Up to four models
GPT-5 nano vs GPT-4.1 nano
On the index (GPT-4 = 100), GPT-5 nano scores 125 and GPT-4.1 nano 109. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-5 nano
125109–141
WeightsClosed
ReleasedAug 2025
Price in / out$0.050 / $0.40
Context400K
Core tests taken3 of 9
GPT-4.1 nano
10993–125
WeightsClosed
ReleasedApr 2025
Price in / out$0.10 / $0.40
Context1.05M
Core tests taken2 of 9
GPT-5 nano leads GPT-4.1 nano by 16 points, ahead on 2 of 2 shared core tests, at a similar price.
Test by testthird-party results
GPT-5 nanoGPT-4.1 nano
Every result as a table
| Test | GPT-5 nano | GPT-4.1 nano |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 69.4% | 48.9% |
| GPQA Diamond (Vals AI) | 63.4% | 50.8% |
| MMLU Pro | 76.1% | 63.5% |
| MMMU Pro | 70.9% | 55.0% |
| Fiction.LiveBench | 44.4% | 25.0% |
| SimpleQA Verified | 11.7% | 6.0% |
| Maths | ||
| AIME-style maths (OTIS mock) | 81.1% | 28.9% |
| MATH (level 5) | 95.2% | 70.0% |
| MATH 500 | 93.8% | 80.2% |
| MGSM | 89.3% | 69.3% |
| Chess puzzles | 22.0% | 0.0% |
| FrontierMath (2025 set) | 8.3% | 1.0% |
| Coding | ||
| LiveCodeBench | 70.2% | 42.7% |
| WeirdML | 38.1% | 19.0% |
| Agents | ||
| DTBench | 62.7% | 52.5% |
| LMCA | 7.9% | 5.5% |
| Professional work | ||
| LegalBench | 50.1% | 61.1% |
| MortgageTax | 53.6% | 52.8% |
| TaxEval v2 | 67.4% | 60.8% |
| Novel problems | ||
| ARC-AGI-2 | 2.6% | 0.0% |
| ARC-AGI-1 | 20.7% | 0.0% |
Tests at least two of these models have taken. Bold rows are the core tests.