Model comparison
Qwen Plus vs Qwen3.8 Max
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 37.1 on the Noometry Index. Qwen Plus costs 5.0× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Last verified . 17 shared benchmarks.
Alibaba (Qwen)Summary
- They share 17 benchmarks with published results for both. Qwen Plus 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 23.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 17.8% for Qwen Plus and 100% for Qwen3.8 Max.
- Qwen Plus is cheaper at $0.40 / $1.20 per million input/output tokens, against $2 / $6 for Qwen3.8 Max.
Side by side
| Qwen Plus | Qwen3.8 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 37.1 | 56.8 |
| Released | 2024-01-25 | 2026-08-02 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 33K | 131K |
| Input $ / M tokens | $0.40 | $2 |
| Output $ / M tokens | $1.20 | $6 |
| Results tracked | 20 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.8 Max leads
Qwen Plus: 38.9 (#167), Qwen3.8 Max: 53.5 (#29)
| Benchmark | Qwen Plus | Qwen3.8 Max |
|---|---|---|
| LMArena Coding | 1328 | 1502 |
| DeepSWE | — | 57.5% |
| LMArena WebDev | — | 1674 |
| FrontierSWE | — | 17.8% |
| SciCode | — | 53.2% |
Agentic & Tool Use Not comparable
Qwen Plus: —, Qwen3.8 Max: 45.4 (#14)
| Benchmark | Qwen Plus | Qwen3.8 Max |
|---|---|---|
| APEX-Agents | — | 63.3% |
| τ²-bench Banking | — | 55.1% |
| GDP.pdf | — | 23.2% |
Reasoning Qwen3.8 Max leads
Qwen Plus: 28.4 (#107), Qwen3.8 Max: 54.4 (#26)
| Benchmark | Qwen Plus | Qwen3.8 Max |
|---|---|---|
| LMArena Hard Prompts | 1317 | 1496 |
| DTBench | 81.1% | 92% |
| LMCA | 24% | 46.2% |
| Kagi LLM Benchmark | 63.3% | — |
| NYT Connections (extended) | — | 88.3% |
| CritPt | — | 20% |
| Chess Puzzles | — | 40% |
| Mystery Game Puzzles | — | 38% |
| Epoch Capabilities Index | — | 156.41 |
Math Qwen3.8 Max leads
Qwen Plus: 23.3 (#271), Qwen3.8 Max: 73.2 (#20)
| Benchmark | Qwen Plus | Qwen3.8 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 17.8% | 100% |
| LMArena Math | 1326 | 1499 |
| FrontierMath (Tiers 1-3) | — | 74.7% |
| FrontierMath Tier 4 | — | 46.3% |
| ProofBench | — | 58% |
| MATH Level 5 | 65.3% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge Qwen3.8 Max leads
Qwen Plus: 27.4 (#251), Qwen3.8 Max: 61.7 (#27)
| Benchmark | Qwen Plus | Qwen3.8 Max |
|---|---|---|
| GPQA Diamond | 48.1% | 92.7% |
| LMArena Expert | 1328 | 1507 |
| SimpleQA Verified | — | 47.3% |
Multimodal Not comparable
Qwen Plus: —, Qwen3.8 Max: 37.2 (#75)
| Benchmark | Qwen Plus | Qwen3.8 Max |
|---|---|---|
| LMArena Vision | — | 1314 |
| Furniture Assembly | — | 20% |
Multilingual Qwen3.8 Max leads
Qwen Plus: 45.1 (#175), Qwen3.8 Max: 56.7 (#18)
| Benchmark | Qwen Plus | Qwen3.8 Max |
|---|---|---|
| LMArena Non-English | 1310 | 1472 |
| LMArena Chinese | 1347 | 1538 |
| LMArena Japanese | 1251 | 1467 |
| LMArena Russian | 1323 | 1481 |
| LMArena French | — | 1503 |
| LMArena German | — | 1483 |
| LMArena Korean | — | 1461 |
| LMArena Spanish | — | 1492 |
Instruction Following Qwen3.8 Max leads
Qwen Plus: 68.8 (#181), Qwen3.8 Max: 77.6 (#17)
| Benchmark | Qwen Plus | Qwen3.8 Max |
|---|---|---|
| LMArena Instruction Following | 1303 | 1479 |
Long Context Qwen3.8 Max leads
Qwen Plus: 40.3 (#158), Qwen3.8 Max: 45.6 (#31)
| Benchmark | Qwen Plus | Qwen3.8 Max |
|---|---|---|
| LMArena Longer Query | 1324 | 1489 |
Writing & Preference Qwen3.8 Max leads
Qwen Plus: 52.2 (#176), Qwen3.8 Max: 67.1 (#30)
| Benchmark | Qwen Plus | Qwen3.8 Max |
|---|---|---|
| LMArena Text | 1326 | 1483 |
| LMArena Creative Writing | 1293 | 1479 |
| LMArena Multi-Turn | 1336 | 1489 |
Frequently asked questions
Is Qwen Plus better than Qwen3.8 Max?
Qwen3.8 Max is the stronger model overall, scoring 56.8 to 37.1 on the Noometry Index. Qwen Plus costs 5.0× less per token, which makes it the better buy when Qwen3.8 Max's lead doesn't matter for your workload.
Which is cheaper, Qwen Plus or Qwen3.8 Max?
Qwen Plus is cheaper. It lists at $0.40 per million input tokens and $1.20 per million output tokens; Qwen3.8 Max lists at $2 and $6.
Is Qwen Plus or Qwen3.8 Max better for coding?
Qwen3.8 Max scores higher on coding benchmarks: 53.5 versus 38.9 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Qwen Plus and Qwen3.8 Max share?
17 benchmarks have published results for both models. Qwen Plus has 20 scored results on Noometry and Qwen3.8 Max has 39.