OpenAI
availableShows if the model has enough results for an index.GPT-5 mini
GPT-5 mini is a reasoning model from OpenAI in the GPT-5 family. 23 benchmarks count toward its score, in 7 categories.
IndexOverall score out of 100.49.8 ±3.9
CoverageShare of the index weight with results.95%
SpeedOutput tokens per second.75/s
Input / 1MUS dollars per 1M input tokens.$0.25 batch $0.125
Output / 1MUS dollars per 1M output tokens.$2 batch $1 US dollars per 1M output tokens in a batch.
ContextMaximum tokens in one request.400K
EloLMArena rating and rank.1373 (#166)
The index is a score out of 100. The ± range shows how much it can change. Batch work costs less.
26,569 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category, out of 100.
Out of 100Results
23 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result as a score out of 100. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| MATH level 5 | Math | 97.8% | 46.8 | high effort | — | Epoch AI |
| MATH 500 | Math | 94.8% | 47.7 | — | 9 Jan 2026 | Vals AI |
| MGSM | Multilingual | 92.6% | — | — | 9 Jan 2026 | Vals AI |
| AIME | Math | 91.5% | 56.4 | — | 16 Apr 2026 | Vals AI |
| OTIS Mock AIME 2024-2025 | Math | 86.7% | 60.0 | high effort | — | Epoch AI |
| LiveCodeBench | Coding | 86.6% | 63.0 | — | 1 Sept 2026 | Vals AI |
| MMLU Pro | Knowledge | 82.2% | 50.1 | — | 1 Sept 2026 | Vals AI |
| GPQA Diamond | Knowledge | 80.3% | 52.4 | — | 1 Sept 2026 | Vals AI |
| MMMU Pro | Multimodal | 78.9% | 55.8 | — | 1 Sept 2026 | Vals AI |
| GPQA diamond | Knowledge | 75.0% | 47.5 | high effort | — | Epoch AI |
| EuroEval Swedish | Multilingual | 66.0% | 84.7 | — | — | EuroEval |
| SWE-Bench verified | Coding | 64.7% | 49.4 | medium effort | — | Epoch AI |
| SWE-bench | Coding | 60.8% | 46.3 | — | 1 Sept 2026 | Vals AI |
| EuroEval Italian | Multilingual | 60.1% | 77.4 | — | — | EuroEval |
| EuroEval French | Multilingual | 60.1% | 77.3 | — | — | EuroEval |
| EuroEval Dutch | Multilingual | 60.1% | 77.3 | — | — | EuroEval |
| SWE-bench Verified | Coding | 59.8% | 45.5 | medium effort · mini-SWE-agent | 26 Feb 2026 | SWE-bench team |
| SWE-bench Verified | Coding | 59.8% | 45.5 | medium effort · mini-SWE-agent | 1 Sept 2026 | SWE-bench team |
| EuroEval Polish | Multilingual | 57.2% | 73.7 | — | — | EuroEval |
| EuroEval Portuguese | Multilingual | 55.9% | 72.0 | — | — | EuroEval |
| ARC-AGI-1 (semi-private) | Reasoning | 54.3% | 52.9 | high effort | — | ARC Prize Foundation |
| EuroEval Spanish | Multilingual | 54.2% | 70.0 | — | — | EuroEval |
| EuroEval German | Multilingual | 52.5% | 67.9 | — | — | EuroEval |
| FrontierMath-Tiers-1-3-v2-Private | Math | 46.7% | 57.7 | high effort | — | Epoch AI |
| SWE-bench Multilingual | Multilingual | 39.7% | — | mini-SWE-agent | 20 Feb 2026 | SWE-bench team |
| SWE-bench Multilingual | Coding | 39.7% | — | mini-SWE-agent | 2 Sept 2026 | SWE-bench team |
| Terminal-Bench 1.0 | Agentic | 30.0% | 37.0 | — | 12 Jan 2026 | Vals AI |
| Chess Puzzles | Reasoning | 30.0% | 62.3 | high effort | — | Epoch AI |
| FrontierMath-2025-02-28-Private | Math | 27.2% | 56.0 | high effort | — | Epoch AI |
| Terminal-Bench 2.0 | Agentic | 27.0% | 41.9 | — | 4 Jun 2026 | Vals AI |
| SimpleQA Verified | Knowledge | 21.6% | 41.5 | high effort | — | Epoch AI |
| Vibe Code Bench v1.1 | Coding | 14.2% | 48.1 | OpenHands | 21 Sept 2026 | Vals AI |
| FrontierMath-Tier-4-v2-Private | Math | 12.2% | 53.8 | high effort | — | Epoch AI |
| IOI v1 | Coding | 6.8% | 43.8 | — | 9 Aug 2026 | Vals AI |
| FrontierMath-Tier-4-2025-07-01-Private | Math | 6.3% | 50.2 | high effort | — | Epoch AI |
| Mystery Game Puzzles | Reasoning | 5.0% | 39.2 | high effort | — | Epoch AI |
| ARC-AGI-2 (semi-private) | Reasoning | 4.4% | 42.0 | high effort | — | ARC Prize Foundation |
23 benchmarks count, from 34 of 37 results. A grey row does not count. Too few models took that benchmark.