Compare / DeepSeek V4 Pro 0423 vs MiniMax M2.1
DeepSeek V4 Pro 0423 vs MiniMax M2.1
11 results from 3 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | DeepSeek V4 Pro 0423 | MiniMax M2.1 |
|---|---|---|---|
| OpenHands Indexreported | Average% resolved | 40.7% | 41.2% |
| OpenHands Indexreported | Front end (SWE-Bench Multimodal)% resolved | 36.8% | 16.2% |
| OpenHands Indexreported | Greenfield (Commit0)% resolved | 12.5% | 18.8% |
| OpenHands Indexreported | Information gathering (GAIA)% resolved | 12.7% | 40.6% |
| OpenHands Indexreported | Issue resolution (SWE-Bench)% resolved | 73.2% | 68.8% |
| OpenHands Indexreported | Testing (SWT-Bench)% resolved | 68.1% | 61.4% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 34.0% | 31.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.36 | 0.41 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 68.4 | 41.6 |
| Vectara Hallucination Leaderboardreported | Answer rate% of documents | 97.2% | 98.5% |
| Vectara Hallucination Leaderboardreported | Hallucination rate% of summaries | 8.6% | 11.8% |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.