readable AI benchmarks (simplified)

readable AI benchmarks

Google

Gemma 3 12B Instruct

non-reasoning · open weights · Mar 12, 2025

Gemma 3 12B Instruct has a Quality Score of 8.6, ranking 541st 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 11.5, ranking 531st among 553 scored models, below average (total average: 35.6).

Quality Score8.6coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability11.5
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
$0.0000

Capability

Intelligence
3.8
Coding
not available
Agentic
not available
Omniscience
-77.1
Correct
10.3%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 97.7%

Correct 10.3%Incorrect 87.4%Partial / not attempted 2.3%

Artificial Analysis benchmarks

GDPval-AA v2
0%
τ³-Banking
1%
SciCode
16%
Humanity’s Last Exam
4%
GPQA Diamond
35%
CritPt
0%
AA-Omniscience
11%
AA-LCR
8%

Similar models

Support me! Patreon