Compare / Qwen3.8-Max (0902) vs GLM-5.2

Qwen3.8-Max (0902) vs GLM-5.2

Which is cheaper, which is more capable, and which does better at each kind of work, from 23 results on 4 sources that measured both models.

AlibabaQwen3.8-Max (0902) Released 3 Aug 2026 · $2.00 in · $6.00 out
Z.aiGLM-5.2 Released 16 Jun 2026 · $1.40 in · $4.40 out
Qwen3.8-Max (0902) wins 147 too close to callGLM-5.2 wins 2

Of the 23 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 9 October 2026 (catalogue release 2026-10-09-dd620e778ac5). See also Alibaba vs Z.ai, every model from both labs.

Qwen3.8-Max (0902) or GLM-5.2? The short answer

Pick Qwen3.8-Max (0902) if quality matters most: it scores higher (Intelligence Index 45.4 against 33.7). Pick GLM-5.2 if cost matters more: it costs 28% less per token.

  • GLM-5.2 is cheaper: $2.15 against $3.00 per million tokens, 28% less.
  • Qwen3.8-Max (0902) scores higher on the Artificial Analysis Intelligence Index: 45.4 against 33.7.
  • Qwen3.8-Max (0902) is newer: released 3 Aug 2026, against 16 Jun 2026 for GLM-5.2.
  • On third-party benchmarks, on the results both models have: Qwen3.8-Max (0902) does better for agents and tool use, reasoning and knowledge and sticking to the facts.

Head to head

45.4
Intelligence Index
33.7
$3.00
Price per million tokens, blendedlower is better
$2.15
1,000,000
Context window, tokens
1,048,576

Every fact side by side

Qwen3.8-Max (0902)GLM-5.2
Price per million tokens$2.00 in · $6.00 out$1.40 in · $4.40 out
Blended (3 in : 1 out)$3.00$2.15
Cheapest host, blended–$0.64 (Decart, MXFP4)
Cached input, per million–$0.26 cached input
Intelligence Index45.433.7
Spring Prompt overall48–
Output speed, tokens a second37–
Context window1,000,000 tokens1,048,576 tokens
Released3 Aug 2026 (newer)16 Jun 2026
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.

Product listingsTurning a sparse product feed and photos into listings that can go live 17 of 20 not measured
Decks from an analysisTurning a finished analysis into a deck you could present as it is 11 of 19 not measured
Marketing planningPlanning a year of ad spend without overspending 14 of 19 not measured
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 7 of 164 40 of 164
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 18 of 51 not measured
Reasoning and knowledgeHard questions across science, maths and general knowledge 17 of 198 43 of 198
WritingWhat people prefer in blind comparisons, and judged writing quality 16 of 188 26 of 188
Sticking to the factsSummarising without inventing things, and factual answers 38 of 152 68 of 152
Speed under pressureGood decisions against a real clock (fast chess) 24 of 24 not measured

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.

