Compare / GLM-4.5V vs GLM-4.6V

GLM-4.5V vs GLM-4.6V

Which is cheaper, which is more capable, and which does better at each kind of work, from 13 results on 2 sources that measured both models.

Z.aiGLM-4.5V Released 11 Aug 2025 · $0.60 in · $1.80 out
Z.aiGLM-4.6V Released 8 Dec 2025 · $0.30 in · $0.90 out
GLM-4.5V wins 15 too close to callGLM-4.6V wins 7

Of the 13 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 19 November 2026 (catalogue release 2026-11-19-3608133e8331).

GLM-4.5V or GLM-4.6V? The short answer

GLM-4.6V is the newer version and costs less, and it scores higher (Intelligence Index 11.2 against 7.6): upgrade.

  • GLM-4.6V is cheaper: $0.45 against $0.90 per million tokens, 2.0 times less.
  • GLM-4.6V scores higher on the Artificial Analysis Intelligence Index: 11.2 against 7.6.
  • GLM-4.6V is newer: released 8 Dec 2025, against 11 Aug 2025 for GLM-4.5V.
  • On third-party benchmarks, on the results both models have: GLM-4.6V does better for reasoning and knowledge and writing.

Head to head

7.6
Intelligence Index
11.2
$0.90
Price per million tokens, blendedlower is better
$0.45
65,536
Context window, tokens
131,072

Every fact side by side

GLM-4.5VGLM-4.6V
Price per million tokens$0.60 in · $1.80 out$0.30 in · $0.90 out
Blended (3 in : 1 out)$0.90$0.45
Cheapest host, blended$0.90 (Novita, FP8)$0.45 (Novita, BF16)
Intelligence Index7.611.2
Spring Prompt overall––
Output speed, tokens a second––
Context window65,536 tokens131,072 tokens
Released11 Aug 20258 Dec 2025 (newer)
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.

Reasoning and knowledgeHard questions across science, maths and general knowledge 144 of 187 130 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 129 of 169 114 of 169
Sticking to the factsSummarising without inventing things, and factual answers not measured 130 of 139

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.

MeasureGLM-4.5VGLM-4.6V
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 186 · 164 of 387 measured 1,352 1,379
Business, management and finance · TextArena rating, higher is better 199 · 165 of 380 measured 1,342 1,370
Creative writing · TextArena rating, higher is better 197 · 153 of 385 measured 1,310 1,351
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 208 · 166 of 249 measured 7.6thinking reasoning 11.2thinking reasoning
GPQA Diamond% of questions, higher is better 161 · 152 of 232 measured 68.4%thinking reasoning 71.9%thinking reasoning
Humanity's Last Exam% of questions, higher is better 188 · 167 of 250 measured 6.3%thinking reasoning 9.6%thinking reasoning
Show all 13 results (7 more)
MeasureGLM-4.5VGLM-4.6V
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Expert prompts · TextArena rating, higher is better 156 · 164 of 338 measured 1,399 1,394
Instruction following · TextArena rating, higher is better 189 · 163 of 387 measured 1,339 1,367
Writing, literature and language · TextArena rating, higher is better 201 · 160 of 386 measured 1,318 1,357
Artificial Analysis reported by Artificial Analysis · 4 results
IFBench% of instructions, higher is better 162 · 181 of 195 measured 34.2%thinking reasoning 30.1%thinking reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 230 · 166 of 241 measured 0.0%no reasoning 48.7%thinking reasoning
Terminal-Bench Hard% of tasks, higher is better 140 · 114 of 190 measured 6.8%no reasoning 14.4%thinking reasoning
τ²-bench telecom% of tasks, higher is better 160 · 130 of 193 measured 22.5%thinking reasoning 31.6%thinking reasoning

Quick answers

Is GLM-4.5V better than GLM-4.6V?

GLM-4.6V is the newer version and costs less, and it scores higher (Intelligence Index 11.2 against 7.6): upgrade.

Which is cheaper, GLM-4.5V or GLM-4.6V?

GLM-4.6V is cheaper: $0.45 against $0.90 per million tokens, 2.0 times less.

Which is better for reasoning and knowledge, GLM-4.5V or GLM-4.6V?

GLM-4.6V ranks 130 of 187 models on sale for hard questions across science, maths and general knowledge, against 144 for GLM-4.5V.

Which is better for writing, GLM-4.5V or GLM-4.6V?

GLM-4.6V ranks 114 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 129 for GLM-4.5V.

Which has the bigger context window, GLM-4.5V or GLM-4.6V?

GLM-4.6V: 131,072 tokens, against 65,536 for GLM-4.5V.

Run GLM-4.5V and GLM-4.6V on your own prompt.

Benchmarks aren't your task. Test both side by side on your prompt, with every answer checked against your rules and the cost of each one.