Compare / Qwen3-235B-A22B-Thinking-2507 vs Qwen3-Max
Qwen3-235B-A22B-Thinking-2507 vs Qwen3-Max
Which is cheaper, which is more capable, and which does better at each kind of work, from 18 results on 5 sources that measured both models.
Of the 18 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 9 October 2026 (catalogue release 2026-10-09-dd620e778ac5).
Qwen3-235B-A22B-Thinking-2507 or Qwen3-Max? The short answer
Pick Qwen3-Max if quality matters most: it scores higher (Intelligence Index 15.6 against 12.7). Pick Qwen3-235B-A22B-Thinking-2507 if cost matters more: it costs 38% less per token.
- Qwen3-235B-A22B-Thinking-2507 is cheaper: $0.97 against $1.56 per million tokens, 38% less.
- Qwen3-Max scores higher on the Artificial Analysis Intelligence Index: 15.6 against 12.7.
- Qwen3-Max is newer: released 24 Sep 2025, against 25 Jul 2025 for Qwen3-235B-A22B-Thinking-2507.
- On third-party benchmarks, on the results both models have: Qwen3-235B-A22B-Thinking-2507 does better for reasoning and knowledge; Qwen3-Max for agents and tool use, writing and sticking to the facts.
Head to head
Every fact side by side
| Qwen3-235B-A22B-Thinking-2507 | Qwen3-Max | |
|---|---|---|
| Price per million tokens | $0.30 in · $3.00 out | $0.78 in · $3.90 out |
| Blended (3 in : 1 out) | $0.97 | $1.56 |
| Cheapest host, blended | $0.75 (Alibaba) | – |
| Intelligence Index | 12.7 | 15.6 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 131,072 tokens | 262,144 tokens |
| Released | 25 Jul 2025 | 24 Sep 2025 (newer) |
| Weights | Open | Closed |
| Developer based in | China | China |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among the models on sale today, for each kind of work, from our own benchmarks and licensed sources. Further right is better; the better rank is in green.
Every shared result
Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. Under each measure, every model that benchmark has measured is a grey tick, best to the right, so you can see where the two sit in the field. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.
| Measure | Qwen3-235B-A22B-Thinking-2507 | Qwen3-Max |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 139 · 108 of 387 measured | 1,400 | 1,423 |
| Business, management and finance · TextArena rating, higher is better 133 · 110 of 380 measured | 1,404 | 1,419 |
| Creative writing · TextArena rating, higher is better 133 · 105 of 385 measured | 1,371 | 1,393 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 147 · 123 of 243 measured | 12.7 | 15.6 |
| GPQA Diamond% of questions, higher is better 114 · 132 of 231 measured | 79.0% | 76.4% |
| Humanity's Last Exam% of questions, higher is better 122 · 140 of 242 measured | 15.9% | 11.9% |
| SimpleQA Verified (Epoch AI) reported by SimpleQA Verified (Epoch AI) · 1 result | ||
| Correct answers% of questions, higher is better 44 · 27 of 76 measured | 40.4% | 48.7% |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 139 · 115 of 230 measured | 32.4 | 38.6 |
| Requested-length error · UGI% off the requested word count, lower is better 166 · 134 of 230 measured | 30.0% | 23.0% |
| Style adherence · UGIscore from 0 to 1, higher is better 194 · 155 of 230 measured | 0.31 | 0.33 |
| Vending-Bench 2 reported by Vending-Bench 2 · 1 result | ||
| Money after a yearUS dollars, higher is better 55 · 52 of 58 measured | $-11.34 | $71.57 |
Show all 18 results (7 more)
| Measure | Qwen3-235B-A22B-Thinking-2507 | Qwen3-Max |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Expert prompts · TextArena rating, higher is better 85 · 137 of 338 measured | 1,466 | 1,417 |
| Instruction following · TextArena rating, higher is better 142 · 106 of 387 measured | 1,385 | 1,413 |
| Writing, literature and language · TextArena rating, higher is better 139 · 101 of 386 measured | 1,377 | 1,405 |
| Artificial Analysis reported by Artificial Analysis · 4 results | ||
| IFBench% of instructions, higher is better 101 · 118 of 195 measured | 51.2% | 44.2% |
| Long-context reasoning (AA-LCR)% of questions, higher is better 99 · 154 of 233 measured | 72.0% | 50.0% |
| Terminal-Bench Hard% of tasks, higher is better 116 · 91 of 190 measured | 13.6% | 20.5% |
| τ²-bench telecom% of tasks, higher is better 101 · 79 of 193 measured | 53.2% | 74.3% |
Quick answers
Is Qwen3-235B-A22B-Thinking-2507 better than Qwen3-Max?
Pick Qwen3-Max if quality matters most: it scores higher (Intelligence Index 15.6 against 12.7). Pick Qwen3-235B-A22B-Thinking-2507 if cost matters more: it costs 38% less per token.
Which is cheaper, Qwen3-235B-A22B-Thinking-2507 or Qwen3-Max?
Qwen3-235B-A22B-Thinking-2507 is cheaper: $0.97 against $1.56 per million tokens, 38% less.
Which is better for agents and tool use, Qwen3-235B-A22B-Thinking-2507 or Qwen3-Max?
Qwen3-235B-A22B-Thinking-2507 ranks 138 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 154 for Qwen3-Max.
Which is better for reasoning and knowledge, Qwen3-235B-A22B-Thinking-2507 or Qwen3-Max?
Qwen3-235B-A22B-Thinking-2507 ranks 117 of 198 models on sale for hard questions across science, maths and general knowledge, against 121 for Qwen3-Max.
Which is better for writing, Qwen3-235B-A22B-Thinking-2507 or Qwen3-Max?
Qwen3-Max ranks 99 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 122 for Qwen3-235B-A22B-Thinking-2507.
Which is better for sticking to the facts, Qwen3-235B-A22B-Thinking-2507 or Qwen3-Max?
Qwen3-Max ranks 50 of 152 models on sale for summarising without inventing things, and factual answers, against 92 for Qwen3-235B-A22B-Thinking-2507.
Which has the bigger context window, Qwen3-235B-A22B-Thinking-2507 or Qwen3-Max?
Qwen3-Max: 262,144 tokens, against 131,072 for Qwen3-235B-A22B-Thinking-2507.
Run Qwen3-235B-A22B-Thinking-2507 and Qwen3-Max on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.