Coding on LiveCodeBench Medium v6
89.4Accuracyo4-mini
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| o4-miniReasoning Setting=High, Leaderboard Rank=Top-12026.05 | 89.4 | — | |
| Metacognitive HarnessBackbone=Sonnet-4.62026.05 | 87.6 | 1.1 | |
| o4-miniReasoning Setting=Medium, Leaderboard Rank=Top-22026.05 | 86.5 | — | |
| Sonnet-4.6Evaluation Mode=Single-pass (Pass@1)2026.05 | 86.5 | — | |
| o3Reasoning Setting=High, Leaderboard Rank=Top-32026.05 | 84.4 | — |