Model comparison
Qwen3 235B-A22B vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 43.5 on the Noometry Index. Qwen3 235B-A22B costs 2.4× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 26 shared benchmarks.
Alibaba (Qwen)Summary
- They share 26 benchmarks with published results for both. Qwen3 235B-A22B scores higher in 1 category and Qwen3.6 Max Preview in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Qwen3.6 Max Preview leads 41.7 to 15.7.
- The biggest single-benchmark swing is SimpleBench: 31% for Qwen3 235B-A22B and 63% for Qwen3.6 Max Preview.
- Qwen3 235B-A22B is cheaper at $0.70 / $2.80 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Qwen3.6 Max Preview 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 | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | Alibaba (Qwen) | Alibaba (Qwen) |
| Noometry Index | 43.5 | 51.5 |
| Released | 2025-04 | 2026-04-20 |
| Weights | Open | Proprietary |
| Context window | 131K | 262K |
| Max output | 16K | 66K |
| Input $ / M tokens | $0.70 | $1.30 |
| Output $ / M tokens | $2.80 | $7.80 |
| Results tracked | 49 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
Qwen3 235B-A22B: 44.3 (#75), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | Qwen3 235B-A22B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Coding | 1445 | 1471 |
| SWE-bench Verified | — | 76.7% |
| Aider Polyglot | 59.6% | — |
| LMArena WebDev | — | 1482 |
| SciCode | 42.4% | — |
| WeirdML | 41% | — |
Agentic & Tool Use Not comparable
Qwen3 235B-A22B: 33.9 (#51), Qwen3.6 Max Preview: —
| Benchmark | Qwen3 235B-A22B | Qwen3.6 Max Preview |
|---|---|---|
| Vending-Bench 2 | -11.34 | 4,254 |
| Berkeley Function Calling Leaderboard | 52.1% | — |
Reasoning Qwen3.6 Max Preview leads
Qwen3 235B-A22B: 15.7 (#311), Qwen3.6 Max Preview: 41.7 (#53)
| Benchmark | Qwen3 235B-A22B | Qwen3.6 Max Preview |
|---|---|---|
| SimpleBench | 31% | 63% |
| Chess Puzzles | 12% | 20% |
| LMArena Hard Prompts | 1433 | 1457 |
| Mystery Game Puzzles | 9% | 19% |
| DTBench | 80.3% | 87.2% |
| LMCA | 29.3% | 42.5% |
| Epoch Capabilities Index | 143.85 | 149.24 |
| ARC-AGI-2 | 1.3% | — |
| Kagi LLM Benchmark | 69.4% | — |
| NYT Connections (extended) | — | 74.1% |
| ARC-AGI-1 | 11% | — |
| CritPt | 0% | — |
| ForecastBench | 59.7 | — |
Math Qwen3.6 Max Preview leads
Qwen3 235B-A22B: 50.4 (#57), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | Qwen3 235B-A22B | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 86.7% | 91.1% |
| LMArena Math | 1432 | 1465 |
| FrontierMath (Feb 2025 set) | 8.5% | 23.1% |
| FrontierMath Tier 4 (v1) | 0% | 4.2% |
| Omni-MATH | 71.8% | — |
| MATH Level 5 | 68.9% | — |
Knowledge Qwen3.6 Max Preview leads
Qwen3 235B-A22B: 49.6 (#73), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | Qwen3 235B-A22B | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 80.1% | 87.4% |
| SimpleQA Verified | 40.4% | 52% |
| LMArena Expert | 1463 | 1478 |
| MMLU-Pro | 84.4% | — |
| Confabulations | 15.6% | — |
| Vectara Hallucination Rate | 9.3% | — |
| GPQA (HELM) | 72.7% | — |
Multilingual Qwen3.6 Max Preview leads
Qwen3 235B-A22B: 52.3 (#89), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | Qwen3 235B-A22B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1409 | 1437 |
| LMArena Chinese | 1481 | 1487 |
| LMArena French | 1445 | 1449 |
| LMArena Russian | 1411 | 1445 |
| LMArena Spanish | 1430 | 1454 |
| LMArena German | 1433 | — |
| LMArena Japanese | 1399 | — |
| LMArena Korean | 1391 | — |
Instruction Following Qwen3.6 Max Preview leads
Qwen3 235B-A22B: 72.6 (#136), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | Qwen3 235B-A22B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1408 | 1438 |
| IFEval | 83.5% | — |
Long Context Qwen3 235B-A22B leads
Qwen3 235B-A22B: 46.1 (#26), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | Qwen3 235B-A22B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1426 | 1457 |
| Fiction.LiveBench | 75% | — |
Writing & Preference Qwen3.6 Max Preview leads
Qwen3 235B-A22B: 59.6 (#108), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | Qwen3 235B-A22B | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1419 | 1447 |
| LMArena Creative Writing | 1384 | 1435 |
| LMArena Multi-Turn | 1432 | 1456 |
| Short-Story Creative Writing | 83% | — |
| EQ-Bench Creative Writing | 1366 | — |
| WildBench | 86.6% | — |
Frequently asked questions
Is Qwen3 235B-A22B better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 43.5 on the Noometry Index. Qwen3 235B-A22B costs 2.4× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Which is cheaper, Qwen3 235B-A22B or Qwen3.6 Max Preview?
Qwen3 235B-A22B is cheaper. It lists at $0.70 per million input tokens and $2.80 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is Qwen3 235B-A22B or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 44.3 in the Noometry coding category.
Which has the bigger context window?
Qwen3.6 Max Preview does, with 262K tokens against 131K.
How many benchmarks do Qwen3 235B-A22B and Qwen3.6 Max Preview share?
26 benchmarks have published results for both models. Qwen3 235B-A22B has 49 scored results on Noometry and Qwen3.6 Max Preview has 29.