OpenAI · model passport

GPT 5 Codex

gpt-5-codex

Best percentile: 97.9LiveBench
Composite standing: 72.9shrunk · 5/27 axes

What the data says

Benchmarked on 5 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

97.9 pct — LiveBench (78.2%)
95.9 pct — MMLU-Pro (Artificial Analysis) (86.5%)
94.7 pct — LiveCodeBench (Artificial Analysis) (84.0%)

Uneven: 43.4 percentile points between its best and worst axis — 97.9 pct on LiveBench versus 54.5 pct on Terminal-Bench.

LiveBench97.9 pct78.2%Verify →
MMLU-Pro (Artificial Analysis)95.9 pct86.5%Verify →
LiveCodeBench (Artificial Analysis)94.7 pct84.0%Verify →
IFBench (Artificial Analysis)90.1 pct74.1%Verify →
Terminal-Bench54.5 pct44.3%Verify →
OverallNot benchmarked
WebDev ArenaNot benchmarked
Vision ArenaNot benchmarked
Factuality ArenaNot benchmarked
Search ArenaNot benchmarked
Document ArenaNot benchmarked
Agent ArenaNot benchmarked
GPQA DiamondNot benchmarked
AIME (math)Not benchmarked
FrontierMathNot benchmarked
SimpleQA VerifiedNot benchmarked
ARC-AGI-2Not benchmarked
Humanity's Last ExamNot benchmarked
SimpleBenchNot benchmarked
BFCL v4 (function calling)Not benchmarked
SWE-bench Verified (live board)Not benchmarked
Terminal-Bench 4.0Not benchmarked
HHEM Hallucination (Vectara)Not benchmarked
SWE-bench VerifiedNot benchmarked
CodingNot benchmarked
Instruction followingNot benchmarked
Hard promptsNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

gpt-5-codex stands at 72.9 (raw mean 86.6) — measured on 5 of 27 axes.
standingtemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →