Up to four models
DeepSeek-V4-Pro (Apr 2026) vs GPT-5.4 Mini
On the index (GPT-4 = 100), DeepSeek-V4-Pro (Apr 2026) scores 147 and GPT-5.4 Mini 147. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
147131–164
WeightsOpen
ReleasedApr 2026
Price in / out$0.90 / $1.5
Context1.05M
Core tests taken3 of 9
GPT-5.4 Mini
147131–163
WeightsClosed
ReleasedMar 2026
Price in / out$0.75 / $4.5
Context400K
Core tests taken5 of 9
DeepSeek-V4-Pro (Apr 2026) and GPT-5.4 Mini are too close to call (0 points apart, within the uncertainty), ahead on 1 of 2 shared core tests, and costs 1.6× less.
Test by testthird-party results
Every result as a table
| Test | DeepSeek-V4-Pro (Apr 2026) | GPT-5.4 Mini |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 90.9% | 86.9% |
| SimpleQA Verified | 47.0% | 29.4% |
| Maths | ||
| FrontierMath (tiers 1-3) | 45.3% | 51.2% |
| AIME-style maths (OTIS mock) | 96.7% | 88.9% |
| Chess puzzles | 19.0% | 23.0% |
| FrontierMath (tier 4) | 2.4% | 9.8% |
| Coding | ||
| WeirdML | 48.6% | 60.3% |
| Agents | ||
| DTBench | 90.7% | 80.0% |
| LMCA | 41.2% | 40.8% |
| Mystery game puzzles | 17.0% | 11.0% |
Tests at least two of these models have taken. Bold rows are the core tests.