Up to four models
GPT-5 vs DeepSeek-V3.1
On the index (GPT-4 = 100), GPT-5 scores 149 and DeepSeek-V3.1 128. 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
149133–164
WeightsClosed
ReleasedAug 2025
Price in / out$1.25 / $10
Context400K
Core tests taken6 of 9
128111–145
WeightsOpen
ReleasedAug 2025
Price in / out$0.25 / $0.95
Context164K
Core tests taken0 of 9
GPT-5 leads DeepSeek-V3.1 by 21 points, at 8.1× the price.
Test by testthird-party results
GPT-5
DeepSeek-V3.1
Every result as a table
| Test | GPT-5 | DeepSeek-V3.1 |
|---|---|---|
| Reasoning & knowledge | ||
| Fiction.LiveBench | 97.2% | 52.8% |
| SimpleBench | 56.7% | 40.0% |
| Coding | ||
| WeirdML | 60.7% | 38.4% |
| Agents | ||
| DTBench | 90.7% | 82.7% |
| LMCA | 40.0% | 24.3% |
| Professional work | ||
| CorpFin v2 | 61.1% | 51.5% |
Task length · METR42 sec
Tests at least two of these models have taken. Bold rows are the core tests.