Model comparison
DeepSeek-V3.1-Terminus vs Qwen3.7 Plus
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 42.6 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 1 category and Qwen3.7 Plus in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.7 Plus leads 49.3 to 35.7.
- The biggest single-benchmark swing is LMCA: 28.6% for DeepSeek-V3.1-Terminus and 37.6% for Qwen3.7 Plus.
- DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 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-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | Qwen3.7 Plus | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.6 | 45.0 |
| Released | 2025-09-22 | 2026-06-02 |
| Weights | Open | Proprietary |
| Context window | 164K | 1M |
| Max output | 66K | 131K |
| Input $ / M tokens | $0.30 | $0.40 |
| Output $ / M tokens | $1 | $1.60 |
| Results tracked | 16 | 32 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 41.5 (#114), Qwen3.7 Plus: 36.1 (#200)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.7 Plus |
|---|---|---|
| SciCode | 40.6% | 45.5% |
| LMArena Coding | 1426 | 1473 |
| FrontierCode | — | 10.2% |
| ALE-Bench | 745.17 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Qwen3.7 Plus: 21.2 (#130)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.7 Plus |
|---|---|---|
| OSWorld 2.0 | — | 2.8% |
Reasoning Qwen3.7 Plus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Qwen3.7 Plus: 38.4 (#54)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.7 Plus |
|---|---|---|
| CritPt | 1.7% | 9.1% |
| LMArena Hard Prompts | 1427 | 1460 |
| DTBench | 81.3% | 84% |
| LMCA | 28.6% | 37.6% |
| Kagi LLM Benchmark | 57.4% | — |
| NYT Connections (extended) | — | 74.8% |
| Chess Puzzles | — | 24% |
| Mystery Game Puzzles | — | 17% |
| Epoch Capabilities Index | — | 147.39 |
Math Qwen3.7 Plus leads
DeepSeek-V3.1-Terminus: 35.7 (#138), Qwen3.7 Plus: 49.3 (#47)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.7 Plus |
|---|---|---|
| LMArena Math | 1402 | 1467 |
| FrontierMath (Tiers 1-3) | — | 34.4% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Qwen3.7 Plus: 54.9 (#46)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.7 Plus |
|---|---|---|
| GPQA Diamond | — | 87.9% |
| LMArena Expert | — | 1467 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, Qwen3.7 Plus: 41.2 (#30)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.7 Plus |
|---|---|---|
| LMArena Vision | — | 1281 |
| LMArena Document | — | 1444 |
Multilingual Qwen3.7 Plus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), Qwen3.7 Plus: 55.0 (#36)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.7 Plus |
|---|---|---|
| LMArena Non-English | 1407 | 1445 |
| LMArena Russian | 1434 | 1457 |
| LMArena Chinese | — | 1510 |
| LMArena French | — | 1471 |
| LMArena German | — | 1471 |
| LMArena Japanese | — | 1411 |
| LMArena Korean | — | 1416 |
| LMArena Spanish | — | 1453 |
Instruction Following Qwen3.7 Plus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), Qwen3.7 Plus: 75.9 (#49)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.7 Plus |
|---|---|---|
| LMArena Instruction Following | 1406 | 1439 |
Long Context Too close to call
DeepSeek-V3.1-Terminus: 43.5 (#88), Qwen3.7 Plus: 44.5 (#61)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.7 Plus |
|---|---|---|
| LMArena Longer Query | 1426 | 1454 |
Writing & Preference Qwen3.7 Plus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Qwen3.7 Plus: 64.5 (#54)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.7 Plus |
|---|---|---|
| LMArena Text | 1420 | 1454 |
| LMArena Creative Writing | 1404 | 1439 |
| LMArena Multi-Turn | 1411 | 1459 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Qwen3.7 Plus?
Qwen3.7 Plus is the stronger model overall, scoring 45.0 to 42.6 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1-Terminus or Qwen3.7 Plus?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; Qwen3.7 Plus lists at $0.40 and $1.60.
Is DeepSeek-V3.1-Terminus or Qwen3.7 Plus better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 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-V3.1-Terminus and Qwen3.7 Plus share?
14 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Qwen3.7 Plus has 32.