Grok 3 — benchmark results
xAI's Grok 3 flagship model for reasoning and general tasks (February 2025). Provider: xAI. Released 2025-02-17. Access: API.
Unified ELO 1601 ± 10, rank #475 of 1776 rated models, from 269 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| UGI Leaderboard | 63.47 | UGI Score | 99.3 |
| ProLLM - Entity Extraction | 85.5 | Score (%) | 97.9 |
| SpeechMap Compliance | 96.1 | % Requests Completed | 97.6 |
| EuroEval Swedish NLU - ScaLA SV | 71.91 | Linguistic acceptability Score (%) | 97.3 |
| EuroEval Icelandic NLU - Hotter and Colder Sentiment | 58.9 | Sentiment classification Score (%) | 97.2 |
| EuroEval Norwegian Knowledge | 71.26 | Knowledge Average Score (%) | 96.5 |
| EuroEval Finnish Common Sense Reasoning | 80.26 | Common Sense Reasoning Average Score (%) | 96.4 |
| EuroEval Portuguese Common Sense Reasoning | 93.05 | Common Sense Reasoning Average Score (%) | 96.4 |
| EuroEval Danish | 73.34 | Average Score (%) | 96.1 |
| EuroEval Icelandic | 56.5 | Average Score (%) | 95.4 |
| EuroEval French NLU - Allocine | 96.47 | Sentiment classification Score (%) | 95.3 |
| EuroEval Danish Knowledge | 93.1 | Knowledge Average Score (%) | 95.1 |
Interactive version: theaggregate.ai/model?slug=grok-3 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.