Compare / Gemma 3 12B vs GLM 4.6V

Gemma 3 12B vs GLM 4.6V

Which is cheaper, which is more capable, and which does better at each kind of work, from 16 results on 3 sources that measured both models.

Gemma 3 12B
Google · profile
GLM 4.6V
Z.ai · profile
Results compared
16
Shared sources
3

Gemma 3 12B or GLM 4.6V? The short answer

  • Gemma 3 12B is cheaper: $0.075 against $0.45 per million tokens, 6.0 times less.
  • GLM 4.6V scores higher on the Artificial Analysis Intelligence Index: 11.2 against 3.8.
  • On our business benchmarks, Gemma 3 12B ranks higher for sticking to the facts.
  • On our business benchmarks, GLM 4.6V ranks higher for reasoning and knowledge and writing.

At a glance

Gemma 3 12BGLM 4.6V
Price per million tokens$0.050 in · $0.15 out$0.30 in · $0.90 out
Blended (3 in : 1 out)$0.075$0.45
Cheapest host, blended–$0.45 (Novita, BF16)
Intelligence Index3.811.2
Spring Prompt overall––
Output speed, tokens a second––
Context window131,072 tokens131,072 tokens
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 models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.

Use caseGemma 3 12BGLM 4.6V
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 147 of 161 not measured
Reasoning and knowledgeHard questions across science, maths and general knowledge 195 of 195 132 of 195
WritingWhat people prefer in blind comparisons, and judged writing quality 149 of 187 118 of 187
Sticking to the factsSummarising without inventing things, and factual answers 5 of 153 134 of 153

Every shared result

BenchmarkMetricGemma 3 12BGLM 4.6V
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,3861,370
Arena (formerly LMArena)reportedCreative writingArena rating 1,3321,350
Arena (formerly LMArena)reportedExpert promptsArena rating 1,2741,394
Arena (formerly LMArena)reportedInstruction followingArena rating 1,3211,367
Arena (formerly LMArena)reportedOverallArena rating 1,3421,379
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,3131,357
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 3.8011.2
Artificial AnalysisreportedGPQA Diamond% of questions 34.9%71.9%
Artificial AnalysisreportedHumanity's Last Exam% of questions 4.2%9.6%
Artificial AnalysisreportedIFBench% of instructions 36.7%30.1%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 8.3%48.7%
Artificial AnalysisreportedTerminal-Bench Hard% of tasks 0.8%14.4%
Artificial AnalysisreportedΤ²-bench telecom% of tasks 10.8%31.6%
UGI LeaderboardreportedRequested-length error% off the requested word count 9.0%35.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.290.39
UGI LeaderboardreportedWriting scorescore out of 100 29.939.7

Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.

Quick answers

Is Gemma 3 12B better than GLM 4.6V?

It depends on the task. Among models available today, on our benchmarks and licensed sources, Gemma 3 12B ranks higher for sticking to the facts; GLM 4.6V ranks higher for reasoning and knowledge and writing.

Which is cheaper, Gemma 3 12B or GLM 4.6V?

Gemma 3 12B costs $0.075 per million tokens (three input to one output), against $0.45 for GLM 4.6V.

Run Gemma 3 12B and GLM 4.6V on your own prompt

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