GPT-5 Nano
GPT / OpenAI
84scores
54benchmarks
$0.05 / $0.4 per 1M tokenscost in/out
Metadata
GPT Closed/API
Aliases: gpt-5-nano, gpt-5-nano-2025-08-07, openai-gpt-5-nano, openai-gpt-5-nano-2025-08-07, openai/gpt-5-nano, openai/gpt-5-nano-2025-08-07
| Benchmark | Category | Rank | Score | Sampled |
|---|---|---|---|---|
| ARC-AGI-1 | Agentic | 111 | 20.71 | 2026-05-05 |
| ARC-AGI-1 | Agentic | 115 | 16.67 | 2026-05-05 |
| ARC-AGI-1 | Agentic | 139 | 4.04 | 2026-05-05 |
| ARC-AGI-1 | Agentic | 141 | 1.50 | 2026-05-05 |
| ARC-AGI-2 | Agentic | 84 | 2.61 | 2026-05-05 |
| ARC-AGI-2 | Agentic | 118 | 0.88 | 2026-05-05 |
| ARC-AGI-2 | Agentic | 145 | 0 | 2026-05-05 |
| ARC-AGI-2 | Agentic | 146 | 0 | 2026-05-05 |
| Berkeley Function-Calling Leaderboard | Agentic | 24 | 51.45% | 2026-05-27 |
| Berkeley Function-Calling Leaderboard | Agentic | 79 | 27.55% | 2026-05-27 |
| Hindsight LLM Memory Leaderboard | Agentic | 13 | 83.90 | 2026-05-06 |
| LLM-WikiRace | Agentic | 17 | 24.70 | 2026-05-06 |
| MCPMark | Agentic | 34 | 0.06 | 2026-05-06 |
| MCPMark | Agentic | 35 | 0.05 | 2026-05-06 |
| MCPMark | Agentic | 37 | 0.04 | 2026-05-06 |
| PinchBench | Agentic | 58 | 0.69 | 2026-05-06 |
| Tau2-Bench Telecom | Agentic | 211 | 36.5% | 2026-05-11 |
| Tau2-Bench Telecom | Agentic | 242 | 30.4% | 2026-05-11 |
| Tau2-Bench Telecom | Agentic | 274 | 25.7% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 159 | 17.4% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 194 | 12.1% | 2026-05-11 |
| Terminal-Bench Hard | Agentic | 235 | 6.8% | 2026-05-11 |
| ALE-Bench | Coding | 49 | 718.67 | 2026-05-06 |
| LiveCodeBench | Coding | 63 | 70.216% | 2026-05-28 |
| MLX Benchmark V2 | Coding | 11 | 41.92 | 2026-05-06 |
| SciCode | Coding | 165 | 36.6% | 2026-05-11 |
| SciCode | Coding | 208 | 33.8% | 2026-05-11 |
| SciCode | Coding | 263 | 29.1% | 2026-05-11 |
| GSMA Open Telco Leaderboard | Domain | 31 | 60.30 | 2026-05-06 |
| SAGE | Education | 48 | 30.377% | 2026-05-28 |
| Vectara HHEM Hallucination Leaderboard | Factuality | 58 | 89.50 | 2026-05-06 |
| MortgageTax | Finance | 58 | 53.617% | 2026-05-28 |
| TaxEval v2 | Finance | 80 | 67.376% | 2026-05-28 |
| MageBench Season 1 | Game | 34 | 1499 rating / 14 games | 2026-05-28 |
| Xent Games | Game | 12 | 23.27 overall | 2026-05-28 |
| ALL Bench LLM | General Knowledge | 39 | 0 | 2026-05-06 |
| HELM AIR-Bench | Generalization | 6 | 0.878205 | 2026-05-28 |
| MedCode | Healthcare | 53 | 30.441% | 2026-05-28 |
| MedQA | Healthcare | 23 | 93.258% | 2026-04-16 |
| MedScribe | Healthcare | 42 | 72.865% | 2026-05-28 |
