GGemma 4 31B
gemma family · launched 2026-04-02
MultimodalReasoningToolsStructuredOpen weightsLargest Gemma 4 instruction model for open, self-hosted chat and reasoning
What this model supports
Strengths by domain
Every result has a source
Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.
Coding1 results
LiveBench 2.0 · CodingLiveBench49.00 scoreReading 49.0
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0Open evidenceResearch & reasoning1 results
LiveBench 2.0 · ResearchLiveBench68.30 scoreReading 68.3
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0Open evidenceProfessional work1 results
LiveBench 2.0 · ProfessionalLiveBench30.60 scoreReading 30.6
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Professional = long-agentic, browser, data-analysis and design average.
Configuration: LiveBench 2.0Open evidenceKnowledge & instruction1 results
LiveBench 2.0 · KnowledgeLiveBench44.40 scoreReading 44.4
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Knowledge uses the published LiveBench research suite.
Configuration: LiveBench 2.0Open evidenceHuman preference & indices3 results
AA IndexArtificial Analysis64.02 indexReading 55.4
Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0Open evidenceArena TextLMArena1,443.0 EloReading 48.4
Direct LMArena text leaderboard result.
Open evidenceLiveBenchLiveBench40.59 scoreReading 40.6
Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.
Configuration: LiveBench 2.0Open evidence