OpenAI
availableShows if the model has enough results for an index.GPT-5 nano
GPT-5 nano is a reasoning model from OpenAI in the GPT-5 family. 19 benchmarks count toward its score, in 6 categories.
IndexOverall score. 50 is the middle.43.2 ±6.2
CoverageShare of the index weight with results.75%
SpeedOutput tokens per second.85/s
Input / 1MUS dollars per 1M input tokens.$0.05 batch $0.025
Output / 1MUS dollars per 1M output tokens.$0.4 batch $0.2 US dollars per 1M output tokens in a batch.
ContextMaximum tokens in one request.400K
EloLMArena rating and rank.1320 (#218)
50 is the middle of the board. The range shows the doubt in the index. Batch work costs less.
8,128 votes. Elo shows what people prefer. It does not change the score.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
19 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result on the index scale. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| MATH level 5 | Math | 94.9% | 45.3 | high effort | — | Epoch AI |
| MATH 500 | Math | 93.8% | 46.6 | — | 9 Jan 2026 | Vals AI |
| MGSM | Multilingual | 89.3% | — | — | 9 Jan 2026 | Vals AI |
| AIME | Math | 81.2% | 51.6 | — | 16 Apr 2026 | Vals AI |
| OTIS Mock AIME 2024-2025 | Math | 81.1% | 56.9 | high effort | — | Epoch AI |
| MMLU Pro | Knowledge | 76.1% | 40.3 | — | 1 Sept 2026 | Vals AI |
| MMMU Pro | Multimodal | 70.9% | 42.8 | — | 1 Sept 2026 | Vals AI |
| LiveCodeBench | Coding | 70.2% | 48.2 | — | 1 Sept 2026 | Vals AI |
| GPQA diamond | Knowledge | 69.4% | 42.4 | high effort | — | Epoch AI |
| GPQA Diamond | Knowledge | 63.4% | 36.8 | — | 1 Sept 2026 | Vals AI |
| EuroEval Swedish | Multilingual | 62.3% | 80.1 | — | — | EuroEval |
| EuroEval French | Multilingual | 53.9% | 69.6 | — | — | EuroEval |
| EuroEval Italian | Multilingual | 53.8% | 69.4 | — | — | EuroEval |
| EuroEval Dutch | Multilingual | 53.7% | 69.4 | — | — | EuroEval |
| EuroEval Polish | Multilingual | 52.8% | 68.2 | — | — | EuroEval |
| EuroEval Portuguese | Multilingual | 49.0% | 63.5 | — | — | EuroEval |
| EuroEval Spanish | Multilingual | 49.0% | 63.5 | — | — | EuroEval |
| EuroEval German | Multilingual | 47.0% | 61.0 | — | — | EuroEval |
| SWE-bench Verified | Coding | 34.8% | 25.4 | medium effort · mini-SWE-agent | 26 Feb 2026 | SWE-bench team |
| SWE-bench Verified | Coding | 34.8% | 25.4 | medium effort · mini-SWE-agent | 1 Sept 2026 | SWE-bench team |
| Chess Puzzles | Reasoning | 27.0% | 58.4 | high effort | — | Epoch AI |
| FrontierMath-Tiers-1-3-v2-Private | Math | 20.0% | 42.7 | high effort | — | Epoch AI |
| ARC-AGI-1 (semi-private) | Reasoning | 16.7% | 35.1 | high effort | — | ARC Prize Foundation |
| SimpleQA Verified | Knowledge | 11.7% | 32.4 | high effort | — | Epoch AI |
| FrontierMath-2025-02-28-Private | Math | 8.3% | 38.4 | high effort | — | Epoch AI |
| Mystery Game Puzzles | Reasoning | 8.0% | 42.4 | high effort | — | Epoch AI |
| ARC-AGI-2 (semi-private) | Reasoning | 2.6% | 41.0 | high effort | — | ARC Prize Foundation |
| FrontierMath-Tier-4-v2-Private | Math | 2.4% | 49.1 | high effort | — | Epoch AI |
| FrontierMath-Tier-4-2025-07-01-Private | Math | 0.0% | 43.4 | high effort | — | Epoch AI |
19 benchmarks count, from 28 of 29 results. A grey row does not count. Too few models took that benchmark.