0 vs 2 benchmarks won
DeepSeek DeepSeek V2.5 | Google Gemini 3.0 Flash | |
|---|---|---|
| Overview | ||
| Company | DeepSeek | |
| Release date | Sep 2024 | Dec 17 2025 |
| Model type | — | — |
| Open source | Yes | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | — | 90.4% |
Software engineering SWE-Bench Verified | — | 78% |
Multimodal understanding MMMU | — | — |
| Timeline | ||
| Release gap | DeepSeek V2.5 shipped 472 days before Gemini 3.0 Flash | |
Gemini 3.0 Flash leads DeepSeek V2.5 on 2 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). DeepSeek V2.5 shipped 472 days before Gemini 3.0 Flash, so benchmark comparisons should account for the intervening progress.
DeepSeek V2.5 is an open-source / open-weight model; Gemini 3.0 Flash is proprietary.
Direct benchmark comparisons are unavailable — at least one of these models has not published scores on GPQA Diamond, SWE-Bench Verified, or MMMU.