DeepSeek V4.1 Flash — Benchmarks
Benchmark scores for DeepSeek V4.1 Flash aggregated from public leaderboards, with how it ranks among open models. See hardware requirements for what you need to run it.
Overall rank: #4 of 78 open modelscomposite 65.8/100 across 8 benchmarks in 3 categories · methodology
Coding
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| LiveBench Coding | 80.0 | #2 / 19 | #19 / 63 |
| SciCode | 51.8% | #4 / 62 | #53 / 161 |
| LMArena WebDev | 1616.1 | #5 / 48 | #17 / 123 |
| Surface Evolver Bench | 46.3% | #6 / 13 | #19 / 27 |
Math
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| ProofBench | 54.0% | #4 / 24 | #17 / 68 |
| LiveBench Math | 93.3 | #2 / 19 | #18 / 63 |
Reasoning
| Benchmark | Score | Open rank | All models |
|---|---|---|---|
| DTBench | 89.9% | #8 / 67 | #71 / 210 |
| LMCA | 47.0% | #3 / 53 | #63 / 172 |
| CritPt | 14.3% | #7 / 62 | #58 / 172 |
| LiveBench Reasoning | 86.7 | #3 / 19 | #27 / 63 |
Scores aggregated from public benchmark sources (each linked from the benchmark pages). llmrun does not run these benchmarks.