OpenAI·released 2025-08-071 source
GPT-5 nano benchmark scores: 17 benchmarks tracked. 24% of its scores are independently reproduced — the rest are self-reported or unverified.
Leads on 0 of 17 benchmarks·best result 95.24 on MATH level 5 (reproduced)·4 of 17 independently reproduced·$0.05/$0.4 per M tokens
Consensus: LiteLLM · Cross-check: models.dev, OpenRouter · See every model’s pricing →
| Benchmark | Score | Evidence status | Measured |
|---|---|---|---|
| MATH level 5 | 95.24accuracy (%) | reproduced· optimizedT1 | 2025-08-07Epoch AI |
| OTIS Mock AIME 2024-2025 | 81.09accuracy (%) | reproduced· optimizedT1 | 2025-08-07Epoch AI |
| GPQA diamond | 59.26accuracy (%) | reproduced· optimizedT1 | 2025-08-07Epoch AI |
| Fiction.LiveBench | 44.4accuracy (%) | unverifiedT1 | 2025-08-07Fiction.live leaderboard |
| WeirdML | 38.06accuracy (%) | unverifiedT1 | 2025-08-07https://htihle.github.io/weirdml.html |
| DTBench | 37.78accuracy (%) | unverifiedT1 | 2025-08-07https://conceptualreasoning.ai/dtbench |
| Terminal Bench | 21.8accuracy (%) | unverifiedT1 | 2025-08-07https://www.tbench.ai/leaderboard/terminal-bench/2.0 |
| ARC-AGI | 20.71accuracy (%) | unverified· optimizedT2 | 2025-08-07 |
| FrontierMath-Tiers-1-3-v2-Private | 20accuracy (%) | unverifiedT2 | 2025-08-07 |
| Chess Puzzles | 17.93accuracy (%) | unverifiedT2 | 2025-08-07 |
| ProofBench | 12accuracy (%) | unverifiedT1 | 2025-08-07https://www.vals.ai/benchmarks/proof_bench |
| SimpleQA Verified | 11.7accuracy (%) | unverifiedT2 | 2025-08-07 |
| LMCA | 9.33accuracy (%) | unverifiedT1 | 2025-08-07https://conceptualreasoning.ai/lmca |
| VPCT | 5.8accuracy (%) | unverifiedT1 | 2025-08-07VPCT leaderboard |
| ARC-AGI-2 | 2.61accuracy (%) | unverifiedT2 | 2025-08-07 |
| FrontierMath-Tier-4-v2-Private | 2.44accuracy (%) | reproducedT1 | 2025-08-07Epoch AI |
| Mystery Game Puzzles | 0accuracy (%) | unverifiedT2 | 2025-08-07 |
Claims drawn from cited facts, not live model generation.
This model was developed by OpenAI and released in 2025.
2 cited facts
This model has scores on 17 tracked benchmarks and currently leads 0 of them. The record’s evidence status is independently reproduced.
3 cited facts
Its mean gap to the best recorded score across its tracked benchmarks is 63.05 points.
1 cited fact
6 facts cross-checked across data sources: 2 corroborated, 2 single-source, 2 disputed.
Source facts, citations, and refresh stamp for this record.
Sources: epoch_benchmarks, litellm_prices, modelsdev_models, openrouter_models
GPT-5 nano is an AI model developed by OpenAI, released 2025-08-07. Its benchmark record below tags every score as independently reproduced, self-reported, or unverified.
GPT-5 nano has recorded scores on 17 benchmarks, each shown with its evidence status.
GPT-5 nano has recorded scores on 17 benchmarks — GPQA diamond, MATH level 5, OTIS Mock AIME 2024-2025, DTBench, WeirdML, LMCA, and 11 more. The full table above shows each score with its evidence status.
4 of 17 recorded scores (24%) are independently reproduced rather than self-reported by the lab.
GPT-5 nano has 17 tracked claims: 4 independently reproduced, 13 unverified.
Listed API pricing: $0.05 per million input tokens, $0.4 per million output tokens (prices disputed across sources). See the pricing block for the full breakdown.