Coding on LiveCodeBench Hard v6
74.6AccuracyMetacognitive Harness
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Metacognitive HarnessBackbone=Sonnet-4.62026.05 | 74.6 | 19.6 | |
| o4-miniReasoning Setting=High, Leaderboard Rank=Top-12026.05 | 63.5 | — | |
| o3Reasoning Setting=High, Leaderboard Rank=Top-22026.05 | 57.1 | — | |
| Sonnet-4.6Evaluation Mode=Single-pass (Pass@1)2026.05 | 55 | — | |
| o4-miniReasoning Setting=Medium, Leaderboard Rank=Top-32026.05 | 52.7 | — |