Codesota · Models · Gemma 3Google1 results · 1 benchmarks
Model card

Gemma 3.

Googlevision-languagegemma
§ 02 · Benchmarks

Every benchmark Gemma 3 has a recorded score for.

#BenchmarkArea · TaskMetricValueRankDateSource
01KITAB-BenchComputer Vision · Optical Character Recognitioncer1.1%#9/14—source ↗
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 actually performs.

Computer Vision
1
benchmark
avg rank #9.0
§ 05 · Related models

Other Google models scored on Codesota.

Gemini 1.5 Pro
21 results
Gemini 2.5 Pro
16 results
Gemini 3 Pro
Undisclosed params · 13 results
Gemini-3.1-Pro
11 results
Gemma-3-27b
27B params · 11 results
Gemma 3 (27B, IT)
9 results
Gemma-2-27b-it
9 results
gemma-3-12b-it
9 results
§ 06 · Sources & freshness

Where these numbers come from.

kitab-bench-leaderboard
1
result
1 of 1 rows marked verified.