| Rank | Model | Score |
|---|---|---|
| 1 | claude-3-5-sonnet | 95.4 |
| 2 | claude-3-opus | 95.4 |
| 3 | gpt-4-0613 | 95.3 |
| 4 | gpt-4o | 95.3 |
| 5 | llama-3-1-70b-instruct | 93.8 |
| 6 | gemini-1-5-pro | 92.5 |
| 7 | llama-3-1-405b-instruct | 92.2 |
| 8 | mimo-v2-5-pro | 89.8 |
| 9 | claude-3-sonnet | 89 |
| 10 | command-r-plus | 88.6 |
| 11 | hermes-3-70b | 88.2 |
| 12 | qwen2-72b-instruct | 87.6 |
| 13 | gemini-1-5-flash | 86.5 |
| 14 | gemma-2-27b | 86.4 |
| 15 | claude-3-haiku | 85.9 |
| 16 | llama-3-1-nemotron-70b-instruct | 85.6 |
| 17 | qwen2-5-32b-instruct | 85.2 |
| 18 | phi-3-5-moe-instruct | 83.8 |
| 19 | mistral-nemo-instruct | 83.5 |
| 20 | qwen2-5-coder-32b-instruct | 83 |
| 21 | gemma-2-9b | 81.9 |
| 22 | granite-3-3-8b-base | 80.1 |
| 23 | gemma-3n-e4b-litert-preview | 78.6 |
| 24 | gemma-3n-e4b | 78.6 |
| 25 | qwen2-5-coder-7b-instruct | 76.8 |
1 phaseActive
No evaluations yet for this benchmark.