Grok 4.20 (Reasoning) — benchmark results
Grok 4.20 evaluated with reasoning enabled. Provider: xAI. Released 2026-02-17. Access: API.
Unified ELO 1790 ± 32, rank #150 of 1776 rated models, from 46 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SpeechMap Compliance | 98.2 | % Requests Completed | 98.9 |
| Wolfram LLM Benchmarking Project | 66.3 | Correct Functionality (%) | 95.8 |
| AI Chess Leaderboard (Reasoning) | 1522 | Elo | 94.3 |
| BenchTable | 76.8 | Total Score (%) | 94.2 |
| AI for Education SEND | 83.94 | Accuracy (%) | 94.1 |
| FutureX | 47.22 | Overall Score (latest week, %) | 92.9 |
| LLM Chess (Saplin) | 843 | ELO | 91.4 |
| AI for Education Pedagogy - Science | 91.8 | Accuracy (%) | 90.7 |
| AI for Education Pedagogy - Maths | 88.89 | Accuracy (%) | 88.6 |
| CLBench | 22.2 | Solving Rate (%) | 88.6 |
| AI Chess Leaderboard (Continuation) | 1091 | Elo | 85.6 |
| AI for Education Pedagogy - Primary | 91.08 | Accuracy (%) | 84.3 |
Interactive version: theaggregate.ai/model?slug=grok-4-20-reasoning · How the rankings work · Data refreshed daily, snapshot 2026-07-22.