Motif-2-12.7B (Reasoning): benchmark results
Motif-2-12.7B evaluated with reasoning enabled. Provider: Motif. Released 2025-11-07. Access: Open.
Unified ELO 1503 ± 1, rank #837 of 1761 rated models, from 17 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| AA IFBench | 57.01 | Accuracy (%) | 68.3 |
| AA Humanity's Last Exam | 8.76 | Accuracy (%) | 50.8 |
| AA TAU-2 Bench | 46.49 | Accuracy (%) | 50.2 |
| AA GPQA Diamond | 69.49 | Accuracy (%) | 47.4 |
| Artificial Analysis Intelligence Index | 6.96 | Intelligence Index | 40.8 |
| BenchmarkList ECI | 102.77 | Capability Index (ECI) | 39.4 |
| AA Omniscience - Law | 9.62 | Accuracy (%) | 37.4 |
| AA Omniscience - Humanities & Social Sciences | 16.68 | Accuracy (%) | 35.3 |
| AA Omniscience - Science, Engineering & Mathematics | 23.2 | Accuracy (%) | 31.7 |
| AA Omniscience - Health | 15.5 | Accuracy (%) | 29.3 |
| AA-Omniscience Accuracy | 15.17 | Accuracy (%) | 25.8 |
| AA Terminal-Bench Hard | 3.79 | Accuracy (%) | 25.6 |
Interactive version: theaggregate.ai/model?slug=motif-2-12-7b-reasoning · How It Works · Data refreshed daily, snapshot 2026-09-05.