Model record

GPT-5

high

OpenAI · released Aug 7, 2025

Overall standing

Overall
45.5rank 42 of 63
45.5 is at approximately the 34th percentile of the ranked Overall field. The field spans 19.0 to 62.2, with a median of 49.4.
8 of 8 measured
Category standingsReasoning 65.1Coding 39.1Math 5.7Agentic 19.6
Reasoning
65.1rank 31 of 63
65.1 is at approximately the 52th percentile of the ranked Reasoning field. The field spans 31.6 to 73.3, with a median of 65.0.
4 of 4 measured
Coding
39.1rank 55 of 63
39.1 is at approximately the 13th percentile of the ranked Coding field. The field spans 10.4 to 72.4, with a median of 54.5.
2 of 2 measured
Math
5.7rank 32 of 63
5.7 is at approximately the 50th percentile of the ranked Math field. The field spans 0.0 to 32.3, with a median of 5.7.
1 of 1 measured
Agentic
19.6rank 30 of 63
19.6 is at approximately the 52th percentile of the ranked Agentic field. The field spans 3.3 to 33.4, with a median of 19.0.
1 of 1 measured
Model factsProprietary · $1.3 / $10.0 per 1M

Model facts come from the provider page. Listed API prices carry a separate first-party source and check date.

Provider
OpenAI
Released
Weights
Proprietary
Context window
400,000 tokens
Input price / Mtok
$1.3
Output price / Mtok
$10.0
Price source
Official pricing (opens in a new tab)
Reasoning effort
high reasoning

Scores and sources

Measured scores retain their source and retrieval date. Missing scores are not treated as zero.

Benchmark scores, evaluation settings, sources, and retrieval dates for GPT-5
BenchmarkCategoryScoreEvaluation settingsSource
Terminal-Bench v2.1Coding35.2Artificial Analysis independent run; 89 tasks; Terminus 2 on E2B; 3 repeats; pass@1; 250-episode cap; 2-hour timeoutOpen source (opens in a new tab)
τ³-BankingAgentic19.6Artificial Analysis independent run; 97 tasks; 5 repeats; backend-state pass@1; BM25 plus grep retrieval; 200-step capOpen source (opens in a new tab)
AA-LCRReasoning75.6Artificial Analysis independent run; 100 roughly 100k-token multi-document questions; 3 repeats; equality-checker pass@1; no toolsOpen source (opens in a new tab)
Humanity's Last ExamReasoning26.5Artificial Analysis independent run; 2,158 text-only questions; pass@1; GPT-4o (August 2024) equality checker; no toolsOpen source (opens in a new tab)
GPQA DiamondReasoning85.4Artificial Analysis independent run; 198 questions; 5 repeats; regex-graded pass@1; no toolsOpen source (opens in a new tab)
SciCodeCoding42.9Artificial Analysis independent run; 288 test subproblems; scientist background included; 3 repeats; subproblem pass@1Open source (opens in a new tab)
IFBenchReasoning73.1Artificial Analysis independent run; 294 single-turn prompts; 5 repeats; official loose evaluator; prompt-level pass@1Open source (opens in a new tab)
CritPtMath5.7Artificial Analysis independent run; 70 test challenges; 5 repeats; two-step answer parsing; official CritPt grader; pass@1; no toolsOpen source (opens in a new tab)