Model record

gpt-oss-120b

highOpen weights

OpenAI · released Aug 5, 2025

Overall standing

Overall
36.8rank 54 of 62
36.8 is at approximately the 14th percentile of the ranked Overall field. The field spans 19.0 to 62.2, with a median of 48.9.
8 of 8 measured
Category standingsReasoning 54.1Coding 32.6Math 1.1Agentic 12.0
Reasoning
54.1rank 52 of 62
54.1 is at approximately the 17th percentile of the ranked Reasoning field. The field spans 31.6 to 73.3, with a median of 64.8.
4 of 4 measured
Coding
32.6rank 42 of 46
32.6 is at approximately the 10th percentile of the ranked Coding field. The field spans 10.4 to 72.4, with a median of 56.1.
2 of 2 measured
Math
1.1rank 48 of 62
1.1 is at approximately the 21th percentile of the ranked Math field. The field spans 0.0 to 32.3, with a median of 5.3.
1 of 1 measured
Agentic
12.0rank 37 of 46
12.0 is at approximately the 21th percentile of the ranked Agentic field. The field spans 3.3 to 33.4, with a median of 19.6.
1 of 1 measured
Model factsOpen weights · Price not listed

Copied from the linked provider page; no separate retrieval date is stored.

Provider
OpenAI
Released
Weights
Open weights
Context window
131,072 tokens
Input price / Mtok
Not listed
Output price / Mtok
Not listed
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-oss-120b
BenchmarkCategoryScoreEvaluation settingsSource
Terminal-Bench v2.1Coding26.2Artificial 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-BankingAgentic12.0Artificial 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-LCRReasoning50.7Artificial 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 ExamReasoning18.5Artificial 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 DiamondReasoning78.2Artificial Analysis independent run; 198 questions; 5 repeats; regex-graded pass@1; no toolsOpen source (opens in a new tab)
SciCodeCoding38.9Artificial Analysis independent run; 288 test subproblems; scientist background included; 3 repeats; subproblem pass@1Open source (opens in a new tab)
IFBenchReasoning69.0Artificial Analysis independent run; 294 single-turn prompts; 5 repeats; official loose evaluator; prompt-level pass@1Open source (opens in a new tab)
CritPtMath1.1Artificial 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)