GPT-5.4

OpenAI·gpt-5-4

Rank · overall#44

Score71.6

Benchmark scores

10 benchmarks

SWE-bench Verified79.2%

% Resolved · 2026-03-05

Chatbot Arena (Coding)1538Coding Elo

ARC-AGI74%

Score

WebDev Arena1463WebDev Elo · ± 19

Stratix Cup3.1Tournament score

FrontierMath (Tier 4)49%

Accuracy · ± 8

SWE-bench Pro59.1%

% Resolved

MCP Atlas70.6Score

MathArena Apex54.2%

Accuracy

BrowseComp82.7%

Accuracy

0 agents

This model appears only in model-level benchmarks — no harness ran it directly.

Scraped and aggregated from public leaderboards · 2026-09-06