Model comparison
DeepSeek-V3.1 vs o1-pro
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 31.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeekSummary
- The widest gap is in knowledge, where DeepSeek-V3.1 leads 43.7 to 29.7.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 per million input/output tokens, against $150 / $600 for o1-pro.
- o1-pro accepts more context: 200K tokens versus 164K.
- DeepSeek-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | o1-pro | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 42.8 | 31.5 |
| Released | 2025-08-21 | 2025-03-19 |
| Weights | Open | Proprietary |
| Context window | 164K | 200K |
| Max output | 8K | 100K |
| Input $ / M tokens | $0.25 | $150 |
| Output $ / M tokens | $0.95 | $600 |
| Results tracked | 27 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek-V3.1: 40.3 (#144), o1-pro: —
| Benchmark | DeepSeek-V3.1 | o1-pro |
|---|---|---|
| WeirdML | 38.4% | — |
| LMArena Coding | 1417 | — |
Reasoning DeepSeek-V3.1 leads
DeepSeek-V3.1: 27.9 (#110), o1-pro: 20.4 (#239)
| Benchmark | DeepSeek-V3.1 | o1-pro |
|---|---|---|
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| ARC-AGI-1 | — | 23.3% |
| EnigmaEval | — | 6.1% |
| LMArena Hard Prompts | 1417 | — |
| DTBench | 82.7% | — |
| LMCA | 24.3% | — |
| Epoch Capabilities Index | 139.92 | — |
| ForecastBench | 58 | — |
Math Not comparable
DeepSeek-V3.1: 38.9 (#122), o1-pro: —
| Benchmark | DeepSeek-V3.1 | o1-pro |
|---|---|---|
| LMArena Math | 1420 | — |
Knowledge DeepSeek-V3.1 leads
DeepSeek-V3.1: 43.7 (#90), o1-pro: 29.7 (#234)
| Benchmark | DeepSeek-V3.1 | o1-pro |
|---|---|---|
| Humanity's Last Exam | — | 8.1% |
| Vectara Hallucination Rate | 5.5% | — |
| LMArena Expert | 1405 | — |
Multilingual Not comparable
DeepSeek-V3.1: 51.6 (#106), o1-pro: —
| Benchmark | DeepSeek-V3.1 | o1-pro |
|---|---|---|
| LMArena Non-English | 1400 | — |
| LMArena Chinese | 1469 | — |
| LMArena French | 1447 | — |
| LMArena German | 1411 | — |
| LMArena Japanese | 1378 | — |
| LMArena Korean | 1337 | — |
| LMArena Russian | 1405 | — |
| LMArena Spanish | 1431 | — |
Instruction Following Not comparable
DeepSeek-V3.1: 73.9 (#110), o1-pro: —
| Benchmark | DeepSeek-V3.1 | o1-pro |
|---|---|---|
| LMArena Instruction Following | 1400 | — |
Long Context Not comparable
DeepSeek-V3.1: 36.3 (#232), o1-pro: —
| Benchmark | DeepSeek-V3.1 | o1-pro |
|---|---|---|
| Fiction.LiveBench | 52.8% | — |
| LMArena Longer Query | 1422 | — |
Writing & Preference Not comparable
DeepSeek-V3.1: 60.3 (#98), o1-pro: —
| Benchmark | DeepSeek-V3.1 | o1-pro |
|---|---|---|
| LMArena Text | 1420 | — |
| LMArena Creative Writing | 1401 | — |
| EQ-Bench Creative Writing | 1436 | — |
| LMArena Multi-Turn | 1408 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than o1-pro?
DeepSeek-V3.1 is the stronger model overall, scoring 42.8 to 31.5 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1 or o1-pro?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; o1-pro lists at $150 and $600.
Which has the bigger context window?
o1-pro does, with 200K tokens against 164K.
How many benchmarks do DeepSeek-V3.1 and o1-pro share?
0 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and o1-pro has 3.