Model comparison
DeepSeek-V3.1-Terminus vs Qwen Plus
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 37.1 on the Noometry Index.
Last verified . 13 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 13 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 6 categories and Qwen Plus in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where DeepSeek-V3.1-Terminus leads 38.5 to 23.3.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 57.4% for DeepSeek-V3.1-Terminus and 63.3% for Qwen Plus.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $0.40 / $1.20 for Qwen Plus.
- Qwen 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 | Qwen Plus | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 43.1 | 37.1 |
| Released | 2025-09-22 | 2024-01-25 |
| Weights | Open | Proprietary |
| Context window | 164K | 1M |
| Max output | 147K | 33K |
| Input $ / M tokens | $0.27 | $0.40 |
| Output $ / M tokens | $1 | $1.20 |
| Results tracked | 16 | 20 |
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: 42.0 (#113), Qwen Plus: 38.9 (#167)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen Plus |
|---|---|---|
| LMArena Coding | 1426 | 1328 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Reasoning Qwen Plus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Qwen Plus: 28.4 (#107)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen Plus |
|---|---|---|
| Kagi LLM Benchmark | 57.4% | 63.3% |
| LMArena Hard Prompts | 1426 | 1317 |
| DTBench | 81.3% | 81.1% |
| LMCA | 28.6% | 24% |
| CritPt | 1.7% | — |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Qwen Plus: 23.3 (#271)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen Plus |
|---|---|---|
| LMArena Math | 1402 | 1326 |
| OTIS Mock AIME 2024-2025 | — | 17.8% |
| MATH Level 5 | — | 65.3% |
| FrontierMath (Feb 2025 set) | — | 1.7% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Qwen Plus: 27.4 (#251)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen Plus |
|---|---|---|
| GPQA Diamond | — | 48.1% |
| LMArena Expert | — | 1328 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Qwen Plus: 45.1 (#175)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen Plus |
|---|---|---|
| LMArena Non-English | 1407 | 1310 |
| LMArena Russian | 1436 | 1323 |
| LMArena Chinese | — | 1347 |
| LMArena Japanese | — | 1251 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Qwen Plus: 68.8 (#181)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen Plus |
|---|---|---|
| LMArena Instruction Following | 1404 | 1303 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Qwen Plus: 40.3 (#158)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen Plus |
|---|---|---|
| LMArena Longer Query | 1421 | 1324 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Qwen Plus: 52.2 (#176)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen Plus |
|---|---|---|
| LMArena Text | 1419 | 1326 |
| LMArena Creative Writing | 1403 | 1293 |
| LMArena Multi-Turn | 1411 | 1336 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Qwen Plus?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 37.1 on the Noometry Index.
Which is cheaper, DeepSeek-V3.1-Terminus or Qwen Plus?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; Qwen Plus lists at $0.40 and $1.20.
Is DeepSeek-V3.1-Terminus or Qwen Plus better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
Qwen Plus does, with 1M tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and Qwen Plus share?
13 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Qwen Plus has 20.