GPT-5 Nano Medium
| Released | 2025-08-07 |
|---|---|
| Price per 1M | $0.050 in · $0.40 out |
| Overall score | 43.6 · rank 351 |
| Context window | 400,000 tokens |
| Provider | OpenAI |
| Weights | Proprietary |
| Configuration | Medium |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 43.6 | 351 | 10 |
| Overall: Coding | 41.4 | 364 | 5 |
| Overall: Reasoning | 46.4 | 310 | 8 |
| Overall: Agentic work | 40.7 | 372 | 5 |
| Overall: Frontend | 46.3 | 271 | 1 |
| Agents | 39.6 | 263 | 1 |
| Reasoning | 44.9 | 327 | 4 |
| Math | 48.5 | 200 | 4 |
| Multimodal | 46.3 | 137 | 1 |
| Value vs price | −1.1 | 257 |
Evidence
Agents 39.6 ±2.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 2.0 | 11.5% | Epoch AI | 2025-11-04 |
Reasoning 44.9 ±2.3
| Benchmark | Result | Source | Date |
|---|---|---|---|
| GPQA Diamond | 67.4% | Epoch AI | 2025-08-07 |
| ARC-AGI-2 | 0.9% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 20.7% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 20.7% | Epoch AI | 2026-11-11 |
| ARC-AGI-2 (ARC Prize verified) | 0.9% | ARC Prize | 2026-11-11 |
| Mystery Game Puzzles | 9.0% | Epoch AI | 2026-08-27 |
Math 48.5 ±1.4
| Benchmark | Result | Source | Date |
|---|---|---|---|
| MATH Level 5 | 95.2% | Epoch AI | 2025-08-20 |
| FrontierMath Tiers 1-3 (2025 set) | 7.2% | Epoch AI | 2025-08-07 |
| FrontierMath Tier 4 (2025 set) | 2.1% | Epoch AI | 2025-08-07 |
| OTIS Mock AIME 2024-2025 | 74.2% | Epoch AI | 2025-08-07 |
Multimodal 46.3 ±5.3
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| Terminal-Bench 2.0 | 9.9% | Epoch AI | Lower duplicate run on the same benchmark |
| Terminal-Bench 2.0 | 7.9% | Epoch AI | Lower duplicate run on the same benchmark |
| Terminal-Bench 2.0 | 7.0% | Epoch AI | Lower duplicate run on the same benchmark |
Names matched to this model
gpt-5-nano-medium