Model comparison
DeepSeek LLM 67B vs Qwen3.5-9B
Qwen3.5-9B is the stronger model overall, scoring 33.8 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 Qwen3.5-9B in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.5-9B leads 46.0 to 7.0.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 0.8% for DeepSeek LLM 67B and 61.7% for Qwen3.5-9B.
Side by side
| DeepSeek LLM 67B | Qwen3.5-9B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 24.9 | 33.8 |
| Released | 2023-11-29 | 2026-02-23 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 15 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.5-9B leads
DeepSeek LLM 67B: 31.9 (#278), Qwen3.5-9B: 35.9 (#217)
| Benchmark | DeepSeek LLM 67B | Qwen3.5-9B |
|---|---|---|
| SciCode | — | 27.5% |
| LMArena Coding | 1096 | — |
Agentic & Tool Use Not comparable
DeepSeek LLM 67B: —, Qwen3.5-9B: 14.5 (#151)
| Benchmark | DeepSeek LLM 67B | Qwen3.5-9B |
|---|---|---|
| Terminal-Bench | — | 9.2% |
Reasoning Qwen3.5-9B leads
DeepSeek LLM 67B: 16.5 (#304), Qwen3.5-9B: 23.1 (#182)
| Benchmark | DeepSeek LLM 67B | Qwen3.5-9B |
|---|---|---|
| Chess Puzzles | 0% | 12% |
| Epoch Capabilities Index | 110.5 | 139.46 |
| CritPt | — | 0.3% |
| LMArena Hard Prompts | 1070 | — |
| DTBench | — | 71.2% |
| LMCA | — | 24.5% |
Math Qwen3.5-9B leads
DeepSeek LLM 67B: 8.7 (#324), Qwen3.5-9B: 34.8 (#192)
| Benchmark | DeepSeek LLM 67B | Qwen3.5-9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 0.8% | 61.7% |
| MathArena Final-Answer Competitions | — | 48.5% |
| LMArena Math | 1108 | — |
| MATH Level 5 | 6.4% | — |
Knowledge Qwen3.5-9B leads
DeepSeek LLM 67B: 7.0 (#313), Qwen3.5-9B: 46.0 (#84)
| Benchmark | DeepSeek LLM 67B | Qwen3.5-9B |
|---|---|---|
| GPQA Diamond | 24.6% | 79% |
Multilingual Not comparable
DeepSeek LLM 67B: 29.4 (#267), Qwen3.5-9B: —
| Benchmark | DeepSeek LLM 67B | Qwen3.5-9B |
|---|---|---|
| LMArena Non-English | 1073 | — |
| LMArena Chinese | 1132 | — |
Instruction Following Not comparable
DeepSeek LLM 67B: 55.4 (#277), Qwen3.5-9B: —
| Benchmark | DeepSeek LLM 67B | Qwen3.5-9B |
|---|---|---|
| LMArena Instruction Following | 1079 | — |
Long Context Not comparable
DeepSeek LLM 67B: 33.1 (#265), Qwen3.5-9B: —
| Benchmark | DeepSeek LLM 67B | Qwen3.5-9B |
|---|---|---|
| LMArena Longer Query | 1092 | — |
Writing & Preference Not comparable
DeepSeek LLM 67B: 31.6 (#282), Qwen3.5-9B: —
| Benchmark | DeepSeek LLM 67B | Qwen3.5-9B |
|---|---|---|
| LMArena Text | 1105 | — |
| LMArena Creative Writing | 1067 | — |
| LMArena Multi-Turn | 1082 | — |
Frequently asked questions
Is DeepSeek LLM 67B better than Qwen3.5-9B?
Qwen3.5-9B is the stronger model overall, scoring 33.8 to 24.9 on the Noometry Index.
Is DeepSeek LLM 67B or Qwen3.5-9B better for coding?
Qwen3.5-9B scores higher on coding benchmarks: 35.9 versus 31.9 in the Noometry coding category.
How many benchmarks do DeepSeek LLM 67B and Qwen3.5-9B share?
4 benchmarks have published results for both models. DeepSeek LLM 67B has 15 scored results on Noometry and Qwen3.5-9B has 10.