Google, released Mar 12, 2025

Gemma 3 4B ITprice, context, benchmarks and release details

Provisional: not enough results to rank yet Open weights 64% confidence, 2 of 7 expected sources in

39.2

SI Score

#128 of 142 ranked models

Input, per 1M tokens: not yet reported
Output, per 1M tokens: not yet reported
Context window: 131K
Max output: 131K
Released: Mar 12, 2025

How the score breaks down

Coding —

Math 7.5

Preference 61.2

Reasoning 23.2

Weights: reasoning 30%, math 15%, coding 40%, preference 15%. Results use fixed 0–100 scales before averaging, and thin evidence is pulled toward 50. Method si-v3-retained-evidence-2, computed Oct 9, 2026, 06:15 UTC.

Around it on the leaderboard

126 Claude Haiku 3 39.9
127 Qwen2.5-Coder-32B-Instruct 39.6
128 Gemma 3 4B IT 39.2
129 GPT-5 Nano 39.1
130 Llama-3.1-8B-Instruct 37.7

Full leaderboard

Benchmark results

3 benchmarks, 3 results

Each row shows the best published result. Where a model was tested at several settings, such as reasoning effort, open the row to see each one. Hover or tap a value for its source.

GPQA Diamondreasoning 23.2% 23.2

OTIS Mock AIME 2024–2025math 7.5% 7.5

LMArena Textpreference 1290.8 elo 61.2

Normalization uses a fixed 0–100 scale for each unit, independent of other models. Compare evaluation conditions before reading a small gap as decisive. “Lab-reported” marks the provider's own published figure.

Details and sources

Open weights: Yes
License: not yet reported
Input modalities: text, image
First seen by SuperIndex: Oct 8, 2026
Coverage: 51% of expected source weight

Reported (2)

Epoch AI BenchmarkingOct 8, 2026
LMArena / ArenaOct 8, 2026

Awaiting (5)

ARC Prize13% of weight
Humanity’s Last Exam13% of weight
Official model cards via models.dev4% of weight
LiveBench13% of weight
Terminal-Bench6% of weight

Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.