Artificial Analysis
Not measured by Artificial Analysis.
Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.
gemma-3-4b-it benchmarks, ranks and price
Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place gemma-3-4b-it, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.
Read Oct 1, 2026
#82of 85
on the LLM leaderboard, with a consensus score of 22 across 2 leaderboards.
Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.
By leaderboard
Where each leaderboard places gemma-3-4b-it
LiveBench
Not measured by LiveBench.
Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.
LMArena
#71of 79
Score 1303. Best run: gemma-3-4b-it.
Blind head-to-head human votes, style controlled.
Berkeley BFCL
#35of 37
Score 19.62%. Best run: Gemma-3-4b-it (Prompt).
Function calling and tool use, single turn to multi turn and web search.
Price and context
–
No gateway lists it.
Nearby
The models either side of gemma-3-4b-it
- #79llama-3.1-8b-instruct24
- #80gpt-oss-20b23
- #81amazon-nova-micro-v1.023
- #82gemma-3-4b-it22
- #83llama-3.2-3b-instruct20
- #84Ministral 3 8B 251220
- #85llama-3.2-1b-instruct18
Questions about gemma-3-4b-it
How good is gemma-3-4b-it?
gemma-3-4b-it ranks #82 of 85 models on the Rank.ai LLM leaderboard, with a consensus score of 22 out of 100 across 2 leaderboards.
Is gemma-3-4b-it better than amazon-nova-micro-v1.0?
Not on the consensus: amazon-nova-micro-v1.0 scores 23 to gemma-3-4b-it's 22. Compare them source by source below, since the leaderboards test different things.
Is gemma-3-4b-it better than llama-3.2-3b-instruct?
On the consensus, yes: 22 to 20.
These models recommend brands. See if they name yours.
Enter your website. In about two minutes, Rank.ai asks ChatGPT, Claude and Gemini 12 questions your customers ask and grades how often they name you.
- Your grade out of 100How often AI names you, cites your site, and how high it ranks you.
- Who gets namedEvery competitor in the answers, most named first.
- The pages AI readsThe sources behind each answer.
- Three fixesWhat to fix first, with a brief for the first article.