Compare / Qwen3.7 Max vs o4 Mini
Qwen3.7 Max vs o4 Mini
Which is cheaper, which is more capable, and which does better at each kind of work, from 8 results on 2 sources that measured both models.
Qwen3.7 Max or o4 Mini? The short answer
- o4 Mini is cheaper: $1.93 against $2.21 per million tokens, 13% less.
- Qwen3.7 Max scores higher on the Artificial Analysis Intelligence Index: 29.5 against 16.7.
- On our business benchmarks, Qwen3.7 Max ranks higher for reasoning and knowledge and sticking to the facts.
- On our business benchmarks, o4 Mini ranks higher for agents and tool use.
At a glance
| Qwen3.7 Max | o4 Mini | |
|---|---|---|
| Price per million tokens | $1.48 in · $4.42 out | $1.10 in · $4.40 out |
| Blended (3 in : 1 out) | $2.21 | $1.93 |
| Cheapest host, blended | – | – |
| Intelligence Index | 29.5 | 16.7 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 1,000,000 tokens | 200,000 tokens |
| Weights | Closed | 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 models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | Qwen3.7 Max | o4 Mini |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 66 of 161 | 46 of 161 |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 37 of 195 | 101 of 195 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | not measured | 98 of 187 |
| Sticking to the factsSummarising without inventing things, and factual answers | 33 of 153 | 141 of 153 |
Every shared result
| Benchmark | Metric | Qwen3.7 Max | o4 Mini |
|---|---|---|---|
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 29.5 | 16.7 |
| Artificial Analysisreported | GPQA Diamond% of questions | 92.3% | 78.4% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 40.5% | 16.5% |
| Artificial Analysisreported | IFBench% of instructions | 80.5% | 68.7% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 79.0% | 61.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 50.8% | 15.2% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 94.7% | 55.6% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 55.8% | 19.6% |
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 Qwen3.7 Max better than o4 Mini?
It depends on the task. Among models available today, on our benchmarks and licensed sources, Qwen3.7 Max ranks higher for reasoning and knowledge and sticking to the facts; o4 Mini ranks higher for agents and tool use.
Which is cheaper, Qwen3.7 Max or o4 Mini?
o4 Mini costs $1.93 per million tokens (three input to one output), against $2.21 for Qwen3.7 Max.
Run Qwen3.7 Max and o4 Mini on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.