Model comparison
DeepSeek V4.1 Flash vs o1-mini
DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 33.7 on the Noometry Index.
Last verified . 15 shared benchmarks.
DeepSeekSummary
- They share 15 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and o1-mini in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek V4.1 Flash leads 46.2 to 8.9.
- DeepSeek V4.1 Flash has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4.1 Flash | o1-mini | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 50.3 | 33.7 |
| Released | 2026-09-09 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 1M | — |
| Max output | 393K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.60 | — |
| Results tracked | 25 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 52.8 (#29), o1-mini: 35.1 (#218)
| Benchmark | DeepSeek V4.1 Flash | o1-mini |
|---|---|---|
| LMArena Coding | 1511 | 1362 |
| Aider Polyglot | — | 32.9% |
| LMArena WebDev | 1620 | — |
| SciCode | 51.9% | — |
| WeirdML | — | 36.3% |
| LiveBench Coding | — | 48% |
| ALE-Bench | 1,092 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Not comparable
DeepSeek V4.1 Flash: —, o1-mini: 24.3 (#112)
| Benchmark | DeepSeek V4.1 Flash | o1-mini |
|---|---|---|
| Cybench | — | 10% |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 46.2 (#39), o1-mini: 8.9 (#340)
| Benchmark | DeepSeek V4.1 Flash | o1-mini |
|---|---|---|
| LMArena Hard Prompts | 1485 | 1333 |
| Epoch Capabilities Index | 155.01 | 135.82 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 18.1% |
| NYT Connections (extended) | 89.6% | — |
| ARC-AGI-1 | — | 14% |
| CritPt | 14.3% | — |
| LiveBench Reasoning | — | 72.3% |
| DTBench | 89.9% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| LiveBench | — | 57.8% |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 48.4 (#52), o1-mini: 33.7 (#168)
| Benchmark | DeepSeek V4.1 Flash | o1-mini |
|---|---|---|
| LMArena Math | 1493 | 1358 |
| OTIS Mock AIME 2024-2025 | — | 46.9% |
| ProofBench | 54% | — |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 41.6 (#97), o1-mini: 34.8 (#180)
| Benchmark | DeepSeek V4.1 Flash | o1-mini |
|---|---|---|
| LMArena Expert | 1505 | 1316 |
| GPQA Diamond | — | 62.4% |
| Confabulations | — | 18.6% |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.5 (#29), o1-mini: 43.8 (#177)
| Benchmark | DeepSeek V4.1 Flash | o1-mini |
|---|---|---|
| LMArena Non-English | 1452 | 1289 |
| LMArena Chinese | 1506 | 1314 |
| LMArena French | 1448 | 1292 |
| LMArena Russian | 1473 | 1283 |
| LMArena Spanish | 1499 | 1302 |
| LMArena German | — | 1278 |
| LMArena Japanese | — | 1245 |
| LMArena Korean | — | 1223 |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.6 (#24), o1-mini: 67.0 (#200)
| Benchmark | DeepSeek V4.1 Flash | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1475 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
Long Context DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 45.2 (#46), o1-mini: 40.1 (#156)
| Benchmark | DeepSeek V4.1 Flash | o1-mini |
|---|---|---|
| LMArena Longer Query | 1476 | 1321 |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.8 (#43), o1-mini: 48.6 (#196)
| Benchmark | DeepSeek V4.1 Flash | o1-mini |
|---|---|---|
| LMArena Text | 1465 | 1317 |
| LMArena Creative Writing | 1436 | 1244 |
| LMArena Multi-Turn | 1460 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 1540 | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is DeepSeek V4.1 Flash better than o1-mini?
DeepSeek V4.1 Flash is the stronger model overall, scoring 50.3 to 33.7 on the Noometry Index.
Is DeepSeek V4.1 Flash or o1-mini better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.8 versus 35.1 in the Noometry coding category.
How many benchmarks do DeepSeek V4.1 Flash and o1-mini share?
15 benchmarks have published results for both models. DeepSeek V4.1 Flash has 25 scored results on Noometry and o1-mini has 39.