GPT-5 mini: benchmarks, price and rank
GPT-5 mini from OpenAI is 105th of 123 rated AI models on Spezia's leaderboard. It costs $0.25 in, $2 out per million tokens.
- 105th of 123 rated models
- Rating 679
- Rated on 6 benchmarks
- Closed
- Released Aug 7, 2025
- 400,000 tokens of context
- Knows the world to May 2024
Where it is strongest
Not in the top tenth on any benchmark in use.
Where it falls behind
- 97th of 103 on GPQA Diamond
- 97th of 107 on LMArena text
- 70th of 78 on SimpleQA Verified
Price: $0.25 in, $2 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.
- Humanity's Last Exam19.4%
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.
Independent result from Epoch AI.
- SimpleQA Verified21.6%
Short factual questions with one checked answer, asked without web search.
70th of 78. Independent result from Epoch AI.
- FrontierMath46.7%
Hundreds of new, unpublished math problems written by mathematicians, from hard undergraduate level up to research, with answers a computer can check.
56th of 76. Independent result from Epoch AI.
- LMArena text1,373
People put a question to two anonymous models and vote for the better answer.
97th of 107. Independent result from LMArena.
- SWE-bench Verified64.7%
Real bug reports and feature requests from popular open-source Python projects. The model has to change the code so the project's hidden tests pass.
Independent result from Epoch AI.
- GPQA Diamond75%
Graduate-level questions in biology, physics and chemistry, written by PhDs so that searching the web does not give the answer away.
97th of 103. Independent result from Epoch AI.
- ARC-AGI-24.4%
Visual puzzles of colored grids, each with a new rule to work out from a few examples.
61st of 69. Independent result from Epoch AI.
- FrontierMath Tier 412.2%
Research-level problems that take professional mathematicians days.
57th of 66. Independent result from Epoch AI.
- Epoch Capabilities Index146.1
One score built from dozens of benchmarks, set on a common scale so that models tested on different benchmarks can still be compared.
75th of 94. Independent result from Epoch AI.
1 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.