| anthropic/claude-opus-4-7 | 65.0% | 80.0% | 57.5% | 77.5% | 70.0% | $0.35 | 145s | 4 |
| openrouter/mistralai/mistral-large-2512 | 55.0% | 80.0% | 55.0% | 82.5% | 68.1% | $0.04 | 200s | 4 |
| openrouter/meta-llama/llama-4-maverick | 55.0% | 80.0% | 55.0% | 77.5% | 66.9% | - | 46s | 4 |
| openai/gpt-5.4 | 60.0% | 85.0% | 55.0% | 65.0% | 66.3% | $0.17 | 251s | 4 |
| anthropic/claude-sonnet-4-20250514 | 55.0% | 80.0% | 56.3% | 66.3% | 64.4% | $0.41 | 320s | 8 |
| openrouter/qwen/qwen3-coder | 55.0% | 75.0% | 50.0% | 75.0% | 63.7% | $0.07 | 1534s | 4 |
| openai/gpt-5.1-codex-mini | 45.0% | 85.0% | 55.0% | 65.0% | 62.5% | $0.02 | 110s | 4 |
| openrouter/deepseek/deepseek-v3.2 | 45.0% | 77.5% | 57.5% | 70.0% | 62.5% | $0.16 | 1651s | 6 |
| openrouter/moonshotai/kimi-k2.5 | 47.5% | 75.0% | 50.0% | 67.5% | 60.0% | $0.05 | 780s | 4 |