Grok 3 Mini Fast: benchmark results
Provider: xAI. Access: API.
Aggregate Rating 1640 ± 46, rank #694 of 10916 rated models, from 18 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| CLARITY (BIRD) - Semantic Ambiguity (Multi-Facet) | 66.8 | Execution accuracy (%) on multi-turn BIRD instances whose re | 100 |
| CLARITY (BIRD) - Value Ambiguity (Multi-Facet) | 53.8 | Execution accuracy (%) on multi-turn BIRD instances whose re | 100 |
| CLARITY (Spider) - Lexical Ambiguity (Uni-Facet) | 78.2 | Execution accuracy (%) on multi-turn Spider instances whose | 100 |
| CLARITY (Spider) - Semantic Ambiguity (Multi-Facet) | 77.8 | Execution accuracy (%) on multi-turn Spider instances whose | 100 |
| CLARITY (Spider) - Semantic Ambiguity (Uni-Facet) | 82.4 | Execution accuracy (%) on multi-turn Spider instances whose | 100 |
| CLARITY (BIRD) - Lexical Ambiguity (Uni-Facet) | 66.2 | Execution accuracy (%) on multi-turn BIRD instances whose re | 75 |
| CLARITY (BIRD) - Value Ambiguity (Uni-Facet) | 44.1 | Execution accuracy (%) on multi-turn BIRD instances whose re | 75 |
| CLARITY (Spider) - Lexical Ambiguity (Multi-Facet) | 75.8 | Execution accuracy (%) on multi-turn Spider instances whose | 75 |
| CLARITY (Spider) - Value Ambiguity (Uni-Facet) | 76.8 | Execution accuracy (%) on multi-turn Spider instances whose | 75 |
| AEPC-QA (Closed-Book) | 61.03 | Accuracy (%) answering from the model's own knowledge on AEP | 68 |
| CLARITY (BIRD) - Unanswerable Column (Uni-Facet) | 64 | Execution accuracy (%) on multi-turn BIRD instances whose re | 50 |
| CLARITY (Spider) - Unanswerable Column (Multi-Facet) | 94 | Execution accuracy (%) on multi-turn Spider instances whose | 50 |
Interactive version: theaggregate.ai/model?slug=grok-3-mini-fast · How It Works · Data refreshed daily, snapshot 2026-11-08.