Model comparison
DeepSeek Coder 6.7B vs Qwen3-4B
Qwen3-4B has enough public results to be ranked (#264); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
DeepSeek
Alibaba (Qwen)Side by side
| DeepSeek Coder 6.7B | Qwen3-4B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.6 | 31.9 |
| Released | 2023-11-02 | 2025-04-29 |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 6 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
DeepSeek Coder 6.7B: 35.8 (#219), Qwen3-4B: —
| Benchmark | DeepSeek Coder 6.7B | Qwen3-4B |
|---|---|---|
| BigCodeBench Instruct | 35.5% | — |
| BigCodeBench Complete | 43.8% | — |
| HumanEval+ | 71.3% | — |
| MBPP+ | 65.6% | — |
Agentic & Tool Use Not comparable
DeepSeek Coder 6.7B: —, Qwen3-4B: 27.6 (#100)
| Benchmark | DeepSeek Coder 6.7B | Qwen3-4B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 35.7% |
Reasoning Not comparable
DeepSeek Coder 6.7B: —, Qwen3-4B: 19.2 (#268)
| Benchmark | DeepSeek Coder 6.7B | Qwen3-4B |
|---|---|---|
| Chess Puzzles | — | 4% |
| Epoch Capabilities Index | 89.62 | — |
| WinoGrande | 57.6% | — |
Math Not comparable
DeepSeek Coder 6.7B: —, Qwen3-4B: 29.7 (#240)
| Benchmark | DeepSeek Coder 6.7B | Qwen3-4B |
|---|---|---|
| MathArena Final-Answer Competitions | — | 38.5% |
| OTIS Mock AIME 2024-2025 | — | 52.2% |
| GSM8K | 21.3% | — |
Knowledge Not comparable
DeepSeek Coder 6.7B: —, Qwen3-4B: 33.0 (#208)
| Benchmark | DeepSeek Coder 6.7B | Qwen3-4B |
|---|---|---|
| GPQA Diamond | — | 52.3% |
| Vectara Hallucination Rate | — | 5.7% |
| ARC (AI2) Challenge | 36.4% | — |
| MMLU | 36.4% | — |
Frequently asked questions
Is DeepSeek Coder 6.7B better than Qwen3-4B?
Qwen3-4B has enough public results to be ranked (#264); DeepSeek Coder 6.7B does not yet, so treat this comparison as directional.
How many benchmarks do DeepSeek Coder 6.7B and Qwen3-4B share?
0 benchmarks have published results for both models. DeepSeek Coder 6.7B has 9 scored results on Noometry and Qwen3-4B has 6.