0 vs 3 benchmarks won
DeepSeek DeepSeek Chat (R1-based) | Google Gemini 2.5 Pro | |
|---|---|---|
| Overview | ||
| Company | DeepSeek | |
| Release date | Jan 20 2025 | Mar 25 2025 |
| Model type | — | — |
| Open source | Yes | No |
| Specifications | ||
Parameters | — | — |
Context window | — | — |
| Benchmarks | ||
Science reasoning GPQA Diamond | — | 86.4% |
Software engineering SWE-Bench Verified | — | 59.6% |
Multimodal understanding MMMU | — | 68% |
| Timeline | ||
| Release gap | DeepSeek Chat (R1-based) shipped 64 days before Gemini 2.5 Pro | |
Gemini 2.5 Pro leads DeepSeek Chat (R1-based) on 3 of the tracked benchmarks (GPQA Diamond, SWE-Bench Verified, MMMU). DeepSeek Chat (R1-based) shipped 64 days before Gemini 2.5 Pro, so benchmark comparisons should account for the intervening progress.
DeepSeek Chat (R1-based) is an open-source / open-weight model; Gemini 2.5 Pro 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.