Grok 3 Mini (Low): benchmark results
Grok 3 Mini evaluated at the low reasoning-effort setting. Provider: xAI. Released 2025-02-17. Access: API.
Aggregate Rating 1617 ± 21, rank #656 of 2168 rated models, from 33 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| MATH Level 5 | 90.94 | Accuracy (%) | 81.3 |
| Confabulation Leaderboard (Lechmazur) | 10.89 | Confabulation rate % (lower is better) | 77.7 |
| Olfactory Perception Benchmark - Rate-All-That-Apply | 36 | Score (%) on rate-all-that-apply descriptor profiling (selec | 67.5 |
| Olfactory Perception Benchmark - Smell Identification | 73.3 | Score (%) on smell identification (pick the odor source, suc | 65 |
| Vals AI TaxEval v2 | 72.98 | Accuracy (%) | 61.8 |
| Generalization V1 (Lechmazur) | 1.9 | Avg Rank (lower is better) | 55.6 |
| Olfactory Perception Benchmark - Odor Pleasantness | 72.6 | Score (%) on odor pleasantness paired comparison (which of t | 55 |
| NYT Connections Older Models | 14 | Score (%) | 52.7 |
| Olfactory Perception Benchmark - Odor Primary Descriptor | 73.1 | Score (%) on odor primary descriptor identification (one of | 52.5 |
| Epoch AI - GPQA Diamond | 76.26 | Accuracy (%) | 52.2 |
| Vals AI LegalBench | 81.92 | Accuracy (%) | 48 |
| Vals AI MGSM | 90.36 | Accuracy (%) | 45.9 |
Interactive version: theaggregate.ai/model?slug=grok-3-mini-low · How It Works · Data refreshed daily, snapshot 2026-10-20.