| AI2D | Intelligence | 6 | 81.9 | 2026-05-27 |
| Artificial Analysis Intelligence Index | Intelligence | 176 | 26.83 | 2026-05-11 |
| Artificial Analysis Intelligence Index | Intelligence | 183 | 25.88 | 2026-05-11 |
| Artificial Analysis Intelligence Index | Intelligence | 352 | 13.84 | 2026-05-11 |
| GPQA Diamond | Intelligence | 79 | 63.384% | 2026-05-28 |
| Humanity's Last Exam | Intelligence | 183 | 8.2% | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 197 | 7.6% | 2026-05-11 |
| Humanity's Last Exam | Intelligence | 402 | 4.1% | 2026-05-11 |
| MMBench | Intelligence | 7 | 80.3 | 2026-05-27 |
| MMLU Pro | Intelligence | 80 | 76.067% | 2026-05-28 |
| MMLU-Pro | Intelligence | 142 | 78% | 2026-05-11 |
| MMLU-Pro | Intelligence | 154 | 77.2% | 2026-05-11 |
| MMLU-Pro | Intelligence | 283 | 55.6% | 2026-05-11 |
| MMMU Pro | Intelligence | 49 | 70.942% | 2026-05-28 |
| RealWorldQA | Intelligence | 6 | 71.8 | 2026-05-27 |
| Seneca-TRBench | Language | 2 | 92.90 | 2026-05-06 |
| CaseLaw v2 | Legal | 44 | 52.626% | 2026-05-04 |
| LegalBench | Legal | 109 | 50.129% | 2026-05-28 |
| LEXam | Legal | 31 | 27.25% open / 47.11% MCQ | 2026-05-28 |
| AIME | Math | 45 | 81.181% | 2026-04-16 |
| AIME 2025 | Math | 53 | 83.7% | 2026-05-11 |
| AIME 2025 | Math | 72 | 78.3% | 2026-05-11 |
| AIME 2025 | Math | 190 | 27.3% | 2026-05-11 |
| MATH 500 | Math | 16 | 93.8% | 2026-01-09 |
| MGSM | Math | 48 | 89.309% | 2026-01-09 |
| ProofBench | Math | 22 | 12% | 2026-05-28 |
| HMMT 2025 | Mathematics | 25 | 0.76 | 2026-05-06 |
| ALL Bench Multimodal | Multimodal | 41 | 0 | 2026-05-06 |
| ALL Bench Multimodal | Multimodal | 5 | 50.88 | 2026-05-06 |
| Design Arena | Multimodal | 84 | 1143 | 2026-05-06 |
| IDP Leaderboard | Multimodal | 22 | 54.81 | 2026-05-06 |
| Artificial Analysis Openness Index | Openness | 225 | 5.56 | 2026-05-11 |
| Artificial Analysis Openness Index | Openness | 226 | 5.56 | 2026-05-11 |
| Artificial Analysis Openness Index | Openness | 227 | 5.56 | 2026-05-11 |
| CAIS Text Capabilities Index | Reasoning | 39 | 4.8 | 2026-05-27 |
| GPQA Diamond | Reasoning | 225 | 67.6% | 2026-05-11 |
| GPQA Diamond | Reasoning | 232 | 67% | 2026-05-11 |
| GPQA Diamond | Reasoning | 379 | 42.8% | 2026-05-11 |
| CAIS Risk Index | Safety | 19 | 51.9 | 2026-05-27 |
| ChemBench | Science | 8 | 0.63 | 2026-05-06 |
| CritPt | Science | 222 | 0% | 2026-05-11 |
| CritPt | Science | 223 | 0% | 2026-05-11 |
| CritPt | Science | 224 | 0% | 2026-05-11 |
| CAIS Vision Capabilities Index | Vision | 26 | 43.4 | 2026-05-27 |
No matching rows.