Model comparison
Deepseek Coder v2 vs o3-mini
Deepseek Coder v2 and o3-mini score almost the same on the Noometry Index (35.9 vs 36.7), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
DeepSeekSummary
- They share 17 benchmarks with published results for both. Deepseek Coder v2 scores higher in 3 categories and o3-mini in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where o3-mini leads 75.1 to 61.7.
- Deepseek Coder v2 has downloadable open weights; the other is API-only.
Side by side
| Deepseek Coder v2 | o3-mini | |
|---|---|---|
| Provider | DeepSeek | OpenAI |
| Noometry Index | 35.9 | 36.7 |
| Released | 2024-06-17 | 2024-12-20 |
| Weights | Open | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $1.10 |
| Output $ / M tokens | — | $4.40 |
| Results tracked | 24 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Deepseek Coder v2: 38.1 (#183), o3-mini: 40.8 (#132)
| Benchmark | Deepseek Coder v2 | o3-mini |
|---|---|---|
| LMArena Coding | 1251 | 1378 |
| Aider Polyglot | — | 60.4% |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| BigCodeBench Instruct | 48.2% | — |
| LiveBench Coding | — | 82.7% |
| BigCodeBench Complete | 59.7% | — |
| CadEval | — | 54% |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Agentic & Tool Use Not comparable
Deepseek Coder v2: —, o3-mini: 29.6 (#84)
| Benchmark | Deepseek Coder v2 | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), o3-mini: 16.3 (#305)
| Benchmark | Deepseek Coder v2 | o3-mini |
|---|---|---|
| LMArena Hard Prompts | 1207 | 1366 |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| LiveBench Reasoning | — | 89.6% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| Epoch Capabilities Index | — | 140.34 |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
| WinoGrande | 83.7% | — |
Math Deepseek Coder v2 leads
Deepseek Coder v2: 34.9 (#190), o3-mini: 28.1 (#244)
| Benchmark | Deepseek Coder v2 | o3-mini |
|---|---|---|
| LMArena Math | 1241 | 1396 |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 76.9% |
| LiveBench Math | — | 77.3% |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
| GSM8K | 94.5% | — |
Knowledge o3-mini leads
Deepseek Coder v2: 32.3 (#212), o3-mini: 38.3 (#146)
| Benchmark | Deepseek Coder v2 | o3-mini |
|---|---|---|
| LMArena Expert | 1181 | 1364 |
| GPQA Diamond | — | 77% |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual o3-mini leads
Deepseek Coder v2: 36.3 (#240), o3-mini: 45.7 (#164)
| Benchmark | Deepseek Coder v2 | o3-mini |
|---|---|---|
| LMArena Non-English | 1182 | 1319 |
| LMArena Chinese | 1201 | 1379 |
| LMArena French | 1185 | 1334 |
| LMArena German | 1164 | 1303 |
| LMArena Japanese | 1126 | 1286 |
| LMArena Korean | 1104 | 1314 |
| LMArena Russian | 1188 | 1304 |
| LMArena Spanish | 1153 | 1321 |
Instruction Following o3-mini leads
Deepseek Coder v2: 61.7 (#242), o3-mini: 75.1 (#72)
| Benchmark | Deepseek Coder v2 | o3-mini |
|---|---|---|
| LMArena Instruction Following | 1180 | 1337 |
| LiveBench Instruction Following | — | 84.4% |
Long Context Deepseek Coder v2 leads
Deepseek Coder v2: 37.0 (#224), o3-mini: 33.8 (#256)
| Benchmark | Deepseek Coder v2 | o3-mini |
|---|---|---|
| LMArena Longer Query | 1219 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference o3-mini leads
Deepseek Coder v2: 38.2 (#253), o3-mini: 50.3 (#182)
| Benchmark | Deepseek Coder v2 | o3-mini |
|---|---|---|
| LMArena Text | 1191 | 1337 |
| LMArena Creative Writing | 1120 | 1286 |
| LMArena Multi-Turn | 1177 | 1320 |
| Short-Story Creative Writing | — | 61.7% |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is Deepseek Coder v2 better than o3-mini?
Deepseek Coder v2 and o3-mini score almost the same on the Noometry Index (35.9 vs 36.7), so choose on price, context window or the category you care about most.
Is Deepseek Coder v2 or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 versus 38.1 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and o3-mini share?
17 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and o3-mini has 51.