Grok 2 mini: benchmark results
Provider: xAI. Access: API.
Unified ELO 1574 ± 42, rank #733 of 2656 rated models, from 9 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (MathVista) | 68.1 | Score (%) | 53.9 |
| LLM Stats (DocVQA) | 93.2 | Score (%) | 53.7 |
| BenchTable - Reasoning | 35.3 | Weighted Score (%) | 43 |
| BenchTable - Tech | 48.1 | Weighted Score (%) | 41.6 |
| BenchTable | 42.6 | Total Score (%) | 40.7 |
| BenchTable - STEM | 35.7 | Weighted Score (%) | 31.7 |
| BenchTable - Utility | 38.4 | Weighted Score (%) | 28.3 |
| LLM Stats Score | 8.58 | LLM Stats Score (conservative rating) | 25.3 |
| ZeroEval GPQA Diamond | 51 | GPQA Diamond Score | 24.1 |
Interactive version: theaggregate.ai/model?slug=grok-2-mini · How It Works · Data refreshed daily, snapshot 2026-09-19.