Model comparison
DeepSeek-V3.1-Terminus vs Qwen2.5-Max
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 40.1 on the Noometry Index.
Last verified . 10 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Qwen2.5-Max in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 55.6.
- DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.
Side by side
| DeepSeek-V3.1-Terminus | Qwen2.5-Max | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.6 | 40.1 |
| Released | 2025-09-22 | 2025-01-25 |
| Weights | Open | Proprietary |
| Context window | 164K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 27 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
DeepSeek-V3.1-Terminus: 41.5 (#114), Qwen2.5-Max: 41.2 (#118)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5-Max |
|---|---|---|
| LMArena Coding | 1426 | 1359 |
| SciCode | 40.6% | — |
| LiveBench Coding | — | 64.4% |
| ALE-Bench | 745.17 | — |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Qwen2.5-Max: 24.6 (#144)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5-Max |
|---|---|---|
| LMArena Hard Prompts | 1427 | 1360 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| LiveBench Reasoning | — | 51.4% |
| DTBench | 81.3% | — |
| LiveBench Data Analysis | — | 67.9% |
| LMCA | 28.6% | — |
| Epoch Capabilities Index | — | 132.54 |
| LiveBench | — | 62.3% |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 35.7 (#138), Qwen2.5-Max: 34.3 (#162)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5-Max |
|---|---|---|
| LMArena Math | 1402 | 1369 |
| LiveBench Math | — | 58.4% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Qwen2.5-Max: 34.8 (#181)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5-Max |
|---|---|---|
| Confabulations | — | 21.8% |
| LMArena Expert | — | 1337 |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), Qwen2.5-Max: 48.3 (#140)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5-Max |
|---|---|---|
| LMArena Non-English | 1407 | 1352 |
| LMArena Russian | 1434 | 1353 |
| LMArena Chinese | — | 1382 |
| LMArena French | — | 1396 |
| LMArena German | — | 1350 |
| LMArena Japanese | — | 1299 |
| LMArena Korean | — | 1304 |
| LMArena Spanish | — | 1377 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), Qwen2.5-Max: 71.5 (#147)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5-Max |
|---|---|---|
| LMArena Instruction Following | 1406 | 1335 |
| LiveBench Instruction Following | — | 75.3% |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), Qwen2.5-Max: 41.3 (#137)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5-Max |
|---|---|---|
| LMArena Longer Query | 1426 | 1358 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Qwen2.5-Max: 55.6 (#141)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2.5-Max |
|---|---|---|
| LMArena Text | 1420 | 1367 |
| LMArena Creative Writing | 1404 | 1339 |
| LMArena Multi-Turn | 1411 | 1364 |
| Short-Story Creative Writing | — | 72.9% |
| LiveBench Language | — | 56.3% |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Qwen2.5-Max?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 40.1 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Qwen2.5-Max better for coding?
They score almost the same on coding (41.5 vs 41.2); test both on your own repository before choosing.
How many benchmarks do DeepSeek-V3.1-Terminus and Qwen2.5-Max share?
10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Qwen2.5-Max has 27.