Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
Codesota · Models · Gemma 3 (27B, IT)6 results · 6 benchmarks
Model card

Gemma 3 (27B, IT).

unknown
§ 02 · Benchmarks

Every benchmark Gemma 3 (27B, IT) has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01SimpleQANatural Language Processing · Question Answeringaccuracy10.0%#7/7source ↗
02MMMUMultimodal · Visual Question Answeringaccuracy64.9%#18/30source ↗
03MMMUMultimodal · Image-Text-to-Textaccuracy64.9%#19/36source ↗
04LiveCodeBenchComputer Code · Code Generationpass-129.7%#24/24source ↗
05MMLU-ProReasoning · Commonsense Reasoningaccuracy67.5%#67/73source ↗
06GPQA DiamondReasoning · Multi-step Reasoningaccuracy42.4%#70/74source ↗
Rank column shows this model’s position vs all other models scored on the same benchmark + metric (competitors after the slash). #1 in red means current SOTA. Sorted by rank, then newest result.
§ 03 · Strengths by area

Where Gemma 3 (27B, IT) actually performs.

Natural Language Processing
1
benchmark
avg rank #7.0
Multimodal
2
benchmarks
avg rank #18.5
Computer Code
1
benchmark
avg rank #24.0
Reasoning
2
benchmarks
avg rank #68.5
§ 04 · Papers

1 paper with results for Gemma 3 (27B, IT).

  1. 2025-03-25· 6 results

    Gemma 3 Technical Report

§ 06 · Sources & freshness

Where these numbers come from.

pwc-dump
6
results
0 of 6 rows marked verified.