Grok 4.7: benchmark results
Provider: xAI. Access: API.
Unified ELO 1987 ± 16, rank #19 of 2622 rated models, from 36 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| LLM Stats (SWE-Marathon) | 46 | Score (%) | 100 |
| Next.js Agent Evals (OpenCode) - Success Rate | 94 | Evals passed, pass@4 (%) | 100 |
| Vals AI Harvey Legal Agent Bench | 19.58 | Accuracy (%) | 93.5 |
| LM Market Cap LMC Score | 88.8 | LMC Score (0-100) | 90 |
| SvelteBench | 98.9 | Average pass@1 (%) | 87.9 |
| RuneBench | 7892 | Total Peak XP Rate (XP/min) | 86.8 |
| LLM Stats (DeepSWE 1.1) | 71 | Score (%) | 82.4 |
| Vals AI Vibe Code Bench | 75.86 | Accuracy (%) | 80.9 |
| Vals AI Terminal-Bench 2.1 | 76.03 | Accuracy (%) | 80 |
| AI Chess Leaderboard (Continuation) | 957 | Elo | 79.5 |
| AI Chess Leaderboard (Reasoning) | 894 | Elo | 73.4 |
| Next.js Agent Evals (OpenCode) - Success Rate with AGENTS.md | 94 | Evals passed with bundled Next.js docs in AGENTS.md, pass@4 | 72.7 |
Interactive version: theaggregate.ai/model?slug=grok-4-7 · How It Works · Data refreshed daily, snapshot 2026-09-22.