Model comparison
Qwen2.5 Plus 1127 vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 45.3 to 38.1 on the Noometry Index.
Last verified . 14 shared benchmarks.
Alibaba (Qwen)Summary
- They share 14 benchmarks with published results for both. Qwen2.5 Plus 1127 scores higher in 0 categories and Qwen3.8 27B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Qwen3.8 27B leads 65.9 to 49.5.
- Qwen3.8 27B has downloadable open weights; the other is API-only.
Side by side
| Qwen2.5 Plus 1127 | Qwen3.8 27B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 38.1 | 45.3 |
| Released | — | 2026-08-14 |
| Weights | Proprietary | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.99 |
| Output $ / M tokens | — | $1.49 |
| Results tracked | 14 | 28 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
Qwen2.5 Plus 1127: 37.9 (#171), Qwen3.8 27B: 50.3 (#42)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 27B |
|---|---|---|
| LMArena Coding | 1314 | 1487 |
| LMArena WebDev | — | 1592 |
| SciCode | — | 46.6% |
Reasoning Qwen3.8 27B leads
Qwen2.5 Plus 1127: 24.8 (#139), Qwen3.8 27B: 31.5 (#71)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 27B |
|---|---|---|
| LMArena Hard Prompts | 1299 | 1459 |
| NYT Connections (extended) | — | 54.5% |
| CritPt | — | 5.4% |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| Epoch Capabilities Index | — | 149.38 |
Math Qwen3.8 27B leads
Qwen2.5 Plus 1127: 33.5 (#175), Qwen3.8 27B: 35.7 (#139)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1298 | 1453 |
| ProofBench | — | 16% |
Knowledge Qwen3.8 27B leads
Qwen2.5 Plus 1127: 34.9 (#179), Qwen3.8 27B: 40.9 (#105)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1289 | 1482 |
Multimodal Not comparable
Qwen2.5 Plus 1127: —, Qwen3.8 27B: 40.5 (#36)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1270 |
Multilingual Qwen3.8 27B leads
Qwen2.5 Plus 1127: 42.1 (#196), Qwen3.8 27B: 54.0 (#54)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1265 | 1431 |
| LMArena Chinese | 1314 | 1504 |
| LMArena German | 1231 | 1435 |
| LMArena Japanese | 1207 | 1392 |
| LMArena Russian | 1271 | 1421 |
| LMArena French | — | 1468 |
| LMArena Korean | — | 1389 |
| LMArena Spanish | — | 1444 |
Instruction Following Qwen3.8 27B leads
Qwen2.5 Plus 1127: 67.4 (#194), Qwen3.8 27B: 75.8 (#54)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1275 | 1436 |
Long Context Qwen3.8 27B leads
Qwen2.5 Plus 1127: 39.2 (#180), Qwen3.8 27B: 44.3 (#66)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1292 | 1448 |
Writing & Preference Qwen3.8 27B leads
Qwen2.5 Plus 1127: 49.5 (#186), Qwen3.8 27B: 65.9 (#41)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1299 | 1441 |
| LMArena Creative Writing | 1262 | 1382 |
| LMArena Multi-Turn | 1299 | 1443 |
| EQ-Bench Creative Writing | — | 1671 |
Frequently asked questions
Is Qwen2.5 Plus 1127 better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 45.3 to 38.1 on the Noometry Index.
Is Qwen2.5 Plus 1127 or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.3 versus 37.9 in the Noometry coding category.
How many benchmarks do Qwen2.5 Plus 1127 and Qwen3.8 27B share?
14 benchmarks have published results for both models. Qwen2.5 Plus 1127 has 14 scored results on Noometry and Qwen3.8 27B has 28.