MeasureQwen3.8-Max (0902)GLM-5.2
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 20 · 27 of 387 measured 1,482 1,476max reasoning
Overall · Text factualityArena rating, higher is better 22 · 36 of 163 measured 1,472 1,463max reasoning
Business, management and finance · TextArena rating, higher is better 16 · 41 of 380 measured 1,484 1,465max reasoning
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 14 · 42 of 243 measured 45.4 33.7max reasoning
GPQA Diamond% of questions, higher is better 15 · 49 of 231 measured 92.8% 89.5%max reasoning
Humanity's Last Exam% of questions, higher is better 24 · 35 of 242 measured 43.1% 41.1%max reasoning
SimpleQA Verified (Epoch AI) reported by SimpleQA Verified (Epoch AI) · 1 result
Correct answers% of questions, higher is better 30 · 51 of 76 measured 47.3%xhigh reasoning 34.2%max reasoning
τ²-bench reported by τ²-bench · 2 results
Consistency (pass^4) · tau2 v1.0.1, banking knowledge, alltools retrieval% of tasks, higher is better 1 · 13 of 21 measured 35.1%xhigh reasoning, tau2 13.4%xhigh reasoning, tau2
Task success (pass^1) · tau2 v1.0.1, banking knowledge, alltools retrieval% of tasks, higher is better 1 · 11 of 21 measured 55.2%xhigh reasoning, tau2 37.1%xhigh reasoning, tau2
Show all 23 results (14 more)
MeasureQwen3.8-Max (0902)GLM-5.2
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 8 results
Confirmed task success · AgentIPS effect estimate, higher is better 20 · 19 of 48 measured 0.05arena agent 0.05max reasoning, arena agent
Creative writing · TextArena rating, higher is better 17 · 26 of 385 measured 1,468 1,454max reasoning
Expert prompts · TextArena rating, higher is better 20 · 35 of 338 measured 1,513 1,502max reasoning
Instruction following · TextArena rating, higher is better 25 · 31 of 387 measured 1,474 1,470max reasoning
Praise over complaint · AgentIPS effect estimate, higher is better 20 · 12 of 48 measured 0.03arena agent 0.10max reasoning, arena agent
Steerability · AgentIPS effect estimate, higher is better 18 · 22 of 48 measured 0.03arena agent 0.01max reasoning, arena agent
Tool grounding · AgentIPS effect estimate, higher is better 43 · 9 of 48 measured -0.01arena agent 0.00max reasoning, arena agent
Writing, literature and language · TextArena rating, higher is better 18 · 31 of 386 measured 1,472 1,459max reasoning
Artificial Analysis reported by Artificial Analysis · 6 results
Terminal-Bench 2.1% of tasks, higher is better 5 · 30 of 130 measured 88.8% 77.9%max reasoning
Terminal-Bench 4.0% of tasks, higher is better 12 · 52 of 112 measured 38.9% 1.0%max reasoning
τ-bench banking% of tasks, higher is better 7 · 27 of 121 measured 47.8% 34.6%max reasoning
Artificial Analysis Coding Indexindex score, higher is better 10 · 30 of 131 measured 76.2 68.8max reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 35 · 54 of 233 measured 80.3% 78.3%max reasoning
SciCode% of problems, higher is better 36 · 42 of 113 measured 52.1% 51.2%max reasoning

Quick answers

Is Qwen3.8-Max (0902) better than GLM-5.2?

Pick Qwen3.8-Max (0902) if quality matters most: it scores higher (Intelligence Index 45.4 against 33.7). Pick GLM-5.2 if cost matters more: it costs 28% less per token.

Which is cheaper, Qwen3.8-Max (0902) or GLM-5.2?

GLM-5.2 is cheaper: $2.15 against $3.00 per million tokens, 28% less.

Which is better for agents and tool use, Qwen3.8-Max (0902) or GLM-5.2?

Qwen3.8-Max (0902) ranks 7 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 40 for GLM-5.2.

Which is better for reasoning and knowledge, Qwen3.8-Max (0902) or GLM-5.2?

Qwen3.8-Max (0902) ranks 17 of 198 models on sale for hard questions across science, maths and general knowledge, against 43 for GLM-5.2.

Which is better for writing, Qwen3.8-Max (0902) or GLM-5.2?

Qwen3.8-Max (0902) ranks 16 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 26 for GLM-5.2.

Which is better for sticking to the facts, Qwen3.8-Max (0902) or GLM-5.2?

Qwen3.8-Max (0902) ranks 38 of 152 models on sale for summarising without inventing things, and factual answers, against 68 for GLM-5.2.

Which has the bigger context window, Qwen3.8-Max (0902) or GLM-5.2?

GLM-5.2: 1,048,576 tokens, against 1,000,000 for Qwen3.8-Max (0902).

Run Qwen3.8-Max (0902) and GLM-5.2 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