Model comparison
Deepseek Coder v2 vs DeepSeek-R1-Distill-Qwen-32B
Deepseek Coder v2 and DeepSeek-R1-Distill-Qwen-32B score almost the same on the Noometry Index (35.3 vs 35.0), so choose on price, context window or the category you care about most.
Last verified . 2 shared benchmarks.
DeepSeekSummary
- They share 2 benchmarks with published results for both. Deepseek Coder v2 scores higher in 3 categories and DeepSeek-R1-Distill-Qwen-32B in 3 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-R1-Distill-Qwen-32B leads 49.6 to 38.4.
Side by side
| Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-32B | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 35.3 | 35.0 |
| Released | 2024-06-17 | 2025-01-20 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Deepseek Coder v2: 37.5 (#178), DeepSeek-R1-Distill-Qwen-32B: 35.6 (#209)
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| BigCodeBench Instruct | 48.2% | 43.9% |
| BigCodeBench Complete | 59.7% | 54.9% |
| LiveBench Coding | — | 33.7% |
| LMArena Coding | 1251 | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Agentic & Tool Use Not comparable
Deepseek Coder v2: —, DeepSeek-R1-Distill-Qwen-32B: 27.8 (#88)
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| BALROG | — | 19.5% |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 22.6 (#175), DeepSeek-R1-Distill-Qwen-32B: 17.6 (#280)
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| Chess Puzzles | — | 1% |
| LiveBench Reasoning | — | 52.3% |
| LMArena Hard Prompts | 1207 | — |
| LiveBench Data Analysis | — | 45.4% |
| Epoch Capabilities Index | — | 137.43 |
| LiveBench | — | 45.5% |
| WinoGrande | 83.7% | — |
Math Too close to call
Deepseek Coder v2: 32.3 (#188), DeepSeek-R1-Distill-Qwen-32B: 32.9 (#183)
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 55.6% |
| LiveBench Math | — | 59.4% |
| LMArena Math | 1241 | — |
| GSM8K | 94.5% | — |
Knowledge DeepSeek-R1-Distill-Qwen-32B leads
Deepseek Coder v2: 31.7 (#209), DeepSeek-R1-Distill-Qwen-32B: 35.7 (#167)
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| GPQA Diamond | — | 64.1% |
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Not comparable
Deepseek Coder v2: 36.4 (#235), DeepSeek-R1-Distill-Qwen-32B: —
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LMArena Non-English | 1182 | — |
| LMArena Chinese | 1201 | — |
| LMArena French | 1184 | — |
| LMArena German | 1164 | — |
| LMArena Japanese | 1126 | — |
| LMArena Korean | 1104 | — |
| LMArena Russian | 1188 | — |
| LMArena Spanish | 1153 | — |
Instruction Following Too close to call
Deepseek Coder v2: 61.9 (#237), DeepSeek-R1-Distill-Qwen-32B: 61.7 (#239)
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LiveBench Instruction Following | — | 55.7% |
| LMArena Instruction Following | 1180 | — |
Long Context Not comparable
Deepseek Coder v2: 37.0 (#219), DeepSeek-R1-Distill-Qwen-32B: —
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LMArena Longer Query | 1219 | — |
Writing & Preference DeepSeek-R1-Distill-Qwen-32B leads
Deepseek Coder v2: 38.4 (#249), DeepSeek-R1-Distill-Qwen-32B: 49.6 (#185)
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-32B |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1120 | — |
| LMArena Multi-Turn | 1176 | — |
| LiveBench Language | — | 26.8% |
Frequently asked questions
Is Deepseek Coder v2 better than DeepSeek-R1-Distill-Qwen-32B?
Deepseek Coder v2 and DeepSeek-R1-Distill-Qwen-32B score almost the same on the Noometry Index (35.3 vs 35.0), so choose on price, context window or the category you care about most.
Is Deepseek Coder v2 or DeepSeek-R1-Distill-Qwen-32B better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 37.5 versus 35.6 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and DeepSeek-R1-Distill-Qwen-32B share?
2 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and DeepSeek-R1-Distill-Qwen-32B has 14.