Model comparison
DeepSeek-V3.1-Terminus vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 6.5× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 12 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 12 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 0 categories and Qwen3.6 Max Preview in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.6 Max Preview leads 54.1 to 38.5.
- The biggest single-benchmark swing is LMCA: 28.6% for DeepSeek-V3.1-Terminus and 42.5% for Qwen3.6 Max Preview.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Qwen3.6 Max Preview accepts more context: 262K tokens versus 164K.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 43.1 | 51.5 |
| Released | 2025-09-22 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 164K | 262K |
| Max output | 147K | 66K |
| Input $ / M tokens | $0.27 | $1.30 |
| Output $ / M tokens | $1 | $7.80 |
| Results tracked | 16 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
DeepSeek-V3.1-Terminus: 42.0 (#113), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1426 | 1471 |
| SWE-bench Verified | — | 76.7% |
| LMArena WebDev | — | 1482 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Qwen3.6 Max Preview: —
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.6 Max Preview |
|---|---|---|
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1457 |
| DTBench | 81.3% | 87.2% |
| LMCA | 28.6% | 42.5% |
| SimpleBench | — | 63% |
| Kagi LLM Benchmark | 57.4% | — |
| NYT Connections (extended) | — | 74.1% |
| CritPt | 1.7% | — |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 19% |
| Epoch Capabilities Index | — | 149.24 |
Math Qwen3.6 Max Preview leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Math | 1402 | 1465 |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | — | 87.4% |
| SimpleQA Verified | — | 52% |
| LMArena Expert | — | 1478 |
Multilingual Qwen3.6 Max Preview leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1407 | 1437 |
| LMArena Russian | 1436 | 1445 |
| LMArena Chinese | — | 1487 |
| LMArena French | — | 1449 |
| LMArena Spanish | — | 1454 |
Instruction Following Qwen3.6 Max Preview leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1404 | 1438 |
Long Context Qwen3.6 Max Preview leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1421 | 1457 |
Writing & Preference Qwen3.6 Max Preview leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1419 | 1447 |
| LMArena Creative Writing | 1403 | 1435 |
| LMArena Multi-Turn | 1411 | 1456 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 6.5× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1-Terminus or Qwen3.6 Max Preview?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is DeepSeek-V3.1-Terminus or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 42.0 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Max Preview does, with 262K tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and Qwen3.6 Max Preview share?
12 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Qwen3.6 Max Preview has 29.