Compare / Qwen3-235B-A22B-Thinking-2507 vs Gemini 3.1 Pro Preview
Qwen3-235B-A22B-Thinking-2507 vs Gemini 3.1 Pro Preview
Which is cheaper, which is more capable, and which does better at each kind of work, from 23 results on 5 sources that measured both models.
Of the 23 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 14 October 2026 (catalogue release 2026-10-14-7d7cf32c3f6d). See also Alibaba vs Google, every model from both labs.
Qwen3-235B-A22B-Thinking-2507 or Gemini 3.1 Pro Preview? The short answer
Pick Gemini 3.1 Pro Preview if quality matters most: it scores higher (Intelligence Index 29.7 against 12.7). Pick Qwen3-235B-A22B-Thinking-2507 if cost matters more: it costs 4.6 times less per token.
- Qwen3-235B-A22B-Thinking-2507 is cheaper: $0.97 against $4.50 per million tokens, 4.6 times less.
- Gemini 3.1 Pro Preview scores higher on the Artificial Analysis Intelligence Index: 29.7 against 12.7.
- Gemini 3.1 Pro Preview is newer: released 19 Feb 2026, against 25 Jul 2025 for Qwen3-235B-A22B-Thinking-2507.
- On third-party benchmarks, on the results both models have: Gemini 3.1 Pro Preview does better for agents and tool use, reasoning and knowledge, writing and sticking to the facts.
Head to head
Every fact side by side
| Qwen3-235B-A22B-Thinking-2507 | Gemini 3.1 Pro Preview | |
|---|---|---|
| Price per million tokens | $0.30 in · $3.00 out | $2.00 in · $12.00 out |
| Blended (3 in : 1 out) | $0.97 | $4.50 |
| Cheapest host, blended | $0.75 (Alibaba) | $4.50 (Google) |
| Cached input, per million | – | $0.20 cached input |
| Intelligence Index | 12.7 | 29.7 |
| Spring Prompt overall | – | 47 |
| Output speed, tokens a second | – | 135 |
| Context window | 131,072 tokens | 1,048,576 tokens |
| Released | 25 Jul 2025 | 19 Feb 2026 (newer) |
| Weights | Open | Closed |
| Developer based in | China | the US |
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.
From our research
- Gemini 4 Argon review: Opus-level product data at a quarter of the cost, until you ask it to sell 14 Oct 2026
- BulletBench: we made 23 AI models play speed chess, and the clock was the judge 3 Jul 2026
- Claude vs Gemini vs GPT in a 12-Month Marketing Simulation 25 Mar 2026
- The AI Marketing Benchmark That Punishes Plausible-Sounding Strategy 20 Mar 2026
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 | Gemini 3.1 Pro Preview |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 139 · 15 of 387 measured | 1,400 | 1,487 |
| Business, management and finance · TextArena rating, higher is better 133 · 23 of 380 measured | 1,404 | 1,477 |
| Creative writing · TextArena rating, higher is better 133 · 10 of 385 measured | 1,371 | 1,480 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 148 · 53 of 244 measured | 12.7 | 29.7 |
| GPQA Diamond% of questions, higher is better 114 · 5 of 231 measured | 79.0% | 94.1% |
| Humanity's Last Exam% of questions, higher is better 123 · 17 of 243 measured | 15.9% | 47.0% |
| SimpleQA Verified (Epoch AI) reported by SimpleQA Verified (Epoch AI) · 1 result | ||
| Correct answers% of questions, higher is better 44 · 3 of 76 measured | 40.4% | 73.5%high reasoning |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 139 · 5 of 230 measured | 32.4 | 72.2low reasoning |
| Requested-length error · UGI% off the requested word count, lower is better 166 · 99 of 230 measured | 30.0% | 19.0%low reasoning |
| Style adherence · UGIscore from 0 to 1, higher is better 194 · 122 of 230 measured | 0.31 | 0.34low reasoning |
| Vending-Bench 2 reported by Vending-Bench 2 · 1 result | ||
| Money after a yearUS dollars, higher is better 55 · 45 of 58 measured | $-11.34 | $911.21 |
Show all 23 results (12 more)
| Measure | Qwen3-235B-A22B-Thinking-2507 | Gemini 3.1 Pro Preview |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Expert prompts · TextArena rating, higher is better 85 · 26 of 338 measured | 1,466 | 1,509 |
| Instruction following · TextArena rating, higher is better 142 · 17 of 387 measured | 1,385 | 1,480 |
| Writing, literature and language · TextArena rating, higher is better 139 · 11 of 386 measured | 1,377 | 1,480 |
| Artificial Analysis reported by Artificial Analysis · 9 results | ||
| Terminal-Bench 2.1% of tasks, higher is better 101 · 35 of 130 measured | 12.0% | 73.8% |
| Terminal-Bench 4.0% of tasks, higher is better 67 · 46 of 113 measured | 0.0% | 4.0% |
| τ-bench banking% of tasks, higher is better 87 · 46 of 121 measured | 7.8% | 21.4% |
| Artificial Analysis Coding Indexindex score, higher is better 98 · 30 of 131 measured | 22.1 | 68.8 |
| IFBench% of instructions, higher is better 101 · 13 of 195 measured | 51.2% | 77.1% |
| Long-context reasoning (AA-LCR)% of questions, higher is better 100 · 24 of 234 measured | 72.0% | 82.0% |
| SciCode% of problems, higher is better 75 · 13 of 114 measured | 41.4% | 58.7% |
| Terminal-Bench Hard% of tasks, higher is better 116 · 8 of 190 measured | 13.6% | 53.8% |
| τ²-bench telecom% of tasks, higher is better 101 · 16 of 193 measured | 53.2% | 95.6% |
Compare them with other models
Quick answers
Is Qwen3-235B-A22B-Thinking-2507 better than Gemini 3.1 Pro Preview?
Pick Gemini 3.1 Pro Preview if quality matters most: it scores higher (Intelligence Index 29.7 against 12.7). Pick Qwen3-235B-A22B-Thinking-2507 if cost matters more: it costs 4.6 times less per token.
Which is cheaper, Qwen3-235B-A22B-Thinking-2507 or Gemini 3.1 Pro Preview?
Qwen3-235B-A22B-Thinking-2507 is cheaper: $0.97 against $4.50 per million tokens, 4.6 times less.
Which is better for agents and tool use, Qwen3-235B-A22B-Thinking-2507 or Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview ranks 62 of 166 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 140 for Qwen3-235B-A22B-Thinking-2507.
Which is better for reasoning and knowledge, Qwen3-235B-A22B-Thinking-2507 or Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview ranks 26 of 200 models on sale for hard questions across science, maths and general knowledge, against 119 for Qwen3-235B-A22B-Thinking-2507.
Which is better for writing, Qwen3-235B-A22B-Thinking-2507 or Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview ranks 9 of 189 models on sale for what people prefer in blind comparisons, and judged writing quality, against 123 for Qwen3-235B-A22B-Thinking-2507.
Which is better for sticking to the facts, Qwen3-235B-A22B-Thinking-2507 or Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview ranks 35 of 153 models on sale for summarising without inventing things, and factual answers, against 93 for Qwen3-235B-A22B-Thinking-2507.
Which has the bigger context window, Qwen3-235B-A22B-Thinking-2507 or Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview: 1,048,576 tokens, against 131,072 for Qwen3-235B-A22B-Thinking-2507.
Run Qwen3-235B-A22B-Thinking-2507 and Gemini 3.1 Pro Preview on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.