 | |
| 34 | Gemini 3.5 Flash-Lite | 54 | |
| 35 | Qwen3.6-27B | Alibaba Cloud / Qwen Team | 54 |
| 36 | MAI-Thinking-1 | Microsoft | 53 |
| 37 | DeepSeek-V4-Flash-Max | DeepSeek | 53 |
| 38 | Muse Spark | Meta | 52 |
| 39 | GPT-5.4 nano | OpenAI | 52 |
| 40 | MAI-Code-1-Flash | Microsoft | 51 |
| 41 | Kimi K2.5 | Moonshot AI | 51 |
| 42 | Qwen3.6-35B-A3B | Alibaba Cloud / Qwen Team | 50 |
| 43 | North Mini Code 1.0 | Cohere | 40 |
43 of 43 models · score normalized 0–100 where available