Model comparison
DeepSeek-V3.1-Terminus vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 6.6× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
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 0 categories and Qwen3.8 Max in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 38.5.
- The biggest single-benchmark swing is CritPt: 1.7% for DeepSeek-V3.1-Terminus and 20% for Qwen3.8 Max.
- DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
- Qwen3.8 Max 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 | Qwen3.8 Max | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 43.1 | 56.8 |
| Released | 2025-09-22 | 2026-08-02 |
| Weights | Open | Proprietary |
| Context window | 164K | 1M |
| Max output | 147K | 131K |
| Input $ / M tokens | $0.27 | $2 |
| Output $ / M tokens | $1 | $6 |
| Results tracked | 16 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
DeepSeek-V3.1-Terminus: 42.0 (#113), Qwen3.8 Max: 53.5 (#29)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| SciCode | 40.6% | 53.2% |
| LMArena Coding | 1426 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| ALE-Bench | 745.17 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Qwen3.8 Max: 54.4 (#26)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| CritPt | 1.7% | 20% |
| LMArena Hard Prompts | 1426 | 1496 |
| DTBench | 81.3% | 92% |
| LMCA | 28.6% | 46.2% |
| Kagi LLM Benchmark | 57.4% | — |
| NYT Connections (extended) | — | 88.3% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| Epoch Capabilities Index | — | 156.41 |
Math Qwen3.8 Max leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Qwen3.8 Max: 73.2 (#20)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 1402 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Qwen3.8 Max: 61.7 (#27)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
| LMArena Expert | — | 1507 |
Multimodal Not comparable
DeepSeek-V3.1-Terminus: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Qwen3.8 Max leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Qwen3.8 Max: 56.7 (#18)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1407 | 1472 |
| LMArena Russian | 1436 | 1481 |
| LMArena Chinese | — | 1538 |
| LMArena French | — | 1503 |
| LMArena German | — | 1483 |
| LMArena Japanese | — | 1467 |
| LMArena Korean | — | 1461 |
| LMArena Spanish | — | 1492 |
Instruction Following Qwen3.8 Max leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Qwen3.8 Max: 77.6 (#17)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1404 | 1479 |
Long Context Qwen3.8 Max leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Qwen3.8 Max: 45.6 (#31)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1421 | 1489 |
Writing & Preference Qwen3.8 Max leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Qwen3.8 Max: 67.1 (#30)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1419 | 1483 |
| LMArena Creative Writing | 1403 | 1479 |
| LMArena Multi-Turn | 1411 | 1489 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 6.6× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, DeepSeek-V3.1-Terminus or Qwen3.8 Max?
DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is DeepSeek-V3.1-Terminus or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 42.0 in the Noometry coding category.
Which has the bigger context window?
Qwen3.8 Max does, with 1M tokens against 164K.
How many benchmarks do DeepSeek-V3.1-Terminus and Qwen3.8 Max share?
14 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Qwen3.8 Max has 39.