Coding on LiveCodeBench Overall v6
84.3AccuracyMetacognitive Harness
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Metacognitive HarnessBackbone=Sonnet-4.62026.05 | 84.3 | 10 | |
| o4-miniReasoning Setting=High, Leaderboard Rank=Top-12026.05 | 80.2 | — | |
| o3Reasoning Setting=High, Leaderboard Rank=Top-22026.05 | 75.8 | — | |
| Sonnet-4.6Evaluation Mode=Single-pass (Pass@1)2026.05 | 74.3 | — | |
| o4-miniReasoning Setting=Medium, Leaderboard Rank=Top-32026.05 | 74.2 | — |