Model comparison
Qwen Plus vs Qwen3.8 27B
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 37.1 on the Noometry Index. Qwen Plus costs 1.9× less per token, which makes it the better buy when Qwen3.8 27B's lead doesn't matter for your workload.
Last verified . 15 shared benchmarks.
Alibaba (Qwen)Summary
- They share 15 benchmarks with published results for both. Qwen Plus scores higher in 0 categories and Qwen3.8 27B in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.8 27B leads 41.6 to 27.4.
- The biggest single-benchmark swing is LMCA: 24% for Qwen Plus and 41.4% for Qwen3.8 27B.
- Qwen Plus is cheaper at $0.40 / $1.20 per million input/output tokens, against $0.99 / $1.49 for Qwen3.8 27B.
- Qwen Plus accepts more context: 1M tokens versus 262K.
- Qwen3.8 27B has downloadable open weights; the other is API-only.
Side by side
| Qwen Plus | Qwen3.8 27B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 37.1 | 46.0 |
| Released | 2024-01-25 | 2026-08-14 |
| Weights | Proprietary | Open |
| Context window | 1M | 262K |
| Max output | 33K | 33K |
| Input $ / M tokens | $0.40 | $0.99 |
| Output $ / M tokens | $1.20 | $1.49 |
| Results tracked | 20 | 31 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 27B leads
Qwen Plus: 38.9 (#167), Qwen3.8 27B: 50.5 (#44)
| Benchmark | Qwen Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Coding | 1328 | 1482 |
| LMArena WebDev | — | 1593 |
| SciCode | — | 46.6% |
Agentic & Tool Use Not comparable
Qwen Plus: —, Qwen3.8 27B: 32.9 (#57)
| Benchmark | Qwen Plus | Qwen3.8 27B |
|---|---|---|
| APEX-Agents | — | 47.5% |
Reasoning Qwen3.8 27B leads
Qwen Plus: 28.4 (#107), Qwen3.8 27B: 41.0 (#54)
| Benchmark | Qwen Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Hard Prompts | 1317 | 1460 |
| DTBench | 81.1% | 88% |
| LMCA | 24% | 41.4% |
| ARC-AGI-2 | — | 42.4% |
| Kagi LLM Benchmark | 63.3% | — |
| NYT Connections (extended) | — | 54.5% |
| ARC-AGI-1 | — | 87.5% |
| CritPt | — | 5.4% |
| Surface Evolver Bench | — | 45% |
| Epoch Capabilities Index | — | 149.38 |
Math Qwen3.8 27B leads
Qwen Plus: 23.3 (#271), Qwen3.8 27B: 37.1 (#161)
| Benchmark | Qwen Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Math | 1326 | 1456 |
| OTIS Mock AIME 2024-2025 | 17.8% | — |
| ProofBench | — | 16% |
| MATH Level 5 | 65.3% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Qwen3.8 27B leads
Qwen Plus: 27.4 (#251), Qwen3.8 27B: 41.6 (#109)
| Benchmark | Qwen Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Expert | 1328 | 1482 |
| GPQA Diamond | 48.1% | — |
Multimodal Not comparable
Qwen Plus: —, Qwen3.8 27B: 41.3 (#37)
| Benchmark | Qwen Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Vision | — | 1271 |
Multilingual Qwen3.8 27B leads
Qwen Plus: 45.1 (#175), Qwen3.8 27B: 53.7 (#60)
| Benchmark | Qwen Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Non-English | 1310 | 1430 |
| LMArena Chinese | 1347 | 1504 |
| LMArena Japanese | 1251 | 1384 |
| LMArena Russian | 1323 | 1415 |
| LMArena French | — | 1465 |
| LMArena German | — | 1438 |
| LMArena Korean | — | 1393 |
| LMArena Spanish | — | 1448 |
Instruction Following Qwen3.8 27B leads
Qwen Plus: 68.8 (#181), Qwen3.8 27B: 75.8 (#53)
| Benchmark | Qwen Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Instruction Following | 1303 | 1439 |
Long Context Qwen3.8 27B leads
Qwen Plus: 40.3 (#158), Qwen3.8 27B: 44.3 (#70)
| Benchmark | Qwen Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Longer Query | 1324 | 1450 |
Writing & Preference Qwen3.8 27B leads
Qwen Plus: 52.2 (#176), Qwen3.8 27B: 65.8 (#43)
| Benchmark | Qwen Plus | Qwen3.8 27B |
|---|---|---|
| LMArena Text | 1326 | 1441 |
| LMArena Creative Writing | 1293 | 1384 |
| LMArena Multi-Turn | 1336 | 1441 |
| EQ-Bench Creative Writing | — | 1671 |
Frequently asked questions
Is Qwen Plus better than Qwen3.8 27B?
Qwen3.8 27B is the stronger model overall, scoring 46.0 to 37.1 on the Noometry Index. Qwen Plus costs 1.9× less per token, which makes it the better buy when Qwen3.8 27B's lead doesn't matter for your workload.
Which is cheaper, Qwen Plus or Qwen3.8 27B?
Qwen Plus is cheaper. It lists at $0.40 per million input tokens and $1.20 per million output tokens; Qwen3.8 27B lists at $0.99 and $1.49.
Is Qwen Plus or Qwen3.8 27B better for coding?
Qwen3.8 27B scores higher on coding benchmarks: 50.5 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
Qwen Plus does, with 1M tokens against 262K.
How many benchmarks do Qwen Plus and Qwen3.8 27B share?
15 benchmarks have published results for both models. Qwen Plus has 20 scored results on Noometry and Qwen3.8 27B has 31.