Model comparison
DeepSeek-V2.5 (Sep 2024) vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 37.6 on the Noometry Index.
Last verified . 14 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. DeepSeek-V2.5 (Sep 2024) scores higher in 0 categories and Qwen3.6 Max Preview in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Max Preview leads 57.6 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) | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 37.6 | 51.5 |
| Released | 2024-09-06 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | — | 262K |
| Max output | — | 66K |
| Input $ / M tokens | — | $1.30 |
| Output $ / M tokens | — | $7.80 |
| Results tracked | 22 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
DeepSeek-V2.5 (Sep 2024): 31.7 (#281), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1309 | 1471 |
| SWE-bench Verified | — | 76.7% |
| Aider Polyglot | 17.8% | — |
| LMArena WebDev | — | 1482 |
| BigCodeBench Instruct | 48.6% | — |
| BigCodeBench Complete | 53.2% | — |
| HumanEval+ | 83.5% | — |
| MBPP+ | 74.1% | — |
Agentic & Tool Use Not comparable
DeepSeek-V2.5 (Sep 2024): —, Qwen3.6 Max Preview: —
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| Vending-Bench 2 | — | 4,254 |
Reasoning Qwen3.6 Max Preview leads
DeepSeek-V2.5 (Sep 2024): 25.6 (#145), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Hard Prompts | 1289 | 1457 |
| SimpleBench | — | 63% |
| NYT Connections (extended) | — | 74.1% |
| Chess Puzzles | — | 20% |
| Mystery Game Puzzles | — | 19% |
| DTBench | — | 87.2% |
| LMCA | — | 42.5% |
| Epoch Capabilities Index | — | 149.24 |
Math Qwen3.6 Max Preview leads
DeepSeek-V2.5 (Sep 2024): 35.9 (#177), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Math | 1288 | 1465 |
| OTIS Mock AIME 2024-2025 | — | 91.1% |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
DeepSeek-V2.5 (Sep 2024): 34.8 (#193), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Expert | 1266 | 1478 |
| GPQA Diamond | — | 87.4% |
| SimpleQA Verified | — | 52% |
Multilingual Qwen3.6 Max Preview leads
DeepSeek-V2.5 (Sep 2024): 42.5 (#193), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1273 | 1437 |
| LMArena Chinese | 1318 | 1487 |
| LMArena French | 1289 | 1449 |
| LMArena Russian | 1289 | 1445 |
| LMArena Spanish | 1248 | 1454 |
| LMArena German | 1258 | — |
| LMArena Japanese | 1228 | — |
| LMArena Korean | 1209 | — |
Instruction Following Qwen3.6 Max Preview leads
DeepSeek-V2.5 (Sep 2024): 67.5 (#194), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1280 | 1438 |
Long Context Qwen3.6 Max Preview leads
DeepSeek-V2.5 (Sep 2024): 39.5 (#174), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1301 | 1457 |
Writing & Preference Qwen3.6 Max Preview leads
DeepSeek-V2.5 (Sep 2024): 49.8 (#187), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | DeepSeek-V2.5 (Sep 2024) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1294 | 1447 |
| LMArena Creative Writing | 1285 | 1435 |
| LMArena Multi-Turn | 1297 | 1456 |
Frequently asked questions
Is DeepSeek-V2.5 (Sep 2024) better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 37.6 on the Noometry Index.
Is DeepSeek-V2.5 (Sep 2024) or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 31.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V2.5 (Sep 2024) and Qwen3.6 Max Preview share?
14 benchmarks have published results for both models. DeepSeek-V2.5 (Sep 2024) has 22 scored results on Noometry and Qwen3.6 Max Preview has 29.