Gemma 3 4B

google/gemma-3-4b-it

Google's Gemma 3 4B is a text and image input, text output model. It has a context length of 131,072 tokens, with input priced at $0.04 and output at $0.05 per million tokens. This is an open-weight model.

  • structured outputs
  • open-weight

At a glance

providergoogle
releasedMar 12, 2025
context131K
input / M$0.040

Specifications

What the API gives you

Context window
131K tokens
Max output
118K tokens
Input price
$0.040 / 1M tokens
Output price
$0.050 / 1M tokens
Cache read
$0.020 / 1M tokens
Modalities
text, image → text
Knowledge cutoff
Aug 31, 2024
Released
Mar 12, 2025

Measured evidence

Public benchmark record

BFCL
19.6%2026-10-21
FACTS Grounding
38.4%2025-09-03evaluated 2025-09-03
GPQA Diamond (Epoch AI)
23.2% ± 1.92026-08-28evaluated 2026-08-28
LMArena Creative Writing
1270 Elo2026-10-20
LMArena Instruction Following
1239 Elo2026-10-20
LMArena Long Query
1273 Elo2026-10-20
LMArena Math
1239 Elo2026-10-20
LMArena Text
1303 Elo2026-10-20
OTIS Mock AIME (Epoch AI)
7.5% ± 2.82026-08-28evaluated 2026-08-28

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference.

Open-weight model on Hugging Face.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • Best LLM for Logic & Problem SolvingEstablished evidence

    55% of intended weighted task evidence across 2 independent sources. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningEstablished evidence

    44% of intended weighted task evidence across 3 independent sources. 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for Competition MathEstablished evidence

    37% of intended weighted task evidence across 2 independent sources. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Document SummarizationEstablished evidence

    35% of intended weighted task evidence across 2 independent sources. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for SummarizationEstablished evidence

    35% of intended weighted task evidence across 2 independent sources. 5 of 6 configured evaluation feeds currently have results.

  • Best LLM for RAG & Long ContextEstablished evidence

    33% of intended weighted task evidence across 2 independent sources. 5 of 6 configured evaluation feeds currently have results.

Show all 32 tasks
  • Best LLM for JSON & Schema OutputEstablished evidence

    29% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Structured Data ExtractionEstablished evidence

    29% of intended weighted task evidence across 2 independent sources. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Business WritingProvisional evidence

    67% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Marketing CopyProvisional evidence

    67% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Chat & RoleplayProvisional evidence

    67% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Roleplay & CharacterProvisional evidence

    67% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Creative WritingProvisional evidence

    56% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for WritingProvisional evidence

    56% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for a General AssistantProvisional evidence

    41% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from SimpleQA Verified (Epoch AI) or LiveBench Instruction Following. 6 of 6 configured evaluation feeds currently have results.

  • Best LLM for Hermes AgentProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OpenHandsProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for GooseProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for OpenClawProvisional evidence

    40% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or SWE-rebench. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Grounded RAGProvisional evidence

    33% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from CRAG or SimpleQA Verified (Epoch AI). 5 of 7 configured evaluation feeds currently have results.

  • Best Open-Weight LLM for Self-HostingProvisional evidence

    27% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for Tool & Function CallingProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or LMArena Agent Steerability. 6 of 7 configured evaluation feeds currently have results.

  • Best Value LLMProvisional evidence

    25% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for Massive ContextProvisional evidence

    20% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Document or LongBench v2. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for AI AgentsProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Agentic Coding or LMArena Agent. 9 of 9 configured evaluation feeds currently have results.

  • Best LLM for Fast SummariesProvisional evidence

    17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 2 of 3 configured evaluation feeds currently have results.

  • Best LLM for Literary TranslationProvisional evidence

    17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Everyday TranslationProvisional evidence

    17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for TranslationProvisional evidence

    17% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Language. 3 of 4 configured evaluation feeds currently have results.

  • Best LLM for Computer & Browser UseProvisional evidence

    11% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LMArena Agent or OSWorld Verified. 3 of 3 configured evaluation feeds currently have results.

  • Best Cheap LLM for High VolumeProvisional evidence

    10% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 2 of 3 configured evaluation feeds currently have results.

  • Cheapest Capable LLMProvisional evidence

    10% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or Route reliability. 2 of 3 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.