Model comparison
DeepSeek-R1-Distill-Qwen-14B vs StarCoder 2 3B
DeepSeek-R1-Distill-Qwen-14B has enough public results to be ranked (#252); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 2 shared benchmarks.
DeepSeek
NVIDIASummary
- They share 2 benchmarks with published results for both. DeepSeek-R1-Distill-Qwen-14B scores higher in 1 category and StarCoder 2 3B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-R1-Distill-Qwen-14B leads 36.9 to 33.5.
- The biggest single-benchmark swing is BigCodeBench Complete: 48.4% for DeepSeek-R1-Distill-Qwen-14B and 21.4% for StarCoder 2 3B.
Side by side
| DeepSeek-R1-Distill-Qwen-14B | StarCoder 2 3B | |
|---|---|---|
| Provider | DeepSeek | NVIDIA |
| Noometry Index | 32.7 | 36.3 |
| Released | 2025-01-20 | 2024-02-22 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 7 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1-Distill-Qwen-14B leads
DeepSeek-R1-Distill-Qwen-14B: 36.9 (#200), StarCoder 2 3B: 33.5
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | StarCoder 2 3B |
|---|---|---|
| BigCodeBench Complete | 48.4% | 21.4% |
| BigCodeBench Instruct | 38.1% | — |
| HumanEval+ | — | 27.4% |
Reasoning Not comparable
DeepSeek-R1-Distill-Qwen-14B: 19.2 (#263), StarCoder 2 3B: —
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | StarCoder 2 3B |
|---|---|---|
| Epoch Capabilities Index | 135.43 | 88.76 |
| Chess Puzzles | 1% | — |
| WinoGrande | — | 57.1% |
Math Not comparable
DeepSeek-R1-Distill-Qwen-14B: 35.5 (#184), StarCoder 2 3B: —
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | StarCoder 2 3B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 50.6% | — |
| MATH Level 5 | 87.1% | — |
| GSM8K | — | 21.6% |
Knowledge Not comparable
DeepSeek-R1-Distill-Qwen-14B: 24.1 (#270), StarCoder 2 3B: —
| Benchmark | DeepSeek-R1-Distill-Qwen-14B | StarCoder 2 3B |
|---|---|---|
| GPQA Diamond | 44.7% | — |
| ARC (AI2) Challenge | — | 34.2% |
| MMLU | — | 36.6% |
Frequently asked questions
Is DeepSeek-R1-Distill-Qwen-14B better than StarCoder 2 3B?
DeepSeek-R1-Distill-Qwen-14B has enough public results to be ranked (#252); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is DeepSeek-R1-Distill-Qwen-14B or StarCoder 2 3B better for coding?
DeepSeek-R1-Distill-Qwen-14B scores higher on coding benchmarks: 36.9 versus 33.5 in the Noometry coding category.
How many benchmarks do DeepSeek-R1-Distill-Qwen-14B and StarCoder 2 3B share?
2 benchmarks have published results for both models. DeepSeek-R1-Distill-Qwen-14B has 7 scored results on Noometry and StarCoder 2 3B has 7.