Benchmarks / Reasoning
SciUniverse
Uses overall Pass@1 averaged equally across 17 task families. Score: Pass@1 across 17 equally weighted task families. Collected by Jake Boggs' benchmark dashboard.
SciUniverse
Higher is better · best effort per model
full table below
| # | Model | Effort | Score |
|---|---|---|---|
| 1 | Fable 5.1 | max | 45.3% |
| 2 | GPT-6 Astra | xhigh | 32.5% |
| 3 | Opus 5 | max | 30.5% |
| 4 | Grok 4.6 | xhigh | 26.2% |
| 5 | Gemini 3.8 Flash | high | 14.6% |
| 6 | GPT-5.6 Sol | xhigh | 9.4% |