1 vs 2 benchmarks won
DeepSeek DeepSeek-V4-Flash | Google Gemini 2.5 Pro | |
|---|---|---|
| Overview | ||
| Company | DeepSeek | |
| Release date | Apr 24 2026 | Mar 25 2025 |
| Model type | — | — |
| Open source | Yes | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | 88.1% | 86.4% |
Software engineering SWE-Bench Verified | — | 59.6% |
Multimodal understanding MMMU | — | 68% |
| Timeline | ||
| Release gap | Gemini 2.5 Pro shipped 395 days before DeepSeek-V4-Flash | |
Gemini 2.5 Pro leads DeepSeek-V4-Flash on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). Gemini 2.5 Pro shipped 395 days before DeepSeek-V4-Flash, so benchmark comparisons should account for the intervening progress.
DeepSeek-V4-Flash is an open-source / open-weight model; Gemini 2.5 Pro is proprietary.
On GPQA Diamond, DeepSeek-V4-Flash scores 88.1%, 1.7 points above Gemini 2.5 Pro at 86.4%.