Compare / Qwen3.7-Max vs GLM-4.7

Qwen3.7-Max vs GLM-4.7

Which is cheaper, which is more capable, and which does better at each kind of work, from 11 results on 2 sources that measured both models.

AlibabaQwen3.7-Max Released 19 May 2026 · $1.48 in · $4.42 out
Z.aiGLM-4.7 Released 22 Dec 2025 · $0.54 in · $1.98 out
Qwen3.7-Max wins 9GLM-4.7 wins 2

Of the 11 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 Z.ai, every model from both labs.

Qwen3.7-Max or GLM-4.7? The short answer

Pick Qwen3.7-Max if quality matters most: it scores higher (Intelligence Index 29.5 against 22.2). Pick GLM-4.7 if cost matters more: it costs 2.5 times less per token.

  • GLM-4.7 is cheaper: $0.90 against $2.21 per million tokens, 2.5 times less.
  • Qwen3.7-Max scores higher on the Artificial Analysis Intelligence Index: 29.5 against 22.2.
  • Qwen3.7-Max is newer: released 19 May 2026, against 22 Dec 2025 for GLM-4.7.
  • On third-party benchmarks, on the results both models have: Qwen3.7-Max does better for reasoning and knowledge and sticking to the facts.

Head to head

29.5
Intelligence Index
22.2
$2.21
Price per million tokens, blendedlower is better
$0.90
1,000,000
Context window, tokens
204,800

Every fact side by side

Qwen3.7-MaxGLM-4.7
Price per million tokens$1.48 in · $4.42 out$0.54 in · $1.98 out
Blended (3 in : 1 out)$2.21$0.90
Cheapest host, blended–$0.74 (DeepInfra, FP4)
Intelligence Index29.522.2
Spring Prompt overall––
Output speed, tokens a second––
Context window1,000,000 tokens204,800 tokens
Released19 May 2026 (newer)22 Dec 2025
WeightsClosedOpen
Developer based inChinaChina

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.

Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 69 of 164 102 of 164
Reasoning and knowledgeHard questions across science, maths and general knowledge 39 of 198 80 of 198
WritingWhat people prefer in blind comparisons, and judged writing quality not measured 72 of 188
Sticking to the factsSummarising without inventing things, and factual answers 31 of 152 103 of 152

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.

MeasureQwen3.7-MaxGLM-4.7
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 53 · 92 of 243 measured 29.5 22.2
GPQA Diamond% of questions, higher is better 21 · 73 of 231 measured 92.3% 85.9%
Humanity's Last Exam% of questions, higher is better 39 · 88 of 242 measured 40.5% 27.4%
SimpleQA Verified (Epoch AI) reported by SimpleQA Verified (Epoch AI) · 1 result
Correct answers% of questions, higher is better 18 · 56 of 76 measured 55.8% 32.2%
Show all 11 results (7 more)
MeasureQwen3.7-MaxGLM-4.7
Artificial Analysis reported by Artificial Analysis · 7 results
Terminal-Bench 2.1% of tasks, higher is better 33 · 67 of 130 measured 74.5% 45.3%
τ-bench banking% of tasks, higher is better 71 · 69 of 121 measured 11.8% 12.2%
Artificial Analysis Coding Indexindex score, higher is better 34 · 66 of 131 measured 66.0 45.3
IFBench% of instructions, higher is better 5 · 62 of 195 measured 80.5% 67.9%
Long-context reasoning (AA-LCR)% of questions, higher is better 50 · 105 of 233 measured 79.0% 71.0%
Terminal-Bench Hard% of tasks, higher is better 12 · 63 of 190 measured 50.8% 31.8%
τ²-bench telecom% of tasks, higher is better 22 · 12 of 193 measured 94.7% 95.9%

Quick answers

Is Qwen3.7-Max better than GLM-4.7?

Pick Qwen3.7-Max if quality matters most: it scores higher (Intelligence Index 29.5 against 22.2). Pick GLM-4.7 if cost matters more: it costs 2.5 times less per token.

Which is cheaper, Qwen3.7-Max or GLM-4.7?

GLM-4.7 is cheaper: $0.90 against $2.21 per million tokens, 2.5 times less.

Which is better for agents and tool use, Qwen3.7-Max or GLM-4.7?

Qwen3.7-Max ranks 69 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 102 for GLM-4.7.

Which is better for reasoning and knowledge, Qwen3.7-Max or GLM-4.7?

Qwen3.7-Max ranks 39 of 198 models on sale for hard questions across science, maths and general knowledge, against 80 for GLM-4.7.

Which is better for sticking to the facts, Qwen3.7-Max or GLM-4.7?

Qwen3.7-Max ranks 31 of 152 models on sale for summarising without inventing things, and factual answers, against 103 for GLM-4.7.

Which has the bigger context window, Qwen3.7-Max or GLM-4.7?

Qwen3.7-Max: 1,000,000 tokens, against 204,800 for GLM-4.7.

Run Qwen3.7-Max and GLM-4.7 on your own prompt

Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.

Try the playgroundTalk to us