Models scored
27
evaluated
Modality
text
Category
general
+1 more
Published
—
Search
| # | Model | Lab | Score |
|---|---|---|---|
| 01 | Nemotron 3 Ultra (550B A55B) | NVIDIA | 82 |
| 02 | Hermes 3 70B | Nous Research | 81 |
| 03 | Nova 2 Pro | Amazon | 80 |
| 04 | Qwen3.7-Plus | Alibaba Cloud / Qwen Team | 79 |
| 05 | Qwen3.7 Max | Alibaba Cloud / Qwen Team | 79 |
| 06 | Qwen3.5-27B | Alibaba Cloud / Qwen Team | 77 |
| 07 | Qwen3.5-397B-A17B | Alibaba Cloud / Qwen Team | 77 |
| 08 | Qwen3.5-122B-A10B | Alibaba Cloud / Qwen Team | 76 |
| 09 | MAI-Code-1-Flash | Microsoft | 75 |
| 10 | Qwen3.6 Plus | Alibaba Cloud / Qwen Team | 74 |
| 11 | Command A+ | Cohere | 74 |
| 12 | Nemotron 3 Super (120B A12B) | NVIDIA | 73 |
| 13 | Mercury 2 | Inception | 71 |
| 14 | Nova 2 Lite | Amazon | 71 |
| 15 | Qwen3.5-35B-A3B | Alibaba Cloud / Qwen Team | 70 |
| 16 | MiniMax M2.1 | MiniMax | 70 |
| 17 | GPT OSS 120B High | OpenAI | 70 |
| 18 | MAI-Thinking-1 | Microsoft | 69 |
| 19 | Mistral Medium 3.5 | Mistral AI | 69 |
| 20 | Nova 2 Omni | Amazon | 69 |
| 21 | K-EXAONE-236B-A23B | LG AI Research | 67 |
| 22 | Qwen3.5-9B | Alibaba Cloud / Qwen Team | 65 |
| 23 | Qwen3.5-4B | Alibaba Cloud / Qwen Team | 59 |
| 24 | Mistral Small 4 | Mistral AI | 48 |
| 25 | Qwen3.5-2B | Alibaba Cloud / Qwen Team | 41 |
| 26 | Nova 2 Sonic | Amazon | 38 |
| 27 | Qwen3.5-0.8B | Alibaba Cloud / Qwen Team | 21 |
27 of 27 models · score normalized 0–100 where available