Model comparison
Qwen1.5-32B vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 30.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Qwen1.5-32B 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 65.8 to 34.2.
Side by side
| Qwen1.5-32B | Qwen3.8 27B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 30.5 | 46.0 |
| Released | 2024-02-04 | 2026-08-14 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 33K |
| Input $ / M tokens | — | $0.99 |
| Output $ / M tokens | — | $1.49 |
| Results tracked | 21 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
Qwen1.5-32B: 31.7 (#282), Qwen3.8 27B: 50.5 (#44)
| Benchmark | Qwen1.5-32B | Qwen3.8 27B |
|---|---|---|
| LMArena Coding | 1155 | 1482 |
| LMArena WebDev | — | 1593 |
| SciCode | — | 46.6% |
| BigCodeBench Instruct | 32.3% | — |
| BigCodeBench Complete | 42% | — |
Agentic & Tool Use Not comparable
Qwen1.5-32B: —, Qwen3.8 27B: 32.9 (#57)
| Benchmark | Qwen1.5-32B | Qwen3.8 27B |
|---|---|---|
| APEX-Agents | — | 47.5% |
Reasoning Qwen3.8 27B leads
Qwen1.5-32B: 21.8 (#212), Qwen3.8 27B: 41.0 (#54)
| Benchmark | Qwen1.5-32B | Qwen3.8 27B |
|---|---|---|
| LMArena Hard Prompts | 1130 | 1460 |
| ARC-AGI-2 | — | 42.4% |
| NYT Connections (extended) | — | 54.5% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 5.4% |
| DTBench | — | 88% |
| LMCA | — | 41.4% |
| Surface Evolver Bench | — | 45% |
| Epoch Capabilities Index | — | 149.38 |
Math Qwen3.8 27B leads
Qwen1.5-32B: 33.0 (#207), Qwen3.8 27B: 37.1 (#161)
| Benchmark | Qwen1.5-32B | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1155 | 1456 |
| ProofBench | — | 16% |
Knowledge Qwen3.8 27B leads
Qwen1.5-32B: 13.5 (#296), Qwen3.8 27B: 41.6 (#109)
| Benchmark | Qwen1.5-32B | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1126 | 1482 |
| GPQA Diamond | 30.7% | — |
| MMLU | 74.4% | — |
Multimodal Not comparable
Qwen1.5-32B: —, Qwen3.8 27B: 41.3 (#37)
| Benchmark | Qwen1.5-32B | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1271 |
Multilingual Qwen3.8 27B leads
Qwen1.5-32B: 31.4 (#259), Qwen3.8 27B: 53.7 (#60)
| Benchmark | Qwen1.5-32B | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1106 | 1430 |
| LMArena Chinese | 1177 | 1504 |
| LMArena French | 1101 | 1465 |
| LMArena German | 1058 | 1438 |
| LMArena Japanese | 1027 | 1384 |
| LMArena Korean | 1008 | 1393 |
| LMArena Russian | 1073 | 1415 |
| LMArena Spanish | 1089 | 1448 |
Instruction Following Qwen3.8 27B leads
Qwen1.5-32B: 57.7 (#265), Qwen3.8 27B: 75.8 (#53)
| Benchmark | Qwen1.5-32B | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1116 | 1439 |
Long Context Qwen3.8 27B leads
Qwen1.5-32B: 34.7 (#246), Qwen3.8 27B: 44.3 (#70)
| Benchmark | Qwen1.5-32B | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1146 | 1450 |
Writing & Preference Qwen3.8 27B leads
Qwen1.5-32B: 34.2 (#271), Qwen3.8 27B: 65.8 (#43)
| Benchmark | Qwen1.5-32B | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1137 | 1441 |
| LMArena Creative Writing | 1083 | 1384 |
| LMArena Multi-Turn | 1140 | 1441 |
| EQ-Bench Creative Writing | — | 1671 |
Frequently asked questions
Is Qwen1.5-32B better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 30.5 on the Noometry Index.
Is Qwen1.5-32B or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 31.7 in the Noometry coding category.
How many benchmarks do Qwen1.5-32B and Qwen3.8 27B share?
17 benchmarks have published results for both models. Qwen1.5-32B has 21 scored results on Noometry and Qwen3.8 27B has 31.