GPT OSS 120B: benchmarks, price and rank
GPT OSS 120B from OpenAI is 113th of 123 rated AI models on Spezia's leaderboard. It costs $0.037 in, $0.17 out per million tokens.
- 113th of 123 rated models
- Rating 492
- Rated on 7 benchmarks
- Open weights
- Released Aug 5, 2025
- 131,000 tokens of context
Where it is strongest
Not in the top tenth on any benchmark in use.
Where it falls behind
- 56th of 56 on APEX-Agents
- 68th of 68 on SimpleBench
- 90th of 94 on Epoch Capabilities Index
Price: $0.037 in, $0.17 out per million tokens.
Its headline results
The benchmarks that count most in the rating, with its place among the models measured the same way, and where each number came from.
- APEX-Agents4.4%
Long tasks written by investment banking analysts, management consultants and corporate lawyers from their own work, done across files and apps in a realistic work setup.
56th of 56. Independent result from Epoch AI.
- Humanity's Last Exam14.9%
About 2,500 questions written by experts in more than a hundred fields to be as hard as they could make them, many needing a diagram or image.
60th of 74. The maker's own number, from OpenAI, via LLM Stats.
- LiveCodeBench v681.9%
Programming contest problems collected after models were trained, from LeetCode, AtCoder and Codeforces.
17th of 43. The maker's own number, from OpenAI, via LLM Stats.
- SimpleBench22.1%
Multiple-choice puzzles about everyday situations, space, time and people, written to trip up models that pattern-match instead of think. Ordinary adults do well on them.
68th of 68. Independent result from Epoch AI.
- LMArena text1,365
People put a question to two anonymous models and vote for the better answer.
99th of 107. Independent result from LMArena.
- HealthBench57.6%
5,000 realistic health conversations with patients and clinicians, each graded against criteria written by 262 physicians.
8th of 16. The maker's own number, from OpenAI, via LLM Stats.
- GPQA Diamond75.8%
Graduate-level questions in biology, physics and chemistry, written by PhDs so that searching the web does not give the answer away.
95th of 103. Independent result from Epoch AI.
- MMLU-Pro80.7%
Twelve thousand multiple-choice questions across fourteen subjects, from law and medicine to engineering, with ten options each.
40th of 56. The maker's own number, from OpenAI, via LLM Stats.
- Epoch Capabilities Index140.2
One score built from dozens of benchmarks, set on a common scale so that models tested on different benchmarks can still be compared.
90th of 94. Independent result from Epoch AI.
2 more results in its full profile.
Every result with its source, what it costs per task, what jumped with its release, side by side with any other model, and answers to your questions about when to use it.
Models ranked near it
How the rating works, and every benchmark it uses: the model leaderboard.