Model comparison
Qwen2.5 Plus 1127 vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 38.8 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 Max in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3.8 Max leads 73.2 to 36.1.
Side by side
| Qwen2.5 Plus 1127 | Qwen3.8 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 38.8 | 56.8 |
| Released | — | 2026-08-02 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 131K |
| Input $ / M tokens | — | $2 |
| Output $ / M tokens | — | $6 |
| Results tracked | 14 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Qwen2.5 Plus 1127: 38.5 (#175), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1314 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
Agentic & Tool Use Not comparable
Qwen2.5 Plus 1127: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Qwen2.5 Plus 1127: 25.9 (#141), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 Max |
|---|---|---|
| LMArena Hard Prompts | 1299 | 1496 |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| DTBench | — | 92% |
| LMCA | — | 46.2% |
| Epoch Capabilities Index | — | 156.41 |
Math Qwen3.8 Max leads
Qwen2.5 Plus 1127: 36.1 (#174), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 Max |
|---|---|---|
| LMArena Math | 1298 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| OTIS Mock AIME 2024-2025 | — | 100% |
| ProofBench | — | 58% |
Knowledge Qwen3.8 Max leads
Qwen2.5 Plus 1127: 35.5 (#183), Qwen3.8 Max: 61.7 (#27)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 Max |
|---|---|---|
| LMArena Expert | 1289 | 1507 |
| GPQA Diamond | — | 92.7% |
| SimpleQA Verified | — | 47.3% |
Multimodal Not comparable
Qwen2.5 Plus 1127: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Qwen3.8 Max leads
Qwen2.5 Plus 1127: 41.9 (#201), Qwen3.8 Max: 56.7 (#18)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1265 | 1472 |
| LMArena Chinese | 1314 | 1538 |
| LMArena German | 1231 | 1483 |
| LMArena Japanese | 1207 | 1467 |
| LMArena Russian | 1271 | 1481 |
| LMArena French | — | 1503 |
| LMArena Korean | — | 1461 |
| LMArena Spanish | — | 1492 |
Instruction Following Qwen3.8 Max leads
Qwen2.5 Plus 1127: 67.2 (#199), Qwen3.8 Max: 77.6 (#17)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1275 | 1479 |
Long Context Qwen3.8 Max leads
Qwen2.5 Plus 1127: 39.2 (#184), Qwen3.8 Max: 45.6 (#31)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1292 | 1489 |
Writing & Preference Qwen3.8 Max leads
Qwen2.5 Plus 1127: 49.4 (#192), Qwen3.8 Max: 67.1 (#30)
| Benchmark | Qwen2.5 Plus 1127 | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1299 | 1483 |
| LMArena Creative Writing | 1262 | 1479 |
| LMArena Multi-Turn | 1299 | 1489 |
Frequently asked questions
Is Qwen2.5 Plus 1127 better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 38.8 on the Noometry Index.
Is Qwen2.5 Plus 1127 or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 38.5 in the Noometry coding category.
How many benchmarks do Qwen2.5 Plus 1127 and Qwen3.8 Max share?
14 benchmarks have published results for both models. Qwen2.5 Plus 1127 has 14 scored results on Noometry and Qwen3.8 Max has 39.