Model comparison
Qwen3 235B-A22B vs Qwen3 Max
Qwen3 235B-A22B and Qwen3 Max score almost the same on the Noometry Index (43.5 vs 43.7), so choose on price, context window or the category you care about most.
Last verified . 29 shared benchmarks.
Alibaba (Qwen)Summary
- They share 29 benchmarks with published results for both. Qwen3 235B-A22B scores higher in 4 categories and Qwen3 Max in 4 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Qwen3 235B-A22B leads 50.4 to 38.7.
- The biggest single-benchmark swing is MATH Level 5: 68.9% for Qwen3 235B-A22B and 97.1% for Qwen3 Max.
- Qwen3 235B-A22B is cheaper at $0.70 / $2.80 per million input/output tokens, against $1.20 / $6 for Qwen3 Max.
- Qwen3 Max accepts more context: 262K tokens versus 131K.
- Qwen3 235B-A22B has downloadable open weights; the other is API-only.
Side by side
| Qwen3 235B-A22B | Qwen3 Max | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 43.5 | 43.7 |
| Released | 2025-04 | 2025-09-23 |
| Weights | Open | Proprietary |
| Context window | 131K | 262K |
| Max output | 16K | 66K |
| Input $ / M tokens | $0.70 | $1.20 |
| Output $ / M tokens | $2.80 | $6 |
| Results tracked | 49 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3 235B-A22B leads
Qwen3 235B-A22B: 44.3 (#75), Qwen3 Max: 43.0 (#93)
| Benchmark | Qwen3 235B-A22B | Qwen3 Max |
|---|---|---|
| LMArena Coding | 1445 | 1456 |
| Aider Polyglot | 59.6% | — |
| SciCode | 42.4% | — |
| WeirdML | 41% | — |
| ALE-Bench | — | 370.45 |
Agentic & Tool Use Not comparable
Qwen3 235B-A22B: 33.9 (#51), Qwen3 Max: —
| Benchmark | Qwen3 235B-A22B | Qwen3 Max |
|---|---|---|
| Vending-Bench 2 | -11.34 | 71.56 |
| Berkeley Function Calling Leaderboard | 52.1% | — |
Reasoning Qwen3 Max leads
Qwen3 235B-A22B: 15.7 (#311), Qwen3 Max: 22.6 (#190)
| Benchmark | Qwen3 235B-A22B | Qwen3 Max |
|---|---|---|
| Kagi LLM Benchmark | 69.4% | 72.5% |
| Chess Puzzles | 12% | 4% |
| LMArena Hard Prompts | 1433 | 1448 |
| Mystery Game Puzzles | 9% | 5% |
| DTBench | 80.3% | 82.1% |
| LMCA | 29.3% | 28.3% |
| Epoch Capabilities Index | 143.85 | 142.38 |
| ARC-AGI-2 | 1.3% | — |
| SimpleBench | 31% | — |
| NYT Connections (extended) | — | 30.1% |
| ARC-AGI-1 | 11% | — |
| CritPt | 0% | — |
| ForecastBench | 59.7 | — |
Math Qwen3 235B-A22B leads
Qwen3 235B-A22B: 50.4 (#57), Qwen3 Max: 38.7 (#131)
| Benchmark | Qwen3 235B-A22B | Qwen3 Max |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | 73.3% |
| LMArena Math | 1432 | 1446 |
| MATH Level 5 | 68.9% | 97.1% |
| FrontierMath (Tiers 1-3) | — | 18.9% |
| Omni-MATH | 71.8% | — |
| FrontierMath (Feb 2025 set) | 8.5% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Qwen3 235B-A22B leads
Qwen3 235B-A22B: 49.6 (#73), Qwen3 Max: 48.1 (#78)
| Benchmark | Qwen3 235B-A22B | Qwen3 Max |
|---|---|---|
| GPQA Diamond | 80.1% | 72.6% |
| SimpleQA Verified | 40.4% | 48.7% |
| LMArena Expert | 1463 | 1455 |
| MMLU-Pro | 84.4% | — |
| Confabulations | 15.6% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 72.7% | — |
Multilingual Qwen3 Max leads
Qwen3 235B-A22B: 52.3 (#89), Qwen3 Max: 53.7 (#62)
| Benchmark | Qwen3 235B-A22B | Qwen3 Max |
|---|---|---|
| LMArena Non-English | 1409 | 1429 |
| LMArena Chinese | 1481 | 1478 |
| LMArena French | 1445 | 1449 |
| LMArena German | 1433 | 1463 |
| LMArena Japanese | 1399 | 1397 |
| LMArena Korean | 1391 | 1399 |
| LMArena Russian | 1411 | 1428 |
| LMArena Spanish | 1430 | 1462 |
Instruction Following Qwen3 Max leads
Qwen3 235B-A22B: 72.6 (#136), Qwen3 Max: 74.8 (#87)
| Benchmark | Qwen3 235B-A22B | Qwen3 Max |
|---|---|---|
| LMArena Instruction Following | 1408 | 1419 |
| IFEval | 83.5% | — |
Long Context Qwen3 235B-A22B leads
Qwen3 235B-A22B: 46.1 (#26), Qwen3 Max: 41.6 (#134)
| Benchmark | Qwen3 235B-A22B | Qwen3 Max |
|---|---|---|
| Fiction.LiveBench | 75% | 66.7% |
| LMArena Longer Query | 1426 | 1438 |
| CL-bench | — | 14.5% |
Writing & Preference Qwen3 Max leads
Qwen3 235B-A22B: 59.6 (#108), Qwen3 Max: 62.4 (#76)
| Benchmark | Qwen3 235B-A22B | Qwen3 Max |
|---|---|---|
| LMArena Text | 1419 | 1439 |
| LMArena Creative Writing | 1384 | 1402 |
| LMArena Multi-Turn | 1432 | 1446 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1366 | — |
| WildBench | 86.6% | — |
Frequently asked questions
Is Qwen3 235B-A22B better than Qwen3 Max?
Qwen3 235B-A22B and Qwen3 Max score almost the same on the Noometry Index (43.5 vs 43.7), so choose on price, context window or the category you care about most.
Which is cheaper, Qwen3 235B-A22B or Qwen3 Max?
Qwen3 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Qwen3 Max lists at $1.20 and $6.
Is Qwen3 235B-A22B or Qwen3 Max better for coding?
Qwen3 235B-A22B scores higher on coding benchmarks: 44.3 versus 43.0 in the Noometry coding category.
Which has the bigger context window?
Qwen3 Max does, with 262K tokens against 131K.
How many benchmarks do Qwen3 235B-A22B and Qwen3 Max share?
29 benchmarks have published results for both models. Qwen3 235B-A22B has 49 scored results on Noometry and Qwen3 Max has 33.