Compare / Gemma 4 26B A4B vs GLM-4.6

Gemma 4 26B A4B vs GLM-4.6

Which is cheaper, which is more capable, and which does better at each kind of work, from 22 results on 4 sources that measured both models.

GoogleGemma 4 26B A4B Released 2 Apr 2026 · $0.090 in · $0.30 out
Z.aiGLM-4.6 Released 30 Sep 2025 · $0.50 in · $2.00 out
Gemma 4 26B A4B wins 104 too close to callGLM-4.6 wins 8

Of the 22 results both models have, the better value on each. Results whose reported ranges overlap are too close to call.

Results as of 16 November 2026 (catalogue release 2026-11-16-49bdfa045dee). See also Google vs Z.ai, every model from both labs.

Gemma 4 26B A4B or GLM-4.6? The short answer

They score about the same, so pick Gemma 4 26B A4B: it costs 6.1 times less per token.

  • Gemma 4 26B A4B is cheaper: $0.14 against $0.88 per million tokens, 6.1 times less.
  • GLM-4.6 scores higher on the Artificial Analysis Intelligence Index: 18.5 against 16.7.
  • Gemma 4 26B A4B is newer: released 2 Apr 2026, against 30 Sep 2025 for GLM-4.6.
  • On third-party benchmarks, on the results both models have: Gemma 4 26B A4B does better for reasoning and knowledge and sticking to the facts; GLM-4.6 for agents and tool use.

Head to head

16.7
Intelligence Index
18.5
$0.14
Price per million tokens, blendedlower is better
$0.88
262,144
Context window, tokens
204,800

Every fact side by side

Gemma 4 26B A4BGLM-4.6
Price per million tokens$0.090 in · $0.30 out$0.50 in · $2.00 out
Blended (3 in : 1 out)$0.14$0.88
Cheapest host, blended$0.068 (Darkbloom)$0.76 (Venice, FP4)
Intelligence Index16.718.5
Spring Prompt overall––
Output speed, tokens a second82–
Context window262,144 tokens204,800 tokens
Released2 Apr 2026 (newer)30 Sep 2025
WeightsOpenOpen
Developer based inthe USChina

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 105 of 159 61 of 159
Reasoning and knowledgeHard questions across science, maths and general knowledge 110 of 187 115 of 187
WritingWhat people prefer in blind comparisons, and judged writing quality 82 of 169 77 of 169
Sticking to the factsSummarising without inventing things, and factual answers 43 of 139 68 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.

MeasureGemma 4 26B A4BGLM-4.6
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results
Overall · TextArena rating, higher is better 87 · 107 of 387 measured 1,437 1,424
Overall · Text factualityArena rating, higher is better 71 · 65 of 163 measured 1,445 1,447
Business, management and finance · TextArena rating, higher is better 78 · 120 of 380 measured 1,444 1,412
Artificial Analysis reported by Artificial Analysis · 3 results
Artificial Analysis Intelligence Indexindex score, higher is better 123 · 117 of 249 measured 16.7 18.5thinking reasoning
GPQA Diamond% of questions, higher is better 113 · 121 of 232 measured 79.2% 78.0%thinking reasoning
Humanity's Last Exam% of questions, higher is better 119 · 137 of 250 measured 19.3% 14.5%thinking reasoning
UGI Leaderboard reported by UGI Leaderboard · 3 results
Writing score · UGIscore out of 100, higher is better 92 · 70 of 230 measured 43.8channel-thought-prefill reasoning 53.3thinking reasoning
Requested-length error · UGI% off the requested word count, lower is better 25 · 57 of 230 measured 8.0% 13.0%thinking reasoning
Style adherence · UGIscore from 0 to 1, higher is better 93 · 31 of 230 measured 0.35channel-thought-prefill reasoning 0.38thinking reasoning
Vectara Hallucination Leaderboard reported by Vectara Hallucination Leaderboard · 2 results
Hallucination rate · Vectara% of summaries, lower is better 13 · 53 of 104 measured 5.2% 9.5%
Answer rate · Vectara% of documents, higher is better 31 · 89 of 104 measured 99.8% 94.5%
Show all 22 results (11 more)
MeasureGemma 4 26B A4BGLM-4.6
Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results
Creative writing · TextArena rating, higher is better 96 · 94 of 385 measured 1,400 1,400
Expert prompts · TextArena rating, higher is better 71 · 115 of 338 measured 1,475 1,439
Instruction following · TextArena rating, higher is better 71 · 108 of 387 measured 1,437 1,412
Writing, literature and language · TextArena rating, higher is better 97 · 102 of 386 measured 1,406 1,405
Artificial Analysis reported by Artificial Analysis · 7 results
Terminal-Bench 2.1% of tasks, higher is better 75 · 64 of 131 measured 39.0% 49.4%thinking reasoning
τ-bench banking% of tasks, higher is better 70 · 64 of 121 measured 12.0% 13.4%thinking reasoning
Artificial Analysis Coding Indexindex score, higher is better 74 · 63 of 130 measured 39.3 45.8thinking reasoning
IFBench% of instructions, higher is better 40 · 120 of 195 measured 72.4% 43.4%thinking reasoning
Long-context reasoning (AA-LCR)% of questions, higher is better 131 · 153 of 241 measured 65.7% 54.0%thinking reasoning
Terminal-Bench Hard% of tasks, higher is better 78 · 69 of 190 measured 25.0%no reasoning 28.8%no reasoning
τ²-bench telecom% of tasks, higher is better 110 · 74 of 193 measured 43.6% 76.9%no reasoning

Quick answers

Is Gemma 4 26B A4B better than GLM-4.6?

They score about the same, so pick Gemma 4 26B A4B: it costs 6.1 times less per token.

Which is cheaper, Gemma 4 26B A4B or GLM-4.6?

Gemma 4 26B A4B is cheaper: $0.14 against $0.88 per million tokens, 6.1 times less.

Which is better for agents and tool use, Gemma 4 26B A4B or GLM-4.6?

GLM-4.6 ranks 61 of 159 models on sale for multi-step tasks with tools: support desks, coding agents, function calls, against 105 for Gemma 4 26B A4B.

Which is better for reasoning and knowledge, Gemma 4 26B A4B or GLM-4.6?

Gemma 4 26B A4B ranks 110 of 187 models on sale for hard questions across science, maths and general knowledge, against 115 for GLM-4.6.

Which is better for writing, Gemma 4 26B A4B or GLM-4.6?

GLM-4.6 ranks 77 of 169 models on sale for what people prefer in blind comparisons, and judged writing quality, against 82 for Gemma 4 26B A4B.

Which is better for sticking to the facts, Gemma 4 26B A4B or GLM-4.6?

Gemma 4 26B A4B ranks 43 of 139 models on sale for summarising without inventing things, and factual answers, against 68 for GLM-4.6.

Which has the bigger context window, Gemma 4 26B A4B or GLM-4.6?

Gemma 4 26B A4B: 262,144 tokens, against 204,800 for GLM-4.6.

Run Gemma 4 26B A4B and GLM-4.6 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.