readable AI benchmarks (simplified)

readable AI benchmarks

Google

Gemma 3 4B Instruct

non-reasoning · open weights · Mar 12, 2025

Gemma 3 4B Instruct has a Quality Score of 8.0, ranking 546th among 551 scored models. Per 1M tokens, pricing is $0.0000 input and $0.0000 output. It has a 128k token context window. Its Reliability Score is 8.6, ranking 547th among 553 scored models, below average (total average: 35.6).

Quality Score8.0coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability8.6
Cache Discountnot available

Model specification

Reasoning
non-reasoning
Input modalities
none
Output modalities
none
Context window
128k tokens
Weights
open weights

Token prices USD per 1M tokens

Input
$0.0000
Output
$0.0000
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
4.8
Coding
not available
Agentic
not available
Omniscience
-82.9
Correct
7.7%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 98.4%

Correct 7.7%Incorrect 90.6%Partial / not attempted 1.6%

Artificial Analysis benchmarks

τ³-Banking
0%
Humanity’s Last Exam
5%
GPQA Diamond
29%
CritPt
0%
AA-Omniscience
9%
AA-LCR
7%

Similar models

Support me! Patreon