Model comparison
DeepSeek LLM 67B vs Qwen3 14B
Qwen3 14B is the stronger model overall, scoring 35.5 to 24.9 on the Noometry Index.
Last verified . 4 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 4 benchmarks with published results for both. DeepSeek LLM 67B scores higher in 0 categories and Qwen3 14B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3 14B leads 39.3 to 7.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 66.4% for Qwen3 14B.
Side by side
| DeepSeek LLM 67B | Qwen3 14B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.9 | 35.5 |
| Released | 2023-11-29 | 2025-04 |
| Weights | Open | Open |
| Context window | — | 131K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.35 |
| Output $ / M tokens | — | $1.40 |
| Results tracked | 15 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 14B leads
DeepSeek LLM 67B: 31.9 (#278), Qwen3 14B: 37.3 (#195)
| Benchmark | DeepSeek LLM 67B | Qwen3 14B |
|---|---|---|
| SciCode | — | 31.6% |
| LMArena Coding | 1096 | — |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Qwen3 14B: 29.6 (#83)
| Benchmark | DeepSeek LLM 67B | Qwen3 14B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 41% |
Reasoning Qwen3 14B leads
DeepSeek LLM 67B: 16.5 (#304), Qwen3 14B: 18.5 (#280)
| Benchmark | DeepSeek LLM 67B | Qwen3 14B |
|---|---|---|
| Chess Puzzles | 0% | 4% |
| Epoch Capabilities Index | 110.5 | 138.23 |
| Kagi LLM Benchmark | — | 49.1% |
| CritPt | — | 0% |
| LMArena Hard Prompts | 1070 | — |
| DTBench | — | 64% |
| LMCA | — | 18.2% |
Math Qwen3 14B leads
DeepSeek LLM 67B: 8.7 (#324), Qwen3 14B: 38.6 (#133)
| Benchmark | DeepSeek LLM 67B | Qwen3 14B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 66.4% |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
Knowledge Qwen3 14B leads
DeepSeek LLM 67B: 7.0 (#313), Qwen3 14B: 39.3 (#134)
| Benchmark | DeepSeek LLM 67B | Qwen3 14B |
|---|---|---|
| GPQA Diamond | 24.6% | 63.8% |
| Vectara Hallucination Rate | — | 5.4% |
Multilingual Not comparable
DeepSeek LLM 67B: 29.4 (#267), Qwen3 14B: —
| Benchmark | DeepSeek LLM 67B | Qwen3 14B |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |
Instruction Following Not comparable
DeepSeek LLM 67B: 55.4 (#277), Qwen3 14B: —
| Benchmark | DeepSeek LLM 67B | Qwen3 14B |
|---|---|---|
| LMArena Instruction Following | 1079 | — |
Long Context Qwen3 14B leads
DeepSeek LLM 67B: 33.1 (#265), Qwen3 14B: 38.1 (#204)
| Benchmark | DeepSeek LLM 67B | Qwen3 14B |
|---|---|---|
| Fiction.LiveBench | — | 62.5% |
| LMArena Longer Query | 1092 | — |
Writing & Preference Not comparable
DeepSeek LLM 67B: 31.6 (#282), Qwen3 14B: —
| Benchmark | DeepSeek LLM 67B | Qwen3 14B |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| LMArena Multi-Turn | 1082 | — |
Frequently asked questions
Is DeepSeek LLM 67B better than Qwen3 14B?
Qwen3 14B is the stronger model overall, scoring 35.5 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Qwen3 14B better for coding?
Qwen3 14B scores higher on coding benchmarks: 37.3 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Qwen3 14B share?
4 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen3 14B has 12.