Model comparison
DeepSeek-R1 vs Qwen3.5-9B
DeepSeek-R1 is the stronger model overall, scoring 42.0 to 33.3 on the Noometry Index. Qwen3.5-9B costs 8.1× less per token, which makes it the better buy when DeepSeek-R1's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 5 benchmarks with published results for both. DeepSeek-R1 scores higher in 3 categories and Qwen3.5-9B in 2 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where DeepSeek-R1 leads 30.4 to 14.4.
- The biggest single-benchmark swing is SciCode: 35.7% for DeepSeek-R1 and 27.5% for Qwen3.5-9B.
- Qwen3.5-9B is cheaper at $0.10 / $0.15 per million input/output tokens, against $0.50 / $2.15 for DeepSeek-R1.
- Qwen3.5-9B accepts more context: 262K tokens versus 164K.
- Qwen3.5-9B has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-R1 | Qwen3.5-9B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.0 | 33.3 |
| Released | 2025-01-20 | 2026-02-23 |
| Weights | Proprietary | Open |
| Context window | 164K | 262K |
| Max output | 64K | 66K |
| Input $ / M tokens | $0.50 | $0.10 |
| Output $ / M tokens | $2.15 | $0.15 |
| Results tracked | 52 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-R1 leads
DeepSeek-R1: 45.9 (#63), Qwen3.5-9B: 35.3 (#213)
| Benchmark | DeepSeek-R1 | Qwen3.5-9B |
|---|---|---|
| SciCode | 35.7% | 27.5% |
| Aider Polyglot | 71.4% | — |
| WeirdML | 41.6% | — |
| LiveBench Coding | 66.7% | — |
| LMArena Coding | 1427 | — |
| ALE-Bench | 804.12 | — |
| AlgoTune | 1.7 | — |
Agentic & Tool Use DeepSeek-R1 leads
DeepSeek-R1: 30.4 (#68), Qwen3.5-9B: 14.4 (#143)
| Benchmark | DeepSeek-R1 | Qwen3.5-9B |
|---|---|---|
| Terminal-Bench | — | 9.2% |
| DeepResearch Bench | 35.1% | — |
| BALROG | 34.9% | — |
| METR Time Horizons | 53.8% | — |
Reasoning Qwen3.5-9B leads
DeepSeek-R1: 18.7 (#253), Qwen3.5-9B: 22.5 (#178)
| Benchmark | DeepSeek-R1 | Qwen3.5-9B |
|---|---|---|
| CritPt | 1.1% | 0.3% |
| Epoch Capabilities Index | 141.3 | 139.45 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 40.8% | — |
| Kagi LLM Benchmark | 69.4% | — |
| ARC-AGI-1 | 21.2% | — |
| Chess Puzzles | — | 12% |
| LiveBench Reasoning | 83.2% | — |
| LMArena Hard Prompts | 1415 | — |
| DTBench | — | 71.2% |
| LiveBench Data Analysis | 69.8% | — |
| LMCA | — | 24.5% |
| ForecastBench | 60 | — |
| LiveBench | 71.6% | — |
Math DeepSeek-R1 leads
DeepSeek-R1: 42.0 (#70), Qwen3.5-9B: 33.5 (#174)
| Benchmark | DeepSeek-R1 | Qwen3.5-9B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.4% | 61.7% |
| MathArena Final-Answer Competitions | — | 48.5% |
| Omni-MATH | 42.4% | — |
| LiveBench Math | 80.7% | — |
| LMArena Math | 1401 | — |
| MATH Level 5 | 96.6% | — |
Knowledge Qwen3.5-9B leads
DeepSeek-R1: 44.3 (#81), Qwen3.5-9B: 46.0 (#77)
| Benchmark | DeepSeek-R1 | Qwen3.5-9B |
|---|---|---|
| GPQA Diamond | 76.3% | 79% |
| MMLU-Pro | 79.3% | — |
| Confabulations | 12.7% | — |
| Vectara Hallucination Rate | 11.3% | — |
| GPQA (HELM) | 66.6% | — |
| LMArena Expert | 1394 | — |
Multilingual Not comparable
DeepSeek-R1: 52.6 (#80), Qwen3.5-9B: —
| Benchmark | DeepSeek-R1 | Qwen3.5-9B |
|---|---|---|
| LMArena Non-English | 1412 | — |
| LMArena Chinese | 1443 | — |
| LMArena French | 1415 | — |
| LMArena German | 1405 | — |
| LMArena Japanese | 1394 | — |
| LMArena Korean | 1359 | — |
| LMArena Russian | 1423 | — |
| LMArena Spanish | 1410 | — |
Instruction Following Not comparable
DeepSeek-R1: 72.2 (#138), Qwen3.5-9B: —
| Benchmark | DeepSeek-R1 | Qwen3.5-9B |
|---|---|---|
| LiveBench Instruction Following | 80.5% | — |
| IFEval | 78.4% | — |
| LMArena Instruction Following | 1382 | — |
Long Context Not comparable
DeepSeek-R1: 45.4 (#36), Qwen3.5-9B: —
| Benchmark | DeepSeek-R1 | Qwen3.5-9B |
|---|---|---|
| Fiction.LiveBench | 75% | — |
| LMArena Longer Query | 1391 | — |
Writing & Preference Not comparable
DeepSeek-R1: 61.5 (#84), Qwen3.5-9B: —
| Benchmark | DeepSeek-R1 | Qwen3.5-9B |
|---|---|---|
| LMArena Text | 1428 | — |
| LMArena Creative Writing | 1406 | — |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1500 | — |
| WildBench | 82.8% | — |
| LMArena Multi-Turn | 1404 | — |
| LiveBench Language | 48.5% | — |
Frequently asked questions
Is DeepSeek-R1 better than Qwen3.5-9B?
DeepSeek-R1 is the stronger model overall, scoring 42.0 to 33.3 on the Noometry Index. Qwen3.5-9B costs 8.1× less per token, which makes it the better buy when DeepSeek-R1's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-R1 or Qwen3.5-9B?
Qwen3.5-9B is cheaper. It lists at $0.10 per million input tokens and $0.15 per million output tokens; DeepSeek-R1 lists at $0.50 and $2.15.
Is DeepSeek-R1 or Qwen3.5-9B better for coding?
DeepSeek-R1 scores higher on coding benchmarks: 45.9 versus 35.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5-9B does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-R1 and Qwen3.5-9B share?
5 benchmarks have published results for both models. DeepSeek-R1 has 52 scored results on Noometry and Qwen3.5-9B has 10.