Compare / Gemma 3 4B vs Llama 4 Maverick

Gemma 3 4B vs Llama 4 Maverick

Which is cheaper, which is more capable, and which does better at each kind of work, from 19 results on 3 sources that measured both models.

Gemma 3 4B
Google · profile
Llama 4 Maverick
Meta · profile
Results compared
19
Shared sources
3

Gemma 3 4B or Llama 4 Maverick? The short answer

  • Gemma 3 4B is cheaper: $0.062 against $0.42 per million tokens, 6.6 times less.
  • Llama 4 Maverick scores higher on the Artificial Analysis Intelligence Index: 10.0 against 4.8.
  • On our business benchmarks, Llama 4 Maverick ranks higher for agents and tool use, reasoning and knowledge and writing.

At a glance

Gemma 3 4BLlama 4 Maverick
Price per million tokens$0.050 in · $0.10 out$0.27 in · $0.85 out
Blended (3 in : 1 out)$0.062$0.42
Cheapest host, blended–$0.30 (DigitalOcean)
Intelligence Index4.810.0
Spring Prompt overall––
Output speed, tokens a second–42
Context window131,072 tokens1,048,576 tokens
WeightsOpenOpen
Developer based inthe USthe US

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 4BLlama 4 Maverick
Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls 160 of 161 141 of 161
Reasoning and knowledgeHard questions across science, maths and general knowledge 187 of 195 146 of 195
WritingWhat people prefer in blind comparisons, and judged writing quality 171 of 187 166 of 187
Sticking to the factsSummarising without inventing things, and factual answers 34 of 153 not measured

Every shared result

BenchmarkMetricGemma 3 4BLlama 4 Maverick
Arena (formerly LMArena)reportedBusiness, management and financeArena rating 1,3301,317
Arena (formerly LMArena)reportedCreative writingArena rating 1,2741,307
Arena (formerly LMArena)reportedExpert promptsArena rating 1,2601,326
Arena (formerly LMArena)reportedInstruction followingArena rating 1,2671,314
Arena (formerly LMArena)reportedOverallArena rating 1,3031,327
Arena (formerly LMArena)reportedWriting, literature and languageArena rating 1,2981,312
Artificial AnalysisreportedArtificial Analysis Coding Indexindex score 2.7016.3
Artificial AnalysisreportedArtificial Analysis Intelligence Indexindex score 4.8010.0
Artificial AnalysisreportedGPQA Diamond% of questions 29.1%67.1%
Artificial AnalysisreportedHumanity's Last Exam% of questions 5.3%4.9%
Artificial AnalysisreportedIFBench% of instructions 28.3%43.0%
Artificial AnalysisreportedLong-context reasoning (AA-LCR)% of questions 6.7%50.0%
Artificial AnalysisreportedTerminal-Bench 2.1% of tasks 0.4%7.9%
Artificial AnalysisreportedTerminal-Bench Hard% of tasks 0.8%6.8%
Artificial AnalysisreportedΤ-bench banking% of tasks 0.4%3.7%
Artificial AnalysisreportedΤ²-bench telecom% of tasks 5.0%17.8%
UGI LeaderboardreportedRequested-length error% off the requested word count 9.0%13.0%
UGI LeaderboardreportedStyle adherencescore from 0 to 1 0.290.37
UGI LeaderboardreportedWriting scorescore out of 100 24.024.0

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 4B better than Llama 4 Maverick?

It depends on the task. Among models available today, on our benchmarks and licensed sources, Llama 4 Maverick ranks higher for agents and tool use, reasoning and knowledge and writing.

Which is cheaper, Gemma 3 4B or Llama 4 Maverick?

Gemma 3 4B costs $0.062 per million tokens (three input to one output), against $0.42 for Llama 4 Maverick.

Run Gemma 3 4B and Llama 4 Maverick on your own prompt

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