Model comparison
Qwen Max vs Qwen3 235B-A22B
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 34.7 on the Noometry Index.
Last verified . 23 shared benchmarks.
Alibaba (Qwen)Summary
- They share 23 benchmarks with published results for both. Qwen Max scores higher in 1 category and Qwen3 235B-A22B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 22.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 16.1% for Qwen Max and 86.7% for Qwen3 235B-A22B.
- Qwen3 235B-A22B is cheaper at $0.70 / $2.80 per million input/output tokens, against $1.60 / $6.40 for Qwen Max.
- Qwen3 235B-A22B accepts more context: 131K tokens versus 33K.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| Qwen Max | Qwen3 235B-A22B | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 34.7 | 43.5 |
| Released | 2024-04-03 | 2025-04 |
| Weights | Proprietary | Open |
| Context window | 33K | 131K |
| Max output | 8K | 16K |
| Input $ / M tokens | $1.60 | $0.70 |
| Output $ / M tokens | $6.40 | $2.80 |
| Results tracked | 23 | 49 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Qwen Max: 30.7 (#292), Qwen3 235B-A22B: 44.3 (#75)
| Benchmark | Qwen Max | Qwen3 235B-A22B |
|---|---|---|
| Aider Polyglot | 21.8% | 59.6% |
| LMArena Coding | 1288 | 1445 |
| SciCode | — | 42.4% |
| WeirdML | — | 41% |
Agentic & Tool Use Not comparable
Qwen Max: —, Qwen3 235B-A22B: 33.9 (#51)
| Benchmark | Qwen Max | Qwen3 235B-A22B |
|---|---|---|
| Berkeley Function Calling Leaderboard | — | 52.1% |
| Vending-Bench 2 | — | -11.34 |
Reasoning Qwen Max leads
Qwen Max: 25.1 (#151), Qwen3 235B-A22B: 15.7 (#311)
| Benchmark | Qwen Max | Qwen3 235B-A22B |
|---|---|---|
| LMArena Hard Prompts | 1269 | 1433 |
| ARC-AGI-2 | — | 1.3% |
| SimpleBench | — | 31% |
| Kagi LLM Benchmark | — | 69.4% |
| ARC-AGI-1 | — | 11% |
| CritPt | — | 0% |
| Chess Puzzles | — | 12% |
| Mystery Game Puzzles | — | 9% |
| DTBench | — | 80.3% |
| LMCA | — | 29.3% |
| Epoch Capabilities Index | — | 143.85 |
| ForecastBench | — | 59.7 |
Math Qwen3 235B-A22B leads
Qwen Max: 22.3 (#276), Qwen3 235B-A22B: 50.4 (#57)
| Benchmark | Qwen Max | Qwen3 235B-A22B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 16.1% | 86.7% |
| LMArena Math | 1275 | 1432 |
| MATH Level 5 | 67.2% | 68.9% |
| FrontierMath (Feb 2025 set) | 1% | 8.5% |
| Omni-MATH | — | 71.8% |
| FrontierMath Tier 4 (v1) | — | 0% |
Knowledge Qwen3 235B-A22B leads
Qwen Max: 30.3 (#228), Qwen3 235B-A22B: 49.6 (#73)
| Benchmark | Qwen Max | Qwen3 235B-A22B |
|---|---|---|
| GPQA Diamond | 56.1% | 80.1% |
| LMArena Expert | 1248 | 1463 |
| SimpleQA Verified | — | 40.4% |
| MMLU-Pro | — | 84.4% |
| Confabulations | — | 15.6% |
| Vectara Hallucination Rate | — | 9.3% |
| GPQA (HELM) | — | 72.7% |
Multilingual Qwen3 235B-A22B leads
Qwen Max: 41.8 (#202), Qwen3 235B-A22B: 52.3 (#89)
| Benchmark | Qwen Max | Qwen3 235B-A22B |
|---|---|---|
| LMArena Non-English | 1263 | 1409 |
| LMArena Chinese | 1254 | 1481 |
| LMArena French | 1330 | 1445 |
| LMArena German | 1254 | 1433 |
| LMArena Japanese | 1205 | 1399 |
| LMArena Korean | 1142 | 1391 |
| LMArena Russian | 1274 | 1411 |
| LMArena Spanish | 1290 | 1430 |
Instruction Following Qwen3 235B-A22B leads
Qwen Max: 66.5 (#208), Qwen3 235B-A22B: 72.6 (#136)
| Benchmark | Qwen Max | Qwen3 235B-A22B |
|---|---|---|
| LMArena Instruction Following | 1262 | 1408 |
| IFEval | — | 83.5% |
Long Context Qwen3 235B-A22B leads
Qwen Max: 39.4 (#180), Qwen3 235B-A22B: 46.1 (#26)
| Benchmark | Qwen Max | Qwen3 235B-A22B |
|---|---|---|
| Fiction.LiveBench | 66.7% | 75% |
| LMArena Longer Query | 1288 | 1426 |
Writing & Preference Qwen3 235B-A22B leads
Qwen Max: 47.8 (#205), Qwen3 235B-A22B: 59.6 (#108)
| Benchmark | Qwen Max | Qwen3 235B-A22B |
|---|---|---|
| LMArena Text | 1282 | 1419 |
| LMArena Creative Writing | 1248 | 1384 |
| LMArena Multi-Turn | 1277 | 1432 |
| Short-Story Creative Writing | — | 83% |
| EQ-Bench Creative Writing | — | 1366 |
| WildBench | — | 86.6% |
Frequently asked questions
Is Qwen Max better than Qwen3 235B-A22B?
Qwen3 235B-A22B is the stronger model overall, scoring 43.5 to 34.7 on the Noometry Index.
Which is cheaper, Qwen Max or Qwen3 235B-A22B?
Qwen3 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Qwen Max lists at $1.60 and $6.40.
Is Qwen Max or Qwen3 235B-A22B better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 30.7 in the Noometry coding category.
Which has the bigger context window?
Qwen3 235B-A22B does, with 131K tokens against 33K.
How many benchmarks do Qwen Max and Qwen3 235B-A22B share?
23 benchmarks have published results for both models. Qwen Max has 23 scored results on Noometry and Qwen3 235B-A22B has 49.