Grok 2 (1212): benchmark results
December 12, 2024 xAI Grok 2 snapshot. Provider: xAI. Released 2024-12-12. Access: API.
Unified ELO 1546 ± 1, rank #454 of 1392 rated models, from 592 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Arcadia CommonsenseQA | 86.24 | Accuracy (%) | 100 |
| OpenVLM MMT-Bench - CIM | 85 | Score (%) | 100 |
| OpenVLM MMT-Bench - Image Dense Captioning | 94.7 | Score (%) | 100 |
| OpenVLM MMT-Bench - Furniture Keypoint Detection | 80 | Score (%) | 99.8 |
| OpenVLM MMT-Bench - Gesture Recognition | 85 | Score (%) | 99.8 |
| OpenVLM MMT-Bench - VR | 88.1 | Score (%) | 99.5 |
| OpenVLM MMT-Bench - Camouflage Object Detection | 85 | Score (%) | 99 |
| OpenVLM MMT-Bench - Fashion Recognition | 90 | Score (%) | 99 |
| OpenVLM MMT-Bench - Film and Television Recognition | 100 | Score (%) | 99 |
| OpenVLM MMT-Bench - KD | 76 | Score (%) | 99 |
| OpenVLM MMT-Bench - Loc | 73.5 | Score (%) | 99 |
| OpenVLM MMT-Bench - Navigation | 95 | Score (%) | 99 |
Interactive version: theaggregate.ai/model?slug=grok-2-1212 · How It Works · Data refreshed daily, snapshot 2026-09-05.