Compare / Qwen3 235B A22B Thinking 2507 vs MiniMax M2.7
Qwen3 235B A22B Thinking 2507 vs MiniMax M2.7
Which is cheaper, which is more capable, and which does better at each kind of work, from 21 results on 3 sources that measured both models.
Qwen3 235B A22B Thinking 2507 or MiniMax M2.7? The short answer
- MiniMax M2.7 is cheaper: $0.52 against $0.97 per million tokens, 46% less.
- MiniMax M2.7 scores higher on the Artificial Analysis Intelligence Index: 22.8 against 12.7.
- On our business benchmarks, Qwen3 235B A22B Thinking 2507 ranks higher for sticking to the facts.
- On our business benchmarks, MiniMax M2.7 ranks higher for agents and tool use, reasoning and knowledge and writing.
At a glance
| Qwen3 235B A22B Thinking 2507 | MiniMax M2.7 | |
|---|---|---|
| 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) | $0.37 (GMICloud, FP8) |
| Intelligence Index | 12.7 | 22.8 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 131,072 tokens | 204,800 tokens |
| 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 models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | Qwen3 235B A22B Thinking 2507 | MiniMax M2.7 |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 134 of 161 | 100 of 161 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 113 of 195 | 68 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 120 of 187 | 108 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 93 of 153 | 124 of 153 |
Every shared result
| Benchmark | Metric | Qwen3 235B A22B Thinking 2507 | MiniMax M2.7 |
|---|---|---|---|
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,404 | 1,423 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,370 | 1,363 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,466 | 1,452 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,385 | 1,407 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,400 | 1,415 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,377 | 1,386 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 22.1 | 52.6 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 12.7 | 22.8 |
| Artificial Analysisreported | GPQA Diamond% of questions | 79.0% | 87.4% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 15.9% | 29.6% |
| Artificial Analysisreported | IFBench% of instructions | 51.2% | 75.7% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 72.0% | 78.3% |
| Artificial Analysisreported | SciCode% of problems | 41.4% | 50.1% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 12.0% | 55.4% |
| Artificial Analysisreported | Terminal-Bench 4.0% of tasks | 0.0% | 0.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 13.6% | 39.4% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 7.8% | 9.9% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 53.2% | 84.8% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 30.0% | 36.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.31 | 0.38 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 32.4 | 37.6 |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.
Quick answers
Is Qwen3 235B A22B Thinking 2507 better than MiniMax M2.7?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Qwen3 235B A22B Thinking 2507 ranks higher for sticking to the facts; MiniMax M2.7 ranks higher for agents and tool use, reasoning and knowledge and writing.
Which is cheaper, Qwen3 235B A22B Thinking 2507 or MiniMax M2.7?
MiniMax M2.7 costs $0.52 per million tokens (three input to one output), against $0.97 for Qwen3 235B A22B Thinking 2507.
Run Qwen3 235B A22B Thinking 2507 and MiniMax M2.7 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.