Model comparison
DeepSeek-V3.2-Exp vs Qwen3.7 Plus
DeepSeek-V3.2-Exp and Qwen3.7 Plus score almost the same on the Noometry Index (44.9 vs 45.0), so choose on price, context window or the category you care about most.
Last verified . 26 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. DeepSeek-V3.2-Exp scores higher in 3 categories and Qwen3.7 Plus in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where DeepSeek-V3.2-Exp leads 37.9 to 21.2.
- The biggest single-benchmark swing is NYT Connections (extended): 36.7% for DeepSeek-V3.2-Exp and 74.8% for Qwen3.7 Plus.
- DeepSeek-V3.2-Exp is cheaper at $0.26 / $0.38 per million input/output tokens, against $0.40 / $1.60 for Qwen3.7 Plus.
- Qwen3.7 Plus 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 | Qwen3.7 Plus | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 44.9 | 45.0 |
| Released | 2025-09-29 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 164K | 1M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.26 | $0.40 |
| Output $ / M tokens | $0.38 | $1.60 |
| Results tracked | 48 | 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: 46.4 (#61), Qwen3.7 Plus: 36.1 (#200)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.7 Plus |
|---|---|---|
| SciCode | 38.9% | 45.5% |
| LMArena Coding | 1454 | 1473 |
| FrontierCode | — | 10.2% |
| SWE-bench Verified (bash only) | 70% | — |
| Aider Polyglot | 74.2% | — |
| LMArena WebDev | 1362 | — |
| SWE-bench Multilingual | 59% | — |
| WeirdML | 39.5% | — |
Agentic & Tool Use DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 37.9 (#31), Qwen3.7 Plus: 21.2 (#130)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.7 Plus |
|---|---|---|
| Terminal-Bench | 39.6% | — |
| Berkeley Function Calling Leaderboard | 56.7% | — |
| OSWorld 2.0 | — | 2.8% |
| TheAgentCompany | 42.9% | — |
| Vending-Bench 2 | 1,034 | — |
Reasoning Qwen3.7 Plus leads
DeepSeek-V3.2-Exp: 22.0 (#185), Qwen3.7 Plus: 38.4 (#54)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.7 Plus |
|---|---|---|
| NYT Connections (extended) | 36.7% | 74.8% |
| CritPt | 2.9% | 9.1% |
| Chess Puzzles | 14% | 24% |
| LMArena Hard Prompts | 1433 | 1460 |
| DTBench | 87.7% | 84% |
| LMCA | 29.1% | 37.6% |
| Epoch Capabilities Index | 146.28 | 147.39 |
| ARC-AGI-2 | 4% | — |
| Kagi LLM Benchmark | 52.2% | — |
| ARC-AGI-1 | 57% | — |
| Thematic Generalization | 65% | — |
| Mystery Game Puzzles | — | 17% |
Math Qwen3.7 Plus leads
DeepSeek-V3.2-Exp: 40.8 (#75), Qwen3.7 Plus: 49.3 (#47)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.7 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 87.8% | 93.3% |
| LMArena Math | 1435 | 1467 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| MathArena Final-Answer Competitions | 57.7% | — |
| ProofBench | 8% | — |
| FrontierMath (Feb 2025 set) | 22.1% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Qwen3.7 Plus leads
DeepSeek-V3.2-Exp: 51.6 (#61), Qwen3.7 Plus: 54.9 (#46)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | 83.4% | 87.9% |
| LMArena Expert | 1436 | 1467 |
| Vectara Hallucination Rate | 5.3% | — |
Multimodal Not comparable
DeepSeek-V3.2-Exp: —, Qwen3.7 Plus: 41.2 (#30)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1281 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
DeepSeek-V3.2-Exp: 52.4 (#85), Qwen3.7 Plus: 55.0 (#36)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1409 | 1445 |
| LMArena Chinese | 1461 | 1510 |
| LMArena French | 1435 | 1471 |
| LMArena German | 1440 | 1471 |
| LMArena Japanese | 1377 | 1411 |
| LMArena Korean | 1372 | 1416 |
| LMArena Russian | 1423 | 1457 |
| LMArena Spanish | 1441 | 1453 |
Instruction Following Qwen3.7 Plus leads
DeepSeek-V3.2-Exp: 74.7 (#89), Qwen3.7 Plus: 75.9 (#49)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1413 | 1439 |
Long Context DeepSeek-V3.2-Exp leads
DeepSeek-V3.2-Exp: 47.6 (#15), Qwen3.7 Plus: 44.5 (#61)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1428 | 1454 |
| Fiction.LiveBench | 83.3% | — |
| CL-bench | 13.2% | — |
| CL-bench Life | 9.5% | — |
Writing & Preference Qwen3.7 Plus leads
DeepSeek-V3.2-Exp: 62.5 (#73), Qwen3.7 Plus: 64.5 (#54)
| Benchmark | DeepSeek-V3.2-Exp | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1425 | 1454 |
| LMArena Creative Writing | 1403 | 1439 |
| LMArena Multi-Turn | 1427 | 1459 |
| EQ-Bench Creative Writing | 1515 | — |
Frequently asked questions
Is DeepSeek-V3.2-Exp better than Qwen3.7 Plus?
DeepSeek-V3.2-Exp and Qwen3.7 Plus score almost the same on the Noometry Index (44.9 vs 45.0), so choose on price, context window or the category you care about most.
Which is cheaper, DeepSeek-V3.2-Exp or Qwen3.7 Plus?
DeepSeek-V3.2-Exp is cheaper. It lists at $0.26 per million input tokens and $0.38 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is DeepSeek-V3.2-Exp or Qwen3.7 Plus better for coding?
DeepSeek-V3.2-Exp scores higher on coding benchmarks: 46.4 versus 36.1 in the Noometry coding category.
Which has the bigger context window?
Qwen3.7 Plus does, with 1M tokens against 164K.
How many benchmarks do DeepSeek-V3.2-Exp and Qwen3.7 Plus share?
26 benchmarks have published results for both models. DeepSeek-V3.2-Exp has 48 scored results on Noometry and Qwen3.7 Plus has 32.