Model comparison
Deepseek Coder v2 vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 35.9 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeekSummary
- The widest gap is in long context, where o3-pro leads 72.2 to 37.0.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | o3-pro | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 35.9 | 42.9 |
| Released | 2024-06-17 | 2025-06-10 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $20 |
| Output $ / M tokens | — | $80 |
| Results tracked | 24 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Deepseek Coder v2: 38.1 (#183), o3-pro: 55.5 (#24)
| Benchmark | Deepseek Coder v2 | o3-pro |
|---|---|---|
| Aider Polyglot | — | 84.9% |
| WeirdML | — | 58.2% |
| BigCodeBench Instruct | 48.2% | — |
| LMArena Coding | 1251 | — |
| BigCodeBench Complete | 59.7% | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Too close to call
Deepseek Coder v2: 23.6 (#176), o3-pro: 23.8 (#171)
| Benchmark | Deepseek Coder v2 | o3-pro |
|---|---|---|
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 72.1% |
| ARC-AGI-1 | — | 59.3% |
| LMArena Hard Prompts | 1207 | — |
| DTBench | — | 86.9% |
| LMCA | — | 38.5% |
| Epoch Capabilities Index | — | 147.42 |
| WinoGrande | 83.7% | — |
Math Not comparable
Deepseek Coder v2: 34.9 (#190), o3-pro: —
| Benchmark | Deepseek Coder v2 | o3-pro |
|---|---|---|
| LMArena Math | 1241 | — |
| GSM8K | 94.5% | — |
Knowledge Deepseek Coder v2 leads
Deepseek Coder v2: 32.3 (#212), o3-pro: 29.5 (#238)
| Benchmark | Deepseek Coder v2 | o3-pro |
|---|---|---|
| Confabulations | — | 14.2% |
| Vectara Hallucination Rate | — | 23.3% |
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Not comparable
Deepseek Coder v2: 36.3 (#240), o3-pro: —
| Benchmark | Deepseek Coder v2 | o3-pro |
|---|---|---|
| LMArena Non-English | 1182 | — |
| LMArena Chinese | 1201 | — |
| LMArena French | 1185 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Not comparable
Deepseek Coder v2: 61.7 (#242), o3-pro: —
| Benchmark | Deepseek Coder v2 | o3-pro |
|---|---|---|
| LMArena Instruction Following | 1180 | — |
Long Context o3-pro leads
Deepseek Coder v2: 37.0 (#224), o3-pro: 72.2 (#1)
| Benchmark | Deepseek Coder v2 | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1219 | — |
Writing & Preference o3-pro leads
Deepseek Coder v2: 38.2 (#253), o3-pro: 57.1 (#133)
| Benchmark | Deepseek Coder v2 | o3-pro |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1120 | — |
| Short-Story Creative Writing | — | 84.4% |
| LMArena Multi-Turn | 1177 | — |
Frequently asked questions
Is Deepseek Coder v2 better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 35.9 on the Noometry Index.
Is Deepseek Coder v2 or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and o3-pro share?
0 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and o3-pro has 12.