Benchmarks · knowledge
AA-Omniscience Science, Engineering & Math
AA-Omniscience Index (-100..100) on the Science, Engineering & Math questions only: right answers minus made-up ones, abstaining scores 0.
136 models · 267 results · data as of 2026-10-29 · artificialanalysis.ai ↗
Leaderboard
Opus 5.5 max
All results
267 rows| # | Model | Effort | Score |
|---|---|---|---|
| 1 | Opus 5.5 | max | 37.8 |
| 2 | Gemini 4 Argon | high | 34.4 |
| 3 | Opus 5.5 | xhigh | 33.8 |
| 4 | Fable 5.1 | max | 33.0 |
| 5 | Fable 5.1 | xhigh | 32.0 |
| 6 | Opus 5.5 | high | 30.1 |
| 7 | Fable 5.1 | high | 29.8 |
| 8 | Grok 4.7 | xhigh | 29.6 |
| 9 | GPT-6 Astra | high | 29.3 |
| 10 | Sonnet 5.5 | max | 29.1 |
| 11 | GPT-6 Astra | xhigh | 29.0 |
| 12 | Opus 5.5 | low | 28.3 |
| 13 | Muse Spark 1.1 | xhigh | 28.1 |
| 14 | Opus 5.5 | medium | 28.0 |
| 15 | GPT-6.1 Sol | xhigh | 28.0 |
| 16 | GPT-6 Astra | max | 27.6 |
| 17 | GPT-6 Astra | medium | 27.5 |
| 18 | GPT-6.1 Sol | high | 26.7 |
| 19 | Opus 5 | max | 26.7 |
| 20 | Grok 4.7 | high | 26.4 |
| 21 | GPT-6.1 Sol | max | 26.3 |
| 22 | Grok 4.6 | high | 25.8 |
| 23 | GPT-6 Astra | low | 25.7 |
| 24 | Muse Spark 1.3 | max | 25.6 |
| 25 | Muse Spark 1.2 | xhigh | 25.3 |
| 26 | Fable 5.1 | medium | 25.2 |
| 27 | Grok 4.6 | medium | 25.1 |
| 28 | Grok 4.6 | xhigh | 25.1 |
| 29 | Gemini 3.8 Flash | high | 25.0 |
| 30 | Opus 5 | xhigh | 24.8 |