Model comparison
DeepSeek-V3.1 vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 42.8 on the Noometry Index. DeepSeek-V3.1 costs 1.6× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 20 benchmarks with published results for both. DeepSeek-V3.1 scores higher in 1 category and Qwen3.7 Plus in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Plus leads 50.5 to 38.9.
- The biggest single-benchmark swing is LMCA: 24.3% for DeepSeek-V3.1 and 37.6% for Qwen3.7 Plus.
- DeepSeek-V3.1 is cheaper at $0.25 / $0.95 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-V3.1 has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1 | Qwen3.7 Plus | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.8 | 45.3 |
| Released | 2025-08-21 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 164K | 1M |
| Max output | 8K | 131K |
| Input $ / M tokens | $0.25 | $0.40 |
| Output $ / M tokens | $0.95 | $1.60 |
| Results tracked | 27 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1 leads
DeepSeek-V3.1: 40.3 (#144), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | DeepSeek-V3.1 | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1417 | 1473 |
| FrontierCode | — | 10.2% |
| SciCode | — | 45.5% |
| WeirdML | 38.4% | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1: —, Qwen3.7 Plus: 21.4 (#138)
| Benchmark | DeepSeek-V3.1 | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |
Reasoning Qwen3.7 Plus leads
DeepSeek-V3.1: 27.9 (#110), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | DeepSeek-V3.1 | Qwen3.7 Plus |
|---|---|---|
| LMArena Hard Prompts | 1417 | 1460 |
| DTBench | 82.7% | 84% |
| LMCA | 24.3% | 37.6% |
| Epoch Capabilities Index | 139.92 | 147.37 |
| SimpleBench | 40% | — |
| Kagi LLM Benchmark | 53.2% | — |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
| ForecastBench | 58 | — |
Math Qwen3.7 Plus leads
DeepSeek-V3.1: 38.9 (#122), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | DeepSeek-V3.1 | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1420 | 1466 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
Knowledge Qwen3.7 Plus leads
DeepSeek-V3.1: 43.7 (#90), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | DeepSeek-V3.1 | Qwen3.7 Plus |
|---|---|---|
| LMArena Expert | 1405 | 1467 |
| GPQA Diamond | — | 87.9% |
| Vectara Hallucination Rate | 5.5% | — |
Multimodal Not comparable
DeepSeek-V3.1: —, Qwen3.7 Plus: 41.8 (#33)
| Benchmark | DeepSeek-V3.1 | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
DeepSeek-V3.1: 51.6 (#106), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | DeepSeek-V3.1 | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1400 | 1445 |
| LMArena Chinese | 1469 | 1510 |
| LMArena French | 1447 | 1473 |
| LMArena German | 1411 | 1471 |
| LMArena Japanese | 1378 | 1413 |
| LMArena Korean | 1337 | 1415 |
| LMArena Russian | 1405 | 1457 |
| LMArena Spanish | 1431 | 1457 |
Instruction Following Qwen3.7 Plus leads
DeepSeek-V3.1: 73.9 (#110), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | DeepSeek-V3.1 | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1400 | 1440 |
Long Context Qwen3.7 Plus leads
DeepSeek-V3.1: 36.3 (#232), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | DeepSeek-V3.1 | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1422 | 1455 |
| Fiction.LiveBench | 52.8% | — |
Writing & Preference Qwen3.7 Plus leads
DeepSeek-V3.1: 60.3 (#98), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | DeepSeek-V3.1 | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1420 | 1455 |
| LMArena Creative Writing | 1401 | 1439 |
| LMArena Multi-Turn | 1408 | 1460 |
| EQ-Bench Creative Writing | 1436 | — |
Frequently asked questions
Is DeepSeek-V3.1 better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 42.8 on the Noometry Index. DeepSeek-V3.1 costs 1.6× less per token, which makes it the better buy when Qwen3.7 Plus's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1 or Qwen3.7 Plus?
DeepSeek-V3.1 is cheaper. It lists at $0.25 per million input tokens and $0.95 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is DeepSeek-V3.1 or Qwen3.7 Plus better for coding?
DeepSeek-V3.1 scores higher on coding benchmarks: 40.3 versus 36.6 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-V3.1 and Qwen3.7 Plus share?
20 benchmarks have published results for both models. DeepSeek-V3.1 has 27 scored results on Noometry and Qwen3.7 Plus has 32.