Model comparison
DeepSeek-V2.5 (Sep 2024) vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 37.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and Qwen3.7 Plus in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.7 Plus leads 54.9 to 34.8.
- DeepSeek-V2.5 (Sep 2024) has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Plus | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.6 | 45.3 |
| Released | 2024-09-06 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.40 |
| Output $ / M tokens | — | $1.60 |
| Results tracked | 22 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.7 Plus leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Qwen3.7 Plus: 36.6 (#206)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Plus |
|---|---|---|
| LMArena Coding | 1309 | 1473 |
| FrontierCode | — | 10.2% |
| Aider Polyglot | 17.8% | — |
| SciCode | — | 45.5% |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, Qwen3.7 Plus: 21.4 (#138)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |
Reasoning Qwen3.7 Plus leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Qwen3.7 Plus: 39.3 (#59)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Plus |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1460 |
| NYT Connections (extended) | — | 74.8% |
| CritPt | — | 9.1% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
| DTBench | — | 84% |
| LMCA | — | 37.6% |
| Epoch Capabilities Index | — | 147.37 |
Math Qwen3.7 Plus leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Qwen3.7 Plus: 50.5 (#56)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1288 | 1466 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
Knowledge Qwen3.7 Plus leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Qwen3.7 Plus: 54.9 (#51)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Plus |
|---|---|---|
| LMArena Expert | 1266 | 1467 |
| GPQA Diamond | — | 87.9% |
Multimodal Not comparable
DeepSeek-V2.5 (Sep 2024): —, Qwen3.7 Plus: 41.8 (#33)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1279 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Qwen3.7 Plus: 54.8 (#38)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1273 | 1445 |
| LMArena Chinese | 1318 | 1510 |
| LMArena French | 1289 | 1473 |
| LMArena German | 1258 | 1471 |
| LMArena Japanese | 1228 | 1413 |
| LMArena Korean | 1209 | 1415 |
| LMArena Russian | 1289 | 1457 |
| LMArena Spanish | 1248 | 1457 |
Instruction Following Qwen3.7 Plus leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Qwen3.7 Plus: 75.8 (#52)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1280 | 1440 |
Long Context Qwen3.7 Plus leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Qwen3.7 Plus: 44.5 (#65)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1301 | 1455 |
Writing & Preference Qwen3.7 Plus leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Qwen3.7 Plus: 64.3 (#56)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1294 | 1455 |
| LMArena Creative Writing | 1285 | 1439 |
| LMArena Multi-Turn | 1297 | 1460 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.3 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Qwen3.7 Plus better for coding?
Qwen3.7 Plus scores higher on coding benchmarks: 36.6 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Qwen3.7 Plus share?
17 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Qwen3.7 Plus has 32.