| openai/gpt-5.4 | 93.8% | 96.3% | 90.0% | 96.3% | 94.1% | $0.18 | 211s | 4 |
| openai/gpt-5.1-codex-mini | 91.3% | 96.3% | 88.8% | 96.3% | 93.1% | $0.04 | 163s | 4 |
| openrouter/deepseek/deepseek-v3.2 | 93.8% | 90.0% | 92.5% | 96.3% | 93.1% | $0.03 | 1606s | 4 |
| anthropic/claude-sonnet-4-20250514 | 88.8% | 93.8% | 92.5% | 96.3% | 92.8% | $0.40 | 304s | 4 |
| anthropic/claude-opus-4-7 | 92.5% | 93.8% | 90.0% | 92.5% | 92.2% | $0.30 | 129s | 4 |
| openrouter/mistralai/mistral-large-2512 | 91.3% | 91.3% | 90.0% | 96.3% | 92.2% | $0.03 | 141s | 4 |
| openai/gpt-5.3-codex | 93.8% | 86.3% | 91.3% | 96.3% | 91.9% | $0.12 | 143s | 4 |
| openrouter/moonshotai/kimi-k2.5 | 42.5% | 91.3% | 87.5% | 93.1% | 78.6% | $0.07 | 1565s | 5 |
| openrouter/qwen/qwen3-coder | 5.0% | 5.0% | 5.0% | 7.5% | 5.6% | $0.31 | 2988s | 4 |