Up to four models
GPT-5.5 vs DeepSeek V4.1 Flash 1017
On the index (GPT-4 = 100), GPT-5.5 scores 172 and DeepSeek V4.1 Flash 1017 172. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-5.5
172156–188
WeightsClosed
ReleasedApr 2026
Price in / out$5.0 / $30
Context1.05M
Core tests taken6 of 9
172156–188
WeightsOpen
ReleasedOct 2026
Price in / out$0.036 / $0.50
Context1.05M
Core tests taken6 of 9
GPT-5.5 and DeepSeek V4.1 Flash 1017 are too close to call (0 points apart, within the uncertainty), ahead on 3 of 5 shared core tests, at 74× the price.
Test by testthird-party results
GPT-5.5
DeepSeek V4.1 Flash 1017
Every result as a table
| Test | GPT-5.5 | DeepSeek V4.1 Flash 1017 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 94.0% | 93.2% |
| SimpleQA Verified | 63.0% | 42.5% |
| Maths | ||
| FrontierMath (tiers 1-3) | 85.3% | 71.2% |
| AIME-style maths (OTIS mock) | 100.0% | 99.4% |
| Chess puzzles | 63.0% | 46.0% |
| FrontierMath (tier 4) | 72.5% | 46.3% |
| Coding | ||
| Code Migration | 45.2% | 44.2% |
| Vibe Code Bench v1.1 | 69.8% | 87.7% |
| Agents | ||
| APEX-Agents | 55.1% | 69.8% |
| Mystery game puzzles | 56.0% | 49.0% |
| Professional work | ||
| Finance Agent (v2) | 51.8% | 57.0% |
| EMB | 64.5% | 61.8% |
| Legal Research Bench | 40.4% | 45.2% |
| Tax Agent Bench | 21.8% | 44.4% |
| Novel problems | ||
| ARC-AGI-2 | 85.0% | 78.1% |
| ARC-AGI-1 | 95.0% | 94.5% |
| ARC-AGI-3 | 0.4% | 0.2% |
Tests at least two of these models have taken. Bold rows are the core tests.