Model comparison
DeepSeek-V3.2-Exp vs Qwen3.5-Flash
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 42.5 on the Noometry Index. Qwen3.5-Flash costs 1.7× less per token, which makes it the better buy when DeepSeek-V3.2-Exp's lead doesn't matter for your workload.
Last verified . 28 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 28 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 7 categories and Qwen3.5-Flash in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in coding, where DeepSeek-V3.2-Exp leads 46.5 to 34.2.
- The biggest single-benchmark swing is Chess Puzzles: 14% for DeepSeek-V3.2-Exp and 21% for Qwen3.5-Flash.
- Qwen3.5-Flash is cheaper at $0.10 / $0.40 per million input/output tokens, against $0.26 / $0.38 for DeepSeek-V3.2-Exp.
- Qwen3.5-Flash accepts more context: 1M tokens versus 164K.
- DeepSeek-V3.2-Exp has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.2-Exp | Qwen3.5-Flash | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 44.3 | 42.5 |
| Released | 2025-09-29 | 2026-02-23 |
| Weights | Open | Proprietary |
| Context window | 164K | 1M |
| Max output | 66K | 66K |
| Input $ / M tokens | $0.26 | $0.10 |
| Output $ / M tokens | $0.38 | $0.40 |
| Results tracked | 49 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 46.5 (#65), Qwen3.5-Flash: 34.2 (#242)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.5-Flash |
|---|---|---|
| LMArena WebDev | 1362 | 1244 |
| LMArena Coding | 1454 | 1412 |
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| SWE-bench Multilingual | 59% | — |
| SciCode | 38.9% | — |
| WeirdML | 39.5% | — |
| ALE-Bench | — | 221.8 |
Agentic & Tool Use Not comparable
DeepSeek-V3.2-Exp: 32.7 (#59), Qwen3.5-Flash: —
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.5-Flash |
|---|---|---|
| Vending-Bench 2 | 1,034 | 462.69 |
| Terminal-Bench | 39.6% | — |
| APEX-Agents | 21.3% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| TheAgentCompany | 42.9% | — |
Reasoning Qwen3.5-Flash leads
DeepSeek-V3.2-Exp: 22.1 (#208), Qwen3.5-Flash: 33.7 (#72)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.5-Flash |
|---|---|---|
| Chess Puzzles | 14% | 21% |
| LMArena Hard Prompts | 1434 | 1403 |
| DTBench | 87.7% | 82.9% |
| LMCA | 29.1% | 29.1% |
| Epoch Capabilities Index | 146.27 | 143.98 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | 52.2% | — |
| NYT Connections (extended) | 36.7% | — |
| ARC-AGI-1 | 57% | — |
| CritPt | 2.9% | — |
| Thematic Generalization | 65% | — |
| Mystery Game Puzzles | — | 20% |
Math DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 41.7 (#87), Qwen3.5-Flash: 37.4 (#158)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.5-Flash |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 87.8% | 84.4% |
| LMArena Math | 1435 | 1407 |
| FrontierMath (Feb 2025 set) | 22.1% | 6.2% |
| FrontierMath Tier 4 (v1) | 2.1% | 0% |
| FrontierMath (Tiers 1-3) | — | 18.2% |
| MathArena Final-Answer Competitions | 57.7% | — |
| ProofBench | 8% | — |
Knowledge DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 51.7 (#66), Qwen3.5-Flash: 43.2 (#93)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.5-Flash |
|---|---|---|
| GPQA Diamond | 83.4% | 82.3% |
| Vectara Hallucination Rate | 5.3% | 10.5% |
| LMArena Expert | 1436 | 1407 |
| SimpleQA Verified | — | 20.3% |
Multilingual DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 52.2 (#90), Qwen3.5-Flash: 50.5 (#121)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.5-Flash |
|---|---|---|
| LMArena Non-English | 1409 | 1385 |
| LMArena Chinese | 1461 | 1446 |
| LMArena French | 1433 | 1412 |
| LMArena German | 1440 | 1390 |
| LMArena Japanese | 1374 | 1368 |
| LMArena Korean | 1371 | 1344 |
| LMArena Russian | 1424 | 1379 |
| LMArena Spanish | 1440 | 1400 |
Instruction Following DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 74.5 (#93), Qwen3.5-Flash: 72.6 (#139)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.5-Flash |
|---|---|---|
| LMArena Instruction Following | 1413 | 1374 |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#16), Qwen3.5-Flash: 42.4 (#124)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.5-Flash |
|---|---|---|
| LMArena Longer Query | 1428 | 1392 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 62.4 (#77), Qwen3.5-Flash: 57.9 (#122)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.5-Flash |
|---|---|---|
| LMArena Text | 1425 | 1397 |
| LMArena Creative Writing | 1403 | 1343 |
| LMArena Multi-Turn | 1427 | 1393 |
| EQ-Bench Creative Writing | 1515 | — |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Qwen3.5-Flash?
DeepSeek-V3.2-Exp is the stronger model overall, scoring 44.3 to 42.5 on the Noometry Index. Qwen3.5-Flash costs 1.7× less per token, which makes it the better buy when DeepSeek-V3.2-Exp's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.2-Exp or Qwen3.5-Flash?
Qwen3.5-Flash is cheaper. It lists at $0.10 per million input tokens and $0.40 per million output tokens; DeepSeek-V3.2-Exp lists at $0.26 and $0.38.
Is DeepSeek-V3.2-Exp or Qwen3.5-Flash better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.5 versus 34.2 in the Noometry coding category.
Which has the bigger context window?
Qwen3.5-Flash does, with 1M tokens against 164K.
How many benchmarks do DeepSeek-V3.2-Exp and Qwen3.5-Flash share?
28 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 49 scored results on Noometry and Qwen3.5-Flash has 32.