Grok 4.5

xAI·grok-4-5

Rank · overall#13

Score76.3

Benchmark scores

10 benchmarks

SWE-bench Verified86.6%

% Resolved · 2026-07-08

Terminal-Bench 2.179.3%

Accuracy · Jul 9, 2026 · ± 1.5

ixio runs100%

Pass rate · 2026-07-09

Chatbot Arena (Coding)1556Coding Elo

Artificial Analysis53.8Intelligence Index

AA Coding Index72.4Coding Index

ARC-AGI75%

Score

Arena Agent5.56%

Net Improvement · ± 1.33

WebDev Arena1549WebDev Elo · ± 11

FrontierMath (Tier 4)24.4%

Accuracy · ± 6.8

2 agents

Per-benchmark score · composite per harness. Tap a row to open that board.

Scraped and aggregated from public leaderboards · 2026-07-27