Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs o1-mini
o1-mini has enough public results to be ranked (#235); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeekSummary
- They share 1 benchmark with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and o1-mini in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 35.5.
- DeepSeek-V2 (MoE-236B, May 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | o1-mini | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 40.3 | 34.0 |
| Released | 2024-05-07 | 2024-09-12 |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 10 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), o1-mini: 35.5 (#224)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | o1-mini |
|---|---|---|
| Aider Polyglot | — | 32.9% |
| WeirdML | — | 36.3% |
| BigCodeBench Instruct | 48.9% | — |
| LiveBench Coding | — | 48% |
| LMArena Coding | — | 1362 |
| BigCodeBench Complete | 59.4% | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 78.8% |
Agentic & Tool Use Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, o1-mini: 24.6 (#118)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | o1-mini |
|---|---|---|
| Cybench | — | 10% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, o1-mini: 8.8 (#346)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | o1-mini |
|---|---|---|
| Epoch Capabilities Index | 124.77 | 135.82 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 18.1% |
| ARC-AGI-1 | — | 14% |
| LiveBench Reasoning | — | 72.3% |
| LMArena Hard Prompts | — | 1333 |
| LiveBench Data Analysis | — | 57.9% |
| BIG-Bench Hard | 78.8% | — |
| HellaSwag | 87.1% | — |
| LiveBench | — | 57.8% |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, o1-mini: 35.4 (#186)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | o1-mini |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 46.9% |
| LiveBench Math | — | 62% |
| LMArena Math | — | 1358 |
| MATH Level 5 | — | 89.2% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, o1-mini: 34.9 (#192)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | o1-mini |
|---|---|---|
| GPQA Diamond | — | 62.4% |
| Confabulations | — | 18.6% |
| LMArena Expert | — | 1316 |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Multilingual Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, o1-mini: 43.6 (#182)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | o1-mini |
|---|---|---|
| LMArena Non-English | — | 1289 |
| LMArena Chinese | — | 1314 |
| LMArena French | — | 1293 |
| LMArena German | — | 1278 |
| LMArena Japanese | — | 1245 |
| LMArena Korean | — | 1223 |
| LMArena Russian | — | 1283 |
| LMArena Spanish | — | 1303 |
Instruction Following Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, o1-mini: 66.7 (#206)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | o1-mini |
|---|---|---|
| LiveBench Instruction Following | — | 65.4% |
| LMArena Instruction Following | — | 1304 |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, o1-mini: 40.1 (#161)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | o1-mini |
|---|---|---|
| LMArena Longer Query | — | 1320 |
Writing & Preference Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, o1-mini: 48.4 (#202)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | o1-mini |
|---|---|---|
| LMArena Text | — | 1317 |
| LMArena Creative Writing | — | 1244 |
| Short-Story Creative Writing | — | 64.9% |
| LMArena Multi-Turn | — | 1314 |
| LiveBench Language | — | 40.9% |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than o1-mini?
o1-mini has enough public results to be ranked (#235); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or o1-mini better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 35.5 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and o1-mini share?
1 benchmark has published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and o1-mini has 39.