Model comparison
DeepSeek-V3.1-Terminus vs Qwen-14B
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 31.4 on the Noometry Index.
Last verified . 9 shared benchmarks.
DeepSeek
Alibaba (Qwen)Summary
- They share 9 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 7 categories and Qwen-14B in 0 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where DeepSeek-V3.1-Terminus leads 61.0 to 27.6.
Side by side
| DeepSeek-V3.1-Terminus | Qwen-14B | |
|---|---|---|
| Provider | DeepSeek | Alibaba (Qwen) |
| Noometry Index | 43.1 | 31.4 |
| Released | 2025-09-22 | 2023-09-24 |
| Weights | Open | Open |
| Context window | 164K | — |
| Max output | 147K | — |
| Input $ / M tokens | $0.27 | — |
| Output $ / M tokens | $1 | — |
| Results tracked | 16 | 18 |
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: 42.0 (#113), Qwen-14B: 31.2 (#288)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen-14B |
|---|---|---|
| LMArena Coding | 1426 | 1071 |
| SciCode | 40.6% | — |
| ALE-Bench | 745.17 | — |
Reasoning DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 26.4 (#133), Qwen-14B: 19.6 (#257)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen-14B |
|---|---|---|
| LMArena Hard Prompts | 1426 | 1027 |
| Kagi LLM Benchmark | 57.4% | — |
| CritPt | 1.7% | — |
| DTBench | 81.3% | — |
| LMCA | 28.6% | — |
| BIG-Bench Hard | — | 55% |
| Epoch Capabilities Index | — | 113.03 |
| LAMBADA | — | 71.1% |
| PIQA | — | 79.9% |
Math DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 38.5 (#137), Qwen-14B: 31.2 (#227)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen-14B |
|---|---|---|
| LMArena Math | 1402 | 1068 |
| GSM8K | — | 61.3% |
Knowledge Not comparable
DeepSeek-V3.1-Terminus: —, Qwen-14B: —
| Benchmark | DeepSeek-V3.1-Terminus | Qwen-14B |
|---|---|---|
| ARC (AI2) Challenge | — | 84.4% |
| BoolQ | — | 86.2% |
| MMLU | — | 66.3% |
Multilingual DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 52.1 (#92), Qwen-14B: 27.5 (#275)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen-14B |
|---|---|---|
| LMArena Non-English | 1407 | 1041 |
| LMArena Chinese | — | 1077 |
| LMArena Russian | 1436 | — |
Instruction Following DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 74.0 (#106), Qwen-14B: 52.4 (#289)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen-14B |
|---|---|---|
| LMArena Instruction Following | 1404 | 1031 |
Long Context DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 43.4 (#97), Qwen-14B: 31.3 (#280)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen-14B |
|---|---|---|
| LMArena Longer Query | 1421 | 1028 |
Writing & Preference DeepSeek-V3.1-Terminus leads
DeepSeek-V3.1-Terminus: 61.0 (#92), Qwen-14B: 27.6 (#299)
| Benchmark | DeepSeek-V3.1-Terminus | Qwen-14B |
|---|---|---|
| LMArena Text | 1419 | 1051 |
| LMArena Creative Writing | 1403 | 1028 |
| LMArena Multi-Turn | 1411 | 1022 |
Frequently asked questions
Is DeepSeek-V3.1-Terminus better than Qwen-14B?
DeepSeek-V3.1-Terminus is the stronger model overall, scoring 43.1 to 31.4 on the Noometry Index.
Is DeepSeek-V3.1-Terminus or Qwen-14B better for coding?
DeepSeek-V3.1-Terminus scores higher on coding benchmarks: 42.0 versus 31.2 in the Noometry coding category.
How many benchmarks do DeepSeek-V3.1-Terminus and Qwen-14B share?
9 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Qwen-14B has 18.