Model comparison
DeepSeek-V3.1-Terminus vs Qwen2-72B
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 29.5 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 Qwen2-72B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.3 to 41.0.
Side by side
| DeepSeek-V3.1-Terminus | Qwen2-72B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 42.6 | 29.5 |
| Released | 2025-09-22 | 2024-06-07 |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 66K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 26 |
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: 41.5 (#114), Qwen2-72B: 28.7 (#303)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2-72B |
|---|---|---|
| LMArena Coding | 1426 | 1196 |
| SciCode | 40.6% | — |
| WeirdML | — | 11.3% |
| BigCodeBench Instruct | — | 38.5% |
| BigCodeBench Complete | — | 54% |
| ALE-Bench | 745.17 | — |
Agentic & Tool Use Not comparable
DeepSeek-V3.1-Terminus: —, Qwen2-72B: 16.9 (#138)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2-72B |
|---|---|---|
| TheAgentCompany | — | 1.1% |
| METR Time Horizons | — | 29.9% |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 25.7 (#126), Qwen2-72B: 22.2 (#184)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2-72B |
|---|---|---|
| LMArena Hard Prompts | 1427 | 1191 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
| Epoch Capabilities Index | — | 125.27 |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 35.7 (#138), Qwen2-72B: 27.9 (#232)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2-72B |
|---|---|---|
| LMArena Math | 1402 | 1235 |
| MATH Level 5 | — | 39.1% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Qwen2-72B: 21.2 (#270)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2-72B |
|---|---|---|
| GPQA Diamond | — | 40.8% |
| LMArena Expert | — | 1171 |
| MMLU | — | 82.4% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.3 (#87), Qwen2-72B: 36.0 (#239)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2-72B |
|---|---|---|
| LMArena Non-English | 1407 | 1176 |
| LMArena Russian | 1434 | 1169 |
| LMArena Chinese | — | 1240 |
| LMArena French | — | 1169 |
| LMArena German | — | 1151 |
| LMArena Japanese | — | 1111 |
| LMArena Korean | — | 1083 |
| LMArena Spanish | — | 1168 |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.4 (#96), Qwen2-72B: 62.0 (#236)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2-72B |
|---|---|---|
| LMArena Instruction Following | 1406 | 1181 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.5 (#88), Qwen2-72B: 36.1 (#230)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2-72B |
|---|---|---|
| LMArena Longer Query | 1426 | 1193 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.3 (#87), Qwen2-72B: 41.0 (#236)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen2-72B |
|---|---|---|
| LMArena Text | 1420 | 1203 |
| LMArena Creative Writing | 1404 | 1181 |
| LMArena Multi-Turn | 1411 | 1195 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Qwen2-72B?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 42.6 to 29.5 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Qwen2-72B better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 41.5 versus 28.7 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Qwen2-72B share?
10 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Qwen2-72B has 26.