Grok 4.5 — benchmark results
xAI's flagship Grok 4.5 model for reasoning and general tasks. Provider: xAI. Released 2026-07-08. Access: API.
Unified ELO 1882 ± 17, rank #77 of 1776 rated models, from 89 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| Benchmarks.bio - BioSecBench-Surveillance | 53.3 | Pass Rate (%) | 100 |
| Long-Horizon Terminal-Bench | 50.5 | Mean Score (%) | 100 |
| Vals AI SkillsBench | 66.03 | Accuracy (%) | 100 |
| UGI Leaderboard | 62.32 | UGI Score | 99.1 |
| AI for Education Pedagogy - Secondary | 89.31 | Accuracy (%) | 97.7 |
| BenchLM | 76.7 | Overall Score | 97 |
| AI for Education Pedagogy | 89.66 | Accuracy (%) | 96.8 |
| AI for Education Pedagogy - Science | 93.44 | Accuracy (%) | 96.6 |
| ZeroEval GPQA Diamond | 93 | GPQA Diamond Score | 96.5 |
| Kagi LLM Benchmark | 83.5 | Accuracy (%) | 96.4 |
| Vals AI GPQA | 92.93 | Accuracy (%) | 96.3 |
| Vals AI Harvey Legal Agent Bench | 12.92 | Accuracy (%) | 95.8 |
Interactive version: theaggregate.ai/model?slug=grok-4-5 · How the rankings work · Data refreshed daily, snapshot 2026-07-22.