Compare / Qwen3-235B-A22B-Thinking-2507 vs MiniMax-M2.5
Qwen3-235B-A22B-Thinking-2507 vs MiniMax-M2.5
Which is cheaper, which is more capable, and which does better at each kind of work, from 17 results on 4 sources that measured both models.
Of the 17 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.
Results as of 13 October 2026 (catalogue release 2026-10-13-2e2420e3c5cc). See also Alibaba vs MiniMax, every model from both labs.
Qwen3-235B-A22B-Thinking-2507 or MiniMax-M2.5? The short answer
Pick MiniMax-M2.5: it scores higher (Intelligence Index 22.8 against 12.7) and costs less.
- MiniMax-M2.5 is cheaper: $0.52 against $0.97 per million tokens, 46% less.
- MiniMax-M2.5 scores higher on the Artificial Analysis Intelligence Index: 22.8 against 12.7.
- MiniMax-M2.5 is newer: released 12 Feb 2026, 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 agents and tool use; MiniMax-M2.5 for reasoning and knowledge and writing.
Head to head
Every fact side by side
| Qwen3-235B-A22B-Thinking-2507 | MiniMax-M2.5 | |
|---|---|---|
| Price per million tokens | $0.30 in · $3.00 out | $0.30 in · $1.20 out |
| Blended (3 in : 1 out) | $0.97 | $0.52 |
| Cheapest host, blended | $0.75 (Alibaba) | $0.44 (Venice) |
| Intelligence Index | 12.7 | 22.8 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 131,072 tokens | 204,800 tokens |
| Released | 25 Jul 2025 | 12 Feb 2026 (newer) |
| Weights | Open | Open |
| 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 | MiniMax-M2.5 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better 139 · 150 of 387 measured | 1,400 | 1,391 |
| Business, management and finance · TextArena rating, higher is better 133 · 142 of 380 measured | 1,404 | 1,400 |
| Creative writing · TextArena rating, higher is better 133 · 147 of 385 measured | 1,371 | 1,357 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 147 · 87 of 243 measured | 12.7 | 22.8 |
| GPQA Diamond% of questions, higher is better 114 · 80 of 231 measured | 79.0% | 84.8% |
| Humanity's Last Exam% of questions, higher is better 122 · 108 of 242 measured | 15.9% | 20.5% |
| UGI Leaderboard reported by UGI Leaderboard · 3 results | ||
| Writing score · UGIscore out of 100, higher is better 139 · 103 of 230 measured | 32.4 | 41.7 |
| Requested-length error · UGI% off the requested word count, lower is better 166 · 192 of 230 measured | 30.0% | 41.0% |
| Style adherence · UGIscore from 0 to 1, higher is better 194 · 35 of 230 measured | 0.31 | 0.38 |
| Vending-Bench 2 reported by Vending-Bench 2 · 1 result | ||
| Money after a yearUS dollars, higher is better 55 · 57 of 58 measured | $-11.34 | $-23.16 |
Show all 17 results (7 more)
| Measure | Qwen3-235B-A22B-Thinking-2507 | MiniMax-M2.5 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Expert prompts · TextArena rating, higher is better 85 · 130 of 338 measured | 1,466 | 1,425 |
| Instruction following · TextArena rating, higher is better 142 · 147 of 387 measured | 1,385 | 1,381 |
| Writing, literature and language · TextArena rating, higher is better 139 · 146 of 386 measured | 1,377 | 1,369 |
| Artificial Analysis reported by Artificial Analysis · 4 results | ||
| IFBench% of instructions, higher is better 101 · 43 of 195 measured | 51.2% | 71.6% |
| Long-context reasoning (AA-LCR)% of questions, higher is better 99 · 92 of 233 measured | 72.0% | 73.3% |
| Terminal-Bench Hard% of tasks, higher is better 116 · 49 of 190 measured | 13.6% | 34.8% |
| τ²-bench telecom% of tasks, higher is better 101 · 20 of 193 measured | 53.2% | 95.3% |
Compare them with other models
Quick answers
Is Qwen3-235B-A22B-Thinking-2507 better than MiniMax-M2.5?
Pick MiniMax-M2.5: it scores higher (Intelligence Index 22.8 against 12.7) and costs less.
Which is cheaper, Qwen3-235B-A22B-Thinking-2507 or MiniMax-M2.5?
MiniMax-M2.5 is cheaper: $0.52 against $0.97 per million tokens, 46% less.
Which is better for agents and tool use, Qwen3-235B-A22B-Thinking-2507 or MiniMax-M2.5?
MiniMax-M2.5 ranks 135 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 138 for Qwen3-235B-A22B-Thinking-2507.
Which is better for reasoning and knowledge, Qwen3-235B-A22B-Thinking-2507 or MiniMax-M2.5?
MiniMax-M2.5 ranks 84 of 198 models on sale for hard questions across science, maths and general knowledge, against 117 for Qwen3-235B-A22B-Thinking-2507.
Which is better for writing, Qwen3-235B-A22B-Thinking-2507 or MiniMax-M2.5?
MiniMax-M2.5 ranks 114 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 MiniMax-M2.5?
Qwen3-235B-A22B-Thinking-2507 ranks 92 of 152 models on sale for summarising without inventing things, and factual answers, against 102 for MiniMax-M2.5.
Which has the bigger context window, Qwen3-235B-A22B-Thinking-2507 or MiniMax-M2.5?
MiniMax-M2.5: 204,800 tokens, against 131,072 for Qwen3-235B-A22B-Thinking-2507.
Run Qwen3-235B-A22B-Thinking-2507 and MiniMax-M2.5 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.