Model comparison
DeepSeek LLM 67B vs o1-pro
o1-pro is the stronger model overall, scoring 31.5 to 24.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeekSummary
- The widest gap is in knowledge, where o1-pro leads 29.7 to 7.0.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | o1-pro | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 24.9 | 31.5 |
| Released | 2023-11-29 | 2025-03-19 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $150 |
| Output $ / M tokens | — | $600 |
| Results tracked | 15 | 3 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek LLM 67B: 31.9 (#278), o1-pro: —
| Benchmark | DeepSeek LLM 67B | o1-pro |
|---|---|---|
| LMArena Coding | 1096 | — |
Reasoning o1-pro leads
DeepSeek LLM 67B: 16.5 (#304), o1-pro: 20.4 (#239)
| Benchmark | DeepSeek LLM 67B | o1-pro |
|---|---|---|
| ARC-AGI-1 | — | 23.3% |
| Chess Puzzles | 0% | — |
| EnigmaEval | — | 6.1% |
| LMArena Hard Prompts | 1070 | — |
| Epoch Capabilities Index | 110.5 | — |
Math Not comparable
DeepSeek LLM 67B: 8.7 (#324), o1-pro: —
| Benchmark | DeepSeek LLM 67B | o1-pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | — |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
Knowledge o1-pro leads
DeepSeek LLM 67B: 7.0 (#313), o1-pro: 29.7 (#234)
| Benchmark | DeepSeek LLM 67B | o1-pro |
|---|---|---|
| GPQA Diamond | 24.6% | — |
| Humanity's Last Exam | — | 8.1% |
Multilingual Not comparable
DeepSeek LLM 67B: 29.4 (#267), o1-pro: —
| Benchmark | DeepSeek LLM 67B | o1-pro |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |
Instruction Following Not comparable
DeepSeek LLM 67B: 55.4 (#277), o1-pro: —
| Benchmark | DeepSeek LLM 67B | o1-pro |
|---|---|---|
| LMArena Instruction Following | 1079 | — |
Long Context Not comparable
DeepSeek LLM 67B: 33.1 (#265), o1-pro: —
| Benchmark | DeepSeek LLM 67B | o1-pro |
|---|---|---|
| LMArena Longer Query | 1092 | — |
Writing & Preference Not comparable
DeepSeek LLM 67B: 31.6 (#282), o1-pro: —
| Benchmark | DeepSeek LLM 67B | o1-pro |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| LMArena Multi-Turn | 1082 | — |
Frequently asked questions
Is DeepSeek LLM 67B better than o1-pro?
o1-pro is the stronger model overall, scoring 31.5 to 24.9 on the Noometry Index.
How many benchmarks do DeepSeek LLM 67B and o1-pro share?
0 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and o1-pro has 3.