Compare / Qwen3.5-397B-A17B vs GLM-4.6

Qwen3.5-397B-A17B vs GLM-4.6

Which is cheaper, which is more capable, and which does better at each kind of work, from 20 results on 3 sources that measured both models.

AlibabaQwen3.5-397B-A17B Released 13 Feb 2026 · $0.55 in · $3.50 out
Z.aiGLM-4.6 Released 30 Sep 2025 · $0.50 in · $2.00 out
Qwen3.5-397B-A17B wins 143 too close to callGLM-4.6 wins 3

Of the 20 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.

Qwen3.5-397B-A17B or GLM-4.6? The short answer

Pick Qwen3.5-397B-A17B if quality matters most: it scores higher (Intelligence Index 21.4 against 18.5). Pick GLM-4.6 if cost matters more: it costs 32% less per token.

  • GLM-4.6 is cheaper: $0.88 against $1.29 per million tokens, 32% less.
  • Qwen3.5-397B-A17B scores higher on the Artificial Analysis Intelligence Index: 21.4 against 18.5.
  • Qwen3.5-397B-A17B is newer: released 13 Feb 2026, against 30 Sep 2025 for GLM-4.6.
  • On third-party benchmarks, on the results both models have: Qwen3.5-397B-A17B does better for agents and tool use and reasoning and knowledge.

Head to head

21.4
Intelligence Index
18.5
$1.29
Price per million tokens, blendedlower is better
$0.88
262,144
Context window, tokens
204,800

Every fact side by side

Qwen3.5-397B-A17BGLM-4.6
Price per million tokens$0.55 in · $3.50 out$0.50 in · $2.00 out
Blended (3 in : 1 out)$1.29$0.88
Cheapest host, blended$0.88 (Alibaba)$0.76 (Venice, FP4)
Intelligence Index21.418.5
Spring Prompt overall––
Output speed, tokens a second90–
Context window262,144 tokens204,800 tokens
Released13 Feb 2026 (newer)30 Sep 2025
WeightsOpenOpen
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 70 of 164 55 of 164
Professional workReal tasks from banking, consulting and law, business documents and freelance projects 48 of 51 not measured
Reasoning and knowledgeHard questions across science, maths and general knowledge 73 of 198 108 of 198
WritingWhat people prefer in blind comparisons, and judged writing quality 69 of 188 79 of 188
Sticking to the factsSummarising without inventing things, and factual answers 75 of 152 70 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.

MeasureQwen3.5-397B-A17BGLM-4.6
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 80 · 107 of 387 measured 1,442 1,424
Overall · Text factualityArena rating, higher is better 70 · 65 of 163 measured 1,445 1,447
Business, management and finance · TextArena rating, higher is better 73 · 120 of 380 measured 1,446 1,412
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 97 · 111 of 243 measured 21.4no reasoning 18.5thinking reasoning
GPQA Diamond% of questions, higher is better 53 · 120 of 231 measured 89.3% 78.0%thinking reasoning
Humanity's Last Exam% of questions, higher is better 77 · 129 of 242 measured 29.0% 14.5%thinking reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 77 · 70 of 230 measured 50.1no reasoning 53.3thinking reasoning
Requested-length error · UGI% off the requested word count, lower is better 134 · 57 of 230 measured 23.0%no reasoning 13.0%thinking reasoning
Style adherence · UGIscore from 0 to 1, higher is better 164 · 31 of 230 measured 0.33no reasoning 0.38thinking reasoning
Show all 20 results (11 more)
MeasureQwen3.5-397B-A17BGLM-4.6
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 86 · 94 of 385 measured 1,405 1,400
Expert prompts · TextArena rating, higher is better 67 · 115 of 338 measured 1,477 1,439
Instruction following · TextArena rating, higher is better 78 · 108 of 387 measured 1,434 1,412
Writing, literature and language · TextArena rating, higher is better 80 · 102 of 386 measured 1,421 1,405
Artificial Analysis reported by Artificial Analysis · 7 results
Terminal-Bench 2.1% of tasks, higher is better 61 · 63 of 130 measured 51.3% 49.4%thinking reasoning
τ-bench banking% of tasks, higher is better 64 · 64 of 121 measured 13.4% 13.4%thinking reasoning
Artificial Analysis Coding Indexindex score, higher is better 61 · 64 of 131 measured 48.2 45.8thinking reasoning
IFBench% of instructions, higher is better 8 · 120 of 195 measured 78.8% 43.4%thinking reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 66 · 145 of 233 measured 77.3% 54.0%thinking reasoning
Terminal-Bench Hard% of tasks, higher is better 34 · 69 of 190 measured 40.9% 28.8%no reasoning
τ²-bench telecom% of tasks, higher is better 16 · 74 of 193 measured 95.6% 76.9%no reasoning

Quick answers

Is Qwen3.5-397B-A17B better than GLM-4.6?

Pick Qwen3.5-397B-A17B if quality matters most: it scores higher (Intelligence Index 21.4 against 18.5). Pick GLM-4.6 if cost matters more: it costs 32% less per token.

Which is cheaper, Qwen3.5-397B-A17B or GLM-4.6?

GLM-4.6 is cheaper: $0.88 against $1.29 per million tokens, 32% less.

Which is better for agents and tool use, Qwen3.5-397B-A17B or GLM-4.6?

GLM-4.6 ranks 55 of 164 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 70 for Qwen3.5-397B-A17B.

Which is better for reasoning and knowledge, Qwen3.5-397B-A17B or GLM-4.6?

Qwen3.5-397B-A17B ranks 73 of 198 models on sale for hard questions across science, maths and general knowledge, against 108 for GLM-4.6.

Which is better for writing, Qwen3.5-397B-A17B or GLM-4.6?

Qwen3.5-397B-A17B ranks 69 of 188 models on sale for what people prefer in blind comparisons, and judged writing quality, against 79 for GLM-4.6.

Which is better for sticking to the facts, Qwen3.5-397B-A17B or GLM-4.6?

GLM-4.6 ranks 70 of 152 models on sale for summarising without inventing things, and factual answers, against 75 for Qwen3.5-397B-A17B.

Which has the bigger context window, Qwen3.5-397B-A17B or GLM-4.6?

Qwen3.5-397B-A17B: 262,144 tokens, against 204,800 for GLM-4.6.

Run Qwen3.5-397B-A17B and GLM-4.6 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