Model comparison
DeepSeek LLM 67B vs Qwen3.6 27B
Qwen3.6 27B is the stronger model overall, scoring 42.2 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 Qwen3.6 27B in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 27B leads 52.4 to 7.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 91.1% for Qwen3.6 27B.
Side by side
| DeepSeek LLM 67B | Qwen3.6 27B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.9 | 42.2 |
| Released | 2023-11-29 | 2026-04-22 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.60 |
| Output $ / M tokens | — | $3.60 |
| Results tracked | 15 | 11 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 27B leads
DeepSeek LLM 67B: 31.9 (#278), Qwen3.6 27B: 39.1 (#163)
| Benchmark | DeepSeek LLM 67B | Qwen3.6 27B |
|---|---|---|
| SciCode | — | 37.3% |
| LMArena Coding | 1096 | — |
Reasoning Qwen3.6 27B leads
DeepSeek LLM 67B: 16.5 (#304), Qwen3.6 27B: 25.0 (#153)
| Benchmark | DeepSeek LLM 67B | Qwen3.6 27B |
|---|---|---|
| Chess Puzzles | 0% | 22% |
| Epoch Capabilities Index | 110.5 | 146.5 |
| CritPt | — | 0.9% |
| LMArena Hard Prompts | 1070 | — |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 78.1% |
| LMCA | — | 34.5% |
Math Qwen3.6 27B leads
DeepSeek LLM 67B: 8.7 (#324), Qwen3.6 27B: 48.5 (#62)
| Benchmark | DeepSeek LLM 67B | Qwen3.6 27B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 91.1% |
| FrontierMath (Tiers 1-3) | — | 35.1% |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
Knowledge Qwen3.6 27B leads
DeepSeek LLM 67B: 7.0 (#313), Qwen3.6 27B: 52.4 (#63)
| Benchmark | DeepSeek LLM 67B | Qwen3.6 27B |
|---|---|---|
| GPQA Diamond | 24.6% | 85.9% |
Multilingual Not comparable
DeepSeek LLM 67B: 29.4 (#267), Qwen3.6 27B: —
| Benchmark | DeepSeek LLM 67B | Qwen3.6 27B |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |
Instruction Following Not comparable
DeepSeek LLM 67B: 55.4 (#277), Qwen3.6 27B: —
| Benchmark | DeepSeek LLM 67B | Qwen3.6 27B |
|---|---|---|
| LMArena Instruction Following | 1079 | — |
Long Context Not comparable
DeepSeek LLM 67B: 33.1 (#265), Qwen3.6 27B: —
| Benchmark | DeepSeek LLM 67B | Qwen3.6 27B |
|---|---|---|
| LMArena Longer Query | 1092 | — |
Writing & Preference Qwen3.6 27B leads
DeepSeek LLM 67B: 31.6 (#282), Qwen3.6 27B: 50.3 (#181)
| Benchmark | DeepSeek LLM 67B | Qwen3.6 27B |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| EQ-Bench 4 | — | 1026 |
| LMArena Multi-Turn | 1082 | — |
Frequently asked questions
Is DeepSeek LLM 67B better than Qwen3.6 27B?
Qwen3.6 27B is the stronger model overall, scoring 42.2 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Qwen3.6 27B better for coding?
Qwen3.6 27B scores higher on coding benchmarks: 39.1 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Qwen3.6 27B share?
4 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen3.6 27B has 11.