Model comparison
DeepSeek LLM 67B vs o1-mini
o1-mini is the stronger model overall, scoring 34.0 to 24.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeekSummary
- They share 14 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 1 category and o1-mini in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o1-mini leads 34.9 to 7.0.
- The biggest single-benchmark swing is MATH Level 5: 6.4% for DeepSeek LLM 67B and 89.2% for o1-mini.
- DeepSeek LLM 67B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek LLM 67B | o1-mini | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 24.9 | 34.0 |
| Released | 2023-11-29 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 15 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o1-mini leads
DeepSeek LLM 67B: 31.9 (#278), o1-mini: 35.5 (#224)
| Benchmark | DeepSeek LLM 67B | o1-mini |
|---|---|---|
| LMArena Coding | 1096 | 1362 |
| Aider Polyglot | — | 32.9% |
| WeirdML | — | 36.3% |
| LiveBench Coding | — | 48% |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, o1-mini: 24.6 (#118)
| Benchmark | DeepSeek LLM 67B | o1-mini |
|---|---|---|
| Cybench | — | 10% |
Reasoning DeepSeek LLM 67B leads
DeepSeek LLM 67B: 16.5 (#304), o1-mini: 8.8 (#346)
| Benchmark | DeepSeek LLM 67B | o1-mini |
|---|---|---|
| LMArena Hard Prompts | 1070 | 1333 |
| Epoch Capabilities Index | 110.5 | 135.82 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 18.1% |
| ARC-AGI-1 | — | 14% |
| Chess Puzzles | 0% | — |
| LiveBench Reasoning | — | 72.3% |
| LiveBench Data Analysis | — | 57.9% |
| LiveBench | — | 57.8% |
Math o1-mini leads
DeepSeek LLM 67B: 8.7 (#324), o1-mini: 35.4 (#186)
| Benchmark | DeepSeek LLM 67B | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 46.9% |
| LMArena Math | 1108 | 1358 |
| MATH Level 5 | 6.4% | 89.2% |
| LiveBench Math | — | 62% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge o1-mini leads
DeepSeek LLM 67B: 7.0 (#313), o1-mini: 34.9 (#192)
| Benchmark | DeepSeek LLM 67B | o1-mini |
|---|---|---|
| GPQA Diamond | 24.6% | 62.4% |
| Confabulations | — | 18.6% |
| LMArena Expert | — | 1316 |
Multilingual o1-mini leads
DeepSeek LLM 67B: 29.4 (#267), o1-mini: 43.6 (#182)
| Benchmark | DeepSeek LLM 67B | o1-mini |
|---|---|---|
| LMArena Non-English | 1073 | 1289 |
| LMArena Chinese | 1132 | 1314 |
| LMArena French | — | 1293 |
| LMArena German | — | 1278 |
| LMArena Japanese | — | 1245 |
| LMArena Korean | — | 1223 |
| LMArena Russian | — | 1283 |
| LMArena Spanish | — | 1303 |
Instruction Following o1-mini leads
DeepSeek LLM 67B: 55.4 (#277), o1-mini: 66.7 (#206)
| Benchmark | DeepSeek LLM 67B | o1-mini |
|---|---|---|
| LMArena Instruction Following | 1079 | 1304 |
| LiveBench Instruction Following | — | 65.4% |
Long Context o1-mini leads
DeepSeek LLM 67B: 33.1 (#265), o1-mini: 40.1 (#161)
| Benchmark | DeepSeek LLM 67B | o1-mini |
|---|---|---|
| LMArena Longer Query | 1092 | 1320 |
Writing & Preference o1-mini leads
DeepSeek LLM 67B: 31.6 (#282), o1-mini: 48.4 (#202)
| Benchmark | DeepSeek LLM 67B | o1-mini |
|---|---|---|
| LMArena Text | 1105 | 1317 |
| LMArena Creative Writing | 1067 | 1244 |
| LMArena Multi-Turn | 1082 | 1314 |
| Short-Story Creative Writing | — | 64.9% |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is DeepSeek LLM 67B better than o1-mini?
o1-mini is the stronger model overall, scoring 34.0 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or o1-mini better for coding?
o1-mini scores higher on coding benchmarks: 35.5 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and o1-mini share?
14 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and o1-mini has 39.