0 vs 2 benchmarks won
DeepSeek DeepSeek-V4-Flash | OpenAI GPT-5.1 | |
|---|---|---|
| Overview | ||
| Company | DeepSeek | OpenAI |
| Release date | Apr 24 2026 | Nov 12 2025 |
| Model type | — | — |
| Open source | Yes | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 88.1% | 88.1% |
Software engineering SWE-Bench Verified | — | 76.3% |
Multimodal understanding MMMU | — | 76% |
| Timeline | ||
| Release gap | GPT-5.1 shipped 163 days before DeepSeek-V4-Flash | |
GPT-5.1 leads DeepSeek-V4-Flash on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). GPT-5.1 shipped 163 days before DeepSeek-V4-Flash, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Flash is an open-source / open-weight model; GPT-5.1 is proprietary.
On GPQA Diamond, both models score 88.1%.