Model comparison
DeepSeek-V3.1 vs o1-mini
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 34.0 on the Noometry Index.
Last verified . 20 shared benchmarks.
DeepSeekSummary
- They share 20 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 7 categories and o1-mini in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where DeepSeek-V3.1 leads 27.9 to 8.8.
- The biggest single-benchmark swing is SimpleBench: 40% for DeepSeek-V3.1 and 18.1% for o1-mini.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | o1-mini | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 42.8 | 34.0 |
| Released | 2025-08-21 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.25 | — |
| Output $ / M tokens | $0.95 | — |
| Results tracked | 27 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 40.3 (#144), o1-mini: 35.5 (#224)
| Benchmark | DeepSeek-V3.1 | o1-mini |
|---|---|---|
| WeirdML | 38.4% | 36.3% |
| LMArena Coding | 1417 | 1362 |
| Aider Polyglot | — | 32.9% |
| LiveBench Coding | — | 48% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Not comparable
DeepSeek-V3.1: —, o1-mini: 24.6 (#118)
| Benchmark | DeepSeek-V3.1 | o1-mini |
|---|---|---|
| Cybench | — | 10% |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), o1-mini: 8.8 (#346)
| Benchmark | DeepSeek-V3.1 | o1-mini |
|---|---|---|
| SimpleBench | 40% | 18.1% |
| LMArena Hard Prompts | 1417 | 1333 |
| Epoch Capabilities Index | 139.92 | 135.82 |
| ARC-AGI-2 | — | 0.8% |
| Kagi LLM Benchmark | 53.2% | — |
| ARC-AGI-1 | — | 14% |
| LiveBench Reasoning | — | 72.3% |
| DTBench | 82.7% | — |
| LiveBench Data Analysis | — | 57.9% |
| LMCA | 24.3% | — |
| ForecastBench | 58 | — |
| LiveBench | — | 57.8% |
Math DeepSeek-V3.1 leads
DeepSeek-V3.1: 38.9 (#122), o1-mini: 35.4 (#186)
| Benchmark | DeepSeek-V3.1 | o1-mini |
|---|---|---|
| LMArena Math | 1420 | 1358 |
| OTIS Mock AIME 2024-2025 | — | 46.9% |
| LiveBench Math | — | 62% |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), o1-mini: 34.9 (#192)
| Benchmark | DeepSeek-V3.1 | o1-mini |
|---|---|---|
| LMArena Expert | 1405 | 1316 |
| GPQA Diamond | — | 62.4% |
| Confabulations | — | 18.6% |
| Vectara Hallucination Rate | 5.5% | — |
Multilingual DeepSeek-V3.1 leads
DeepSeek-V3.1: 51.6 (#106), o1-mini: 43.6 (#182)
| Benchmark | DeepSeek-V3.1 | o1-mini |
|---|---|---|
| LMArena Non-English | 1400 | 1289 |
| LMArena Chinese | 1469 | 1314 |
| LMArena French | 1447 | 1293 |
| LMArena German | 1411 | 1278 |
| LMArena Japanese | 1378 | 1245 |
| LMArena Korean | 1337 | 1223 |
| LMArena Russian | 1405 | 1283 |
| LMArena Spanish | 1431 | 1303 |
Instruction Following DeepSeek-V3.1 leads
DeepSeek-V3.1: 73.9 (#110), o1-mini: 66.7 (#206)
| Benchmark | DeepSeek-V3.1 | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1400 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
Long Context o1-mini leads
DeepSeek-V3.1: 36.3 (#232), o1-mini: 40.1 (#161)
| Benchmark | DeepSeek-V3.1 | o1-mini |
|---|---|---|
| LMArena Longer Query | 1422 | 1320 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference DeepSeek-V3.1 leads
DeepSeek-V3.1: 60.3 (#98), o1-mini: 48.4 (#202)
| Benchmark | DeepSeek-V3.1 | o1-mini |
|---|---|---|
| LMArena Text | 1420 | 1317 |
| LMArena Creative Writing | 1401 | 1244 |
| LMArena Multi-Turn | 1408 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| EQ-Bench Creative Writing | 1436 | — |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is DeepSeek-V3.1 better than o1-mini?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 34.0 on the Noometry Index.
Is DeepSeek-V3.1 or o1-mini better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 35.5 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1 and o1-mini share?
20 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and o1-mini has 39.