Grok 2 (Dec '24) — benchmark results

Provider: xAI. Released 2024-12-12. Access: API.

Unified ELO 1480 ± 36, rank #921 of 1841 rated models, from 7 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
AA MATH-50077.8Accuracy (%)43.9
AA MMLU-Pro70.88Accuracy (%)37.8
Epoch AI - Scicode28.47Score37.6
AA LiveCodeBench26.67Pass@1 (%)28.5
AA GPQA Diamond51.01Accuracy (%)26.8
Artificial Analysis Intelligence Index8.04Intelligence Index25
AA Humanity's Last Exam3.8Accuracy (%)8.5

Interactive version: theaggregate.ai/model?slug=grok-2-dec-24 · How It Works · Data refreshed daily, snapshot 2026-07-25.