Grok 2 Mini: benchmark results
Provider: xAI. Released 2024-08-13. Access: API.
Aggregate Rating 1527 ± 22, rank #1987 of 10916 rated models, from 11 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (MathVista) | 68.1 | Score (%) | 53.9 |
| LLM Stats (DocVQA) | 93.2 | Score (%) | 51.8 |
| Aider Code Editing Leaderboard | 54.9 | Exercises completed correctly after one retry, pass_rate_2 ( | 45.2 |
| 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 |
| Arcee MMLU-Pro (BenchLM) | 72 | Accuracy (%) | 28.4 |
| BenchTable - Utility | 38.4 | Weighted Score (%) | 28.3 |
| LLM Stats Score | 8.14 | LLM Stats Score (conservative rating) | 23.2 |
| ZeroEval GPQA Diamond | 51 | GPQA Diamond Score | 23.2 |
Interactive version: theaggregate.ai/model?slug=grok-2-mini · How It Works · Data refreshed daily, snapshot 2026-11-08.