Model comparison
Qwen-14B vs Qwen2.5 Plus 1127
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.1 to 30.8 on the Noometry Index.
Last verified . 10 shared benchmarks.
Alibaba (Qwen)Summary
- They share 10 benchmarks with published results for both. Qwen-14B scores higher in 0 categories and Qwen2.5 Plus 1127 in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen2.5 Plus 1127 leads 49.5 to 27.8.
- Qwen-14B has downloadable open weights; the other is API-only.
Side by side
| Qwen-14B | Qwen2.5 Plus 1127 | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.8 | 38.1 |
| Released | 2023-09-24 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 18 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen2.5 Plus 1127 leads
Qwen-14B: 30.6 (#283), Qwen2.5 Plus 1127: 37.9 (#171)
| Benchmark | Qwen-14B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Coding | 1072 | 1314 |
Reasoning Qwen2.5 Plus 1127 leads
Qwen-14B: 18.7 (#255), Qwen2.5 Plus 1127: 24.8 (#139)
| Benchmark | Qwen-14B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Hard Prompts | 1027 | 1299 |
| BIG-Bench Hard | 55% | — |
| Epoch Capabilities Index | 112.8 | — |
| LAMBADA | 71.1% | — |
| PIQA | 79.9% | — |
Math Qwen2.5 Plus 1127 leads
Qwen-14B: 28.7 (#224), Qwen2.5 Plus 1127: 33.5 (#175)
| Benchmark | Qwen-14B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Math | 1068 | 1298 |
| GSM8K | 61.3% | — |
Knowledge Not comparable
Qwen-14B: —, Qwen2.5 Plus 1127: 34.9 (#179)
| Benchmark | Qwen-14B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Expert | — | 1289 |
| ARC (AI2) Challenge | 84.4% | — |
| BoolQ | 86.2% | — |
| MMLU | 66.3% | — |
Multilingual Qwen2.5 Plus 1127 leads
Qwen-14B: 27.7 (#270), Qwen2.5 Plus 1127: 42.1 (#196)
| Benchmark | Qwen-14B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Non-English | 1042 | 1265 |
| LMArena Chinese | 1077 | 1314 |
| LMArena German | — | 1231 |
| LMArena Japanese | — | 1207 |
| LMArena Russian | — | 1271 |
Instruction Following Qwen2.5 Plus 1127 leads
Qwen-14B: 52.6 (#284), Qwen2.5 Plus 1127: 67.4 (#194)
| Benchmark | Qwen-14B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Instruction Following | 1031 | 1275 |
Long Context Qwen2.5 Plus 1127 leads
Qwen-14B: 31.3 (#276), Qwen2.5 Plus 1127: 39.2 (#180)
| Benchmark | Qwen-14B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Longer Query | 1029 | 1292 |
Writing & Preference Qwen2.5 Plus 1127 leads
Qwen-14B: 27.8 (#294), Qwen2.5 Plus 1127: 49.5 (#186)
| Benchmark | Qwen-14B | Qwen2.5 Plus 1127 |
|---|---|---|
| LMArena Text | 1051 | 1299 |
| LMArena Creative Writing | 1028 | 1262 |
| LMArena Multi-Turn | 1022 | 1299 |
Frequently asked questions
Is Qwen-14B better than Qwen2.5 Plus 1127?
Qwen2.5 Plus 1127 is the stronger model overall, scoring 38.1 to 30.8 on the Noometry Index.
Is Qwen-14B or Qwen2.5 Plus 1127 better for coding?
Qwen2.5 Plus 1127 scores higher on coding benchmarks: 37.9 versus 30.6 in the Noometry coding category.
How many benchmarks do Qwen-14B and Qwen2.5 Plus 1127 share?
10 benchmarks have published results for both models. Qwen-14B has 18 scored results on Noometry and Qwen2.5 Plus 1127 has 14.