Model comparison
DeepSeek-V2 (MoE-236B, May 2024) vs Qwen3 14B
Qwen3 14B has enough public results to be ranked (#225); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Last verified . 1 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 1 benchmark with published results for both. DeepSeek-V2 (MoE-236B, May 2024) scores higher in 1 category and Qwen3 14B in 0 categories; one gap is clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V2 (MoE-236B, May 2024) leads 40.4 to 37.3.
Side by side
| DeepSeek-V2 (MoE-236B, May 2024) | Qwen3 14B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 40.3 | 35.5 |
| Released | 2024-05-07 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.35 |
| Output $ / M tokens | — | $1.40 |
| Results tracked | 10 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V2 (MoE-236B, May 2024) leads
DeepSeek-V2 (MoE-236B, May 2024): 40.4 (#139), Qwen3 14B: 37.3 (#195)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen3 14B |
|---|---|---|
| SciCode | — | 31.6% |
| BigCodeBench Instruct | 48.9% | — |
| BigCodeBench Complete | 59.4% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Qwen3 14B: 29.6 (#83)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen3 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41% |
Reasoning Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Qwen3 14B: 18.5 (#280)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen3 14B |
|---|---|---|
| Epoch Capabilities Index | 124.77 | 138.23 |
| Kagi LLM Benchmark | — | 49.1% |
| CritPt | — | 0% |
| Chess Puzzles | — | 4% |
| DTBench | — | 64% |
| LMCA | — | 18.2% |
| BIG-Bench Hard | 78.8% | — |
| HellaSwag | 87.1% | — |
| PIQA | 83.9% | — |
| WinoGrande | 86.3% | — |
Math Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Qwen3 14B: 38.6 (#133)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen3 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 66.4% |
Knowledge Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Qwen3 14B: 39.3 (#134)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen3 14B |
|---|---|---|
| GPQA Diamond | — | 63.8% |
| Vectara Hallucination Rate | — | 5.4% |
| ARC (AI2) Challenge | 92.2% | — |
| MMLU | 78.4% | — |
| TriviaQA | 80% | — |
Long Context Not comparable
DeepSeek-V2 (MoE-236B, May 2024): —, Qwen3 14B: 38.1 (#204)
| Benchmark | DeepSeek-V2 (MoE-236B, May 2024) | Qwen3 14B |
|---|---|---|
| Fiction.LiveBench | — | 62.5% |
Frequently asked questions
Is DeepSeek-V2 (MoE-236B, May 2024) better than Qwen3 14B?
Qwen3 14B has enough public results to be ranked (#225); DeepSeek-V2 (MoE-236B, May 2024) does not yet, so treat this comparison as directional.
Is DeepSeek-V2 (MoE-236B, May 2024) or Qwen3 14B better for coding?
DeepSeek-V2 (MoE-236B, May 2024) scores higher on coding benchmarks: 40.4 versus 37.3 in the Noometry coding category.
How many benchmarks do DeepSeek-V2 (MoE-236B, May 2024) and Qwen3 14B share?
1 benchmark has published results for both models. DeepSeek-V2 (MoE-236B, May 2024) has 10 scored results on Noometry and Qwen3 14B has 12.