MuirBench leaderboard
As of November 14, 2026, among the results listed here, Thinking Machines Inkling 2 Small has the highest reported MuirBench score, 79.2%, published by Thinking Machines, ahead of Perceptron Mk1 at 69.7%. 2 models have a MuirBench result in our records.
Scores as the model makers published them, not re-run by us; each row links to its announcement.
Best reported score
79.2%
T Thinking Machines Inkling 2 Small
Reported by Thinking Machines, November 9, 2026
2 models ranked · 2 makers
| Rank | Model | Score | Setting | Reported by | Date |
|---|---|---|---|---|---|
| 1 | T Inkling 2 Small | 79.2% | Not published | Thinking Machines | November 9, 2026 (model release) |
| 2 | Perceptron Mk1 | 69.7% | Not published | Perceptron | May 12, 2026 (model release) · read from the maker's chart |
How much to trust these numbers
- Source
- Reported by the model makers themselves. Not re-run by LLMBenchmark or anyone independent.
- Settings
- All ranked results use the same reported setting.
- Spread
- 79.2% to 69.7% across 2 models.
- Freshness
- Newest result published November 9, 2026; oldest May 12, 2026.
- Charts
- Some values were read from charts in the announcements. Two independent readings had to match exactly.
What MuirBench measures
MuirBench tests models with 2,600 multiple-choice questions across 12 tasks involving multiple images; the search results do not explain how its score is calculated. Source: MuirBench