Model comparison
Deepseek Coder v2 vs DeepSeek-R1-Distill-Qwen-14B
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 32.7 on the Noometry Index.
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-14B in 1 category; 3 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Deepseek Coder v2 leads 32.3 to 24.1.
- The biggest single-benchmark swing is BigCodeBench Complete: 59.7% for Deepseek Coder v2 and 48.4% for DeepSeek-R1-Distill-Qwen-14B.
Side by side
| Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-14B | |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Noometry Index | 35.9 | 32.7 |
| Released | 2024-06-17 | 2025-01-20 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 24 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Deepseek Coder v2 leads
Deepseek Coder v2: 38.1 (#183), DeepSeek-R1-Distill-Qwen-14B: 36.9 (#200)
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-14B |
|---|---|---|
| BigCodeBench Instruct | 48.2% | 38.1% |
| BigCodeBench Complete | 59.7% | 48.4% |
| LMArena Coding | 1251 | — |
| HumanEval+ | 82.3% | — |
| MBPP+ | 75.1% | — |
Reasoning Deepseek Coder v2 leads
Deepseek Coder v2: 23.6 (#176), DeepSeek-R1-Distill-Qwen-14B: 19.2 (#263)
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-14B |
|---|---|---|
| Chess Puzzles | — | 1% |
| LMArena Hard Prompts | 1207 | — |
| Epoch Capabilities Index | — | 135.43 |
| WinoGrande | 83.7% | — |
Math Too close to call
Deepseek Coder v2: 34.9 (#190), DeepSeek-R1-Distill-Qwen-14B: 35.5 (#184)
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 50.6% |
| LMArena Math | 1241 | — |
| MATH Level 5 | — | 87.1% |
| GSM8K | 94.5% | — |
Knowledge Deepseek Coder v2 leads
Deepseek Coder v2: 32.3 (#212), DeepSeek-R1-Distill-Qwen-14B: 24.1 (#270)
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-14B |
|---|---|---|
| GPQA Diamond | — | 44.7% |
| LMArena Expert | 1181 | — |
| ARC (AI2) Challenge | 64.3% | — |
Multilingual Not comparable
Deepseek Coder v2: 36.3 (#240), DeepSeek-R1-Distill-Qwen-14B: —
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-14B |
|---|---|---|
| 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), DeepSeek-R1-Distill-Qwen-14B: —
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1180 | — |
Long Context Not comparable
Deepseek Coder v2: 37.0 (#224), DeepSeek-R1-Distill-Qwen-14B: —
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1219 | — |
Writing & Preference Not comparable
Deepseek Coder v2: 38.2 (#253), DeepSeek-R1-Distill-Qwen-14B: —
| Benchmark | Deepseek Coder v2 | DeepSeek-R1-Distill-Qwen-14B |
|---|---|---|
| LMArena Text | 1191 | — |
| LMArena Creative Writing | 1120 | — |
| LMArena Multi-Turn | 1177 | — |
Frequently asked questions
Is Deepseek Coder v2 better than DeepSeek-R1-Distill-Qwen-14B?
Deepseek Coder v2 is the stronger model overall, scoring 35.9 to 32.7 on the Noometry Index.
Is Deepseek Coder v2 or DeepSeek-R1-Distill-Qwen-14B better for coding?
Deepseek Coder v2 scores higher on coding benchmarks: 38.1 versus 36.9 in the Noometry coding category.
How many benchmarks do Deepseek Coder v2 and DeepSeek-R1-Distill-Qwen-14B share?
2 benchmarks have published results for both models. Deepseek Coder v2 has 24 scored results on Noometry and DeepSeek-R1-Distill-Qwen-14B has 7.