FrontierSWEV2
Leaderboard
Scores across all 34 tasks. Each model runs 5 trials per task with a 20-hour budget.
Bar and value are mean@5, whiskers span worst@5–best@5. Green marks the top result. Cost and time are per-trial averages.
*Gemini 4 Argon: Cache hit rate is much lower due to a non-production setting.
Task Highlights
See all 34 tasks
Analysis
Score for every model on every task; stronger color is higher. The "Best"column is the highest score any model achieved on that task. Click a cell for that pair's traces; click a Best cell to open the top-scoring run's trace.
Mean score against cost per run or wall-clock time. Filter by tag or pick specific tasks.
Tasks: all 34 ▾
Models: all 22 ▾
*Gemini 4 Argon: Cache hit rate is much lower due to a non-production setting.
Share of a model's runs scoring at or above each reward threshold, pooled over every task. The dashed Best of all curve takes the highest-scoring run on each task regardless of model. Click a model below to toggle its curve.