Model comparison
DeepSeek V4.1 Flash vs Qwen2.5-Coder-32B
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 33.4 on the Noometry Index.
Last verified . 13 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. DeepSeek V4.1 Flash scores higher in 8 categories and Qwen2.5-Coder-32B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek V4.1 Flash leads 66.7 to 33.3.
- DeepSeek V4.1 Flash is cheaper at $0.15 / $0.60 per million input/output tokens, against $0.66 / $1 for Qwen2.5-Coder-32B.
- DeepSeek V4.1 Flash accepts more context: 1M tokens versus 33K.
Side by side
| DeepSeek V4.1 Flash | Qwen2.5-Coder-32B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 52.8 | 33.4 |
| Released | 2026-09-09 | 2024-09-18 |
| Weights | Open | Open |
| Context window | 1M | 33K |
| Max output | 393K | 29K |
| Input $ / M tokens | $0.15 | $0.66 |
| Output $ / M tokens | $0.60 | $1 |
| Results tracked | 37 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 52.9 (#32), Qwen2.5-Coder-32B: 22.6 (#333)
| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Coding | 1506 | 1276 |
| SWE-bench Verified (bash only) | — | 9% |
| Aider Polyglot | — | 16.4% |
| LMArena WebDev | 1619 | — |
| SciCode | 51.9% | — |
| BigCodeBench Instruct | — | 49% |
| LiveBench Coding | — | 56.9% |
| BigCodeBench Complete | — | 58% |
| ALE-Bench | 1,092 | — |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 77% |
Agentic & Tool Use Not comparable
DeepSeek V4.1 Flash: 31.2 (#69), Qwen2.5-Coder-32B: —
| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Coder-32B |
|---|---|---|
| APEX-Agents | 39.5% | — |
| GDP.pdf | 19.8% | — |
Reasoning DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 50.2 (#36), Qwen2.5-Coder-32B: 21.2 (#225)
| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Hard Prompts | 1483 | 1251 |
| Epoch Capabilities Index | 154.9 | 119.49 |
| NYT Connections (extended) | 89.6% | — |
| CritPt | 14.3% | — |
| LiveBench Reasoning | — | 42.1% |
| Mystery Game Puzzles | 43% | — |
| DTBench | 89.9% | — |
| LiveBench Data Analysis | — | 49.9% |
| LMCA | 47% | — |
| Surface Evolver Bench | 46.3% | — |
| HellaSwag | — | 83% |
| LiveBench | — | 46.2% |
| WinoGrande | — | 80.8% |
Math DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 66.7 (#25), Qwen2.5-Coder-32B: 33.3 (#204)
| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Math | 1477 | 1251 |
| FrontierMath (Tiers 1-3) | 67.4% | — |
| FrontierMath Tier 4 | 26.8% | — |
| OTIS Mock AIME 2024-2025 | 98.3% | — |
| ProofBench | 54% | — |
| LiveBench Math | — | 46.6% |
| GSM8K | — | 93% |
Knowledge DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 57.9 (#38), Qwen2.5-Coder-32B: 33.4 (#203)
| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Expert | 1506 | 1221 |
| GPQA Diamond | 89.8% | — |
| ARC (AI2) Challenge | — | 70.5% |
| MMLU | — | 79.1% |
Multimodal Not comparable
DeepSeek V4.1 Flash: 39.1 (#61), Qwen2.5-Coder-32B: —
| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Vision | 1277 | — |
| Furniture Assembly | 34.2% | — |
Multilingual DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 55.0 (#35), Qwen2.5-Coder-32B: 37.8 (#235)
| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Non-English | 1448 | 1205 |
| LMArena Chinese | 1497 | 1222 |
| LMArena Russian | 1471 | 1228 |
| LMArena French | 1452 | — |
| LMArena German | 1484 | — |
| LMArena Japanese | 1412 | — |
| LMArena Korean | 1452 | — |
| LMArena Spanish | 1459 | — |
Instruction Following DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 77.3 (#26), Qwen2.5-Coder-32B: 61.4 (#245)
| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Instruction Following | 1474 | 1223 |
| LiveBench Instruction Following | — | 58.7% |
Long Context DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 45.2 (#47), Qwen2.5-Coder-32B: 38.0 (#208)
| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Longer Query | 1475 | 1251 |
Writing & Preference DeepSeek V4.1 Flash leads
DeepSeek V4.1 Flash: 65.4 (#48), Qwen2.5-Coder-32B: 41.6 (#240)
| Benchmark | DeepSeek V4.1 Flash | Qwen2.5-Coder-32B |
|---|---|---|
| LMArena Text | 1462 | 1230 |
| LMArena Creative Writing | 1435 | 1174 |
| LMArena Multi-Turn | 1457 | 1222 |
| EQ-Bench Creative Writing | 1540 | — |
| LiveBench Language | — | 23.3% |
Frequently asked questions
Is DeepSeek V4.1 Flash better than Qwen2.5-Coder-32B?
DeepSeek V4.1 Flash is the stronger model overall, scoring 52.8 to 33.4 on the Noometry Index.
Which is cheaper, DeepSeek V4.1 Flash or Qwen2.5-Coder-32B?
DeepSeek V4.1 Flash is cheaper. It lists at $0.15 per million input tokens and $0.60 per million output tokens; Qwen2.5-Coder-32B lists at $0.66 and $1.
Is DeepSeek V4.1 Flash or Qwen2.5-Coder-32B better for coding?
DeepSeek V4.1 Flash scores higher on coding benchmarks: 52.9 versus 22.6 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4.1 Flash does, with 1M tokens against 33K.
How many benchmarks do DeepSeek V4.1 Flash and Qwen2.5-Coder-32B share?
13 benchmarks have published results for both models. DeepSeek V4.1 Flash has 37 scored results on Noometry and Qwen2.5-Coder-32B has 31.