Models scored
25
evaluated
Modality
text
Category
agents
+2 more
Published
—
Search
| # | Model | Lab | Score |
|---|---|---|---|
| 01 | Claude Sonnet 4.5 | Anthropic | 50 |
| 02 | MiniMax M2.1 | MiniMax | 48 |
| 03 | Kimi K2-Thinking-0905 | Moonshot AI | 47 |
| 04 | MiniMax M2 | MiniMax | 46 |
| 05 | Claude Opus 4.1 | Anthropic | 43 |
| 06 | Nova 2 Pro | Amazon | 41 |
| 07 | Claude Haiku 4.5 | Anthropic | 41 |
| 08 | GLM-4.6 | Zhipu AI | 41 |
| 09 | LongCat-Flash-Chat | Meituan | 40 |
| 10 | Claude Opus 4 | Anthropic | 39 |
| 11 | DeepSeek-V3.2-Exp | DeepSeek | 38 |
| 12 | GLM-4.5 | Zhipu AI | 38 |
| 13 | Claude Sonnet 4 | Anthropic | 36 |
| 14 | Claude 3.7 Sonnet | Anthropic | 35 |
| 15 | LongCat-Flash-Lite | Meituan | 34 |
| 16 | GLM-4.7 | Zhipu AI | 33 |
| 17 | Nova 2 Lite | Amazon | 33 |
| 18 | DeepSeek-V3.1 | DeepSeek | 31 |
| 19 | MiMo-V2-Flash | Xiaomi | 31 |
| 20 | Kimi K2 Instruct | Moonshot AI | 30 |
| 21 | GLM-4.5-Air | Zhipu AI | 30 |
| 22 | Nemotron 3 Super (120B A12B) | NVIDIA | 26 |
| 23 | Kimi K2-Instruct-0905 | Moonshot AI | 25 |
| 24 | Nemotron 3 Nano (30B A3B) | NVIDIA | 9 |
| 25 | DeepSeek-R1-0528 | DeepSeek | 6 |
25 of 25 models · score normalized 0–100 where available