Compare / Qwen3.7-Max vs Claude Sonnet 5
Qwen3.7-Max vs Claude Sonnet 5
Which is cheaper, which is more capable, and which does better at each kind of work, from 14 results on 3 sources that measured both models.
Of the 14 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 Anthropic, every model from both labs.
Qwen3.7-Max or Claude Sonnet 5? The short answer
Pick Claude Sonnet 5 if quality matters most: it scores higher (Intelligence Index 38.2 against 29.5). Pick Qwen3.7-Max if cost matters more: it costs 45% less per token.
- Qwen3.7-Max is cheaper: $2.21 against $4.00 per million tokens, 45% less.
- Claude Sonnet 5 scores higher on the Artificial Analysis Intelligence Index: 38.2 against 29.5.
- Claude Sonnet 5 is newer: released 30 Jun 2026, against 19 May 2026 for Qwen3.7-Max.
- On third-party benchmarks, on the results both models have: Qwen3.7-Max does better for sticking to the facts; Claude Sonnet 5 for agents and tool use and reasoning and knowledge.
Head to head
Every fact side by side
| Qwen3.7-Max | Claude Sonnet 5 | |
|---|---|---|
| Price per million tokens | $1.48 in · $4.42 out | $2.00 in · $10.00 out |
| Blended (3 in : 1 out) | $2.21 | $4.00 |
| Cheapest host, blended | – | $4.00 (Amazon Bedrock) |
| Cached input, per million | – | $0.20 cached input |
| Intelligence Index | 29.5 | 38.2 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | – | – |
| Context window | 1,000,000 tokens | 1,000,000 tokens |
| Released | 19 May 2026 | 30 Jun 2026 (newer) |
| 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 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
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 | Qwen3.7-Max | Claude Sonnet 5 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Confirmed task success · AgentIPS effect estimate, higher is better 39 · 26 of 48 measured | -0.09arena agent | 0.01high reasoning, arena agent |
| Praise over complaint · AgentIPS effect estimate, higher is better 39 · 13 of 48 measured | -0.09arena agent | 0.09high reasoning, arena agent |
| Steerability · AgentIPS effect estimate, higher is better 41 · 14 of 48 measured | -0.06arena agent | 0.05high reasoning, arena agent |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better 53 · 34 of 243 measured | 29.5 | 38.2max reasoning |
| GPQA Diamond% of questions, higher is better 21 · 31 of 231 measured | 92.3% | 91.1%max reasoning |
| Humanity's Last Exam% of questions, higher is better 39 · 34 of 242 measured | 40.5% | 41.3%max reasoning |
| SimpleQA Verified (Epoch AI) reported by SimpleQA Verified (Epoch AI) · 1 result | ||
| Correct answers% of questions, higher is better 18 · 53 of 76 measured | 55.8% | 33.7%max reasoning |
Show all 14 results (7 more)
| Measure | Qwen3.7-Max | Claude Sonnet 5 |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 1 result | ||
| Tool grounding · AgentIPS effect estimate, higher is better 34 · 19 of 48 measured | 0.00arena agent | 0.00high reasoning, arena agent |
| Artificial Analysis reported by Artificial Analysis · 6 results | ||
| Terminal-Bench 2.1% of tasks, higher is better 33 · 23 of 130 measured | 74.5% | 80.5%max reasoning |
| Terminal-Bench 4.0% of tasks, higher is better 51 · 29 of 112 measured | 1.5% | 14.1%max reasoning |
| τ-bench banking% of tasks, higher is better 71 · 24 of 121 measured | 11.8% | 37.3%max reasoning |
| Artificial Analysis Coding Indexindex score, higher is better 34 · 22 of 131 measured | 66.0 | 71.5max reasoning |
| Long-context reasoning (AA-LCR)% of questions, higher is better 50 · 24 of 233 measured | 79.0% | 82.0%max reasoning |
| SciCode% of problems, higher is better 52 · 28 of 113 measured | 49.5% | 54.3%high reasoning |
Compare them with other models
Quick answers
Is Qwen3.7-Max better than Claude Sonnet 5?
Pick Claude Sonnet 5 if quality matters most: it scores higher (Intelligence Index 38.2 against 29.5). Pick Qwen3.7-Max if cost matters more: it costs 45% less per token.
Which is cheaper, Qwen3.7-Max or Claude Sonnet 5?
Qwen3.7-Max is cheaper: $2.21 against $4.00 per million tokens, 45% less.
Which is better for agents and tool use, Qwen3.7-Max or Claude Sonnet 5?
Claude Sonnet 5 ranks 35 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 69 for Qwen3.7-Max.
Which is better for reasoning and knowledge, Qwen3.7-Max or Claude Sonnet 5?
Claude Sonnet 5 ranks 33 of 198 models on sale for hard questions across science, maths and general knowledge, against 39 for Qwen3.7-Max.
Which is better for sticking to the facts, Qwen3.7-Max or Claude Sonnet 5?
Qwen3.7-Max ranks 31 of 152 models on sale for summarising without inventing things, and factual answers, against 85 for Claude Sonnet 5.
Run Qwen3.7-Max and Claude Sonnet 5 on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.