Up to four models
GPT-5.5 vs DeepSeek-V4-Pro (Apr 2026)
On the index (GPT-4 = 100), GPT-5.5 scores 172 and DeepSeek-V4-Pro (Apr 2026) 147. 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
147131–164
WeightsOpen
ReleasedApr 2026
Price in / out$0.90 / $1.5
Context1.05M
Core tests taken3 of 9
GPT-5.5 leads DeepSeek-V4-Pro (Apr 2026) by 25 points, ahead on 3 of 3 shared core tests, at 11× the price.
Test by testthird-party results
GPT-5.5
DeepSeek-V4-Pro (Apr 2026)
Every result as a table
| Test | GPT-5.5 | DeepSeek-V4-Pro (Apr 2026) |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 94.0% | 90.9% |
| LiveBench Data Analysis | 81.6% | 74.5% |
| LiveBench IF | 70.7% | 62.4% |
| LiveBench Language | 87.4% | 78.1% |
| LiveBench Reasoning | 89.6% | 82.7% |
| SimpleQA Verified | 63.0% | 47.0% |
| Maths | ||
| FrontierMath (tiers 1-3) | 85.3% | 45.3% |
| AIME-style maths (OTIS mock) | 100.0% | 96.7% |
| LiveBench Mathematics | 95.9% | 90.7% |
| Chess puzzles | 63.0% | 19.0% |
| FrontierMath (tier 4) | 72.5% | 2.4% |
| Surface Evolver Bench | 88.1% | 40.0% |
| Coding | ||
| SWE-bench Verified | 80.6% | 77.6% |
| LiveBench Agentic Coding | 54.0% | 42.6% |
| LiveBench Coding | 82.2% | 70.0% |
| WeirdML | 84.9% | 48.6% |
| Agents | ||
| DTBench | 96.0% | 90.7% |
| LMCA | 54.3% | 41.2% |
| Mystery game puzzles | 56.0% | 17.0% |
Tests at least two of these models have taken. Bold rows are the core tests.