readable AI benchmarks (simplified)

readable AI benchmarks

Google

Gemini 4 Hydrogen (Low)

reasoning · closed weights · Nov 12, 2026

Gemini 4 Hydrogen (Low) has a Quality Score of 47.5, ranking 79th among 283 scored models. Per 1M tokens, pricing is $1.50 input, $7.50 output, and $0.075 cached input. It has a 1M token context window. Its Reliability Score is 68.0, ranking 44th among 288 scored models, above average (total average: 48.2). Its Value Score is 32.8, around average compared with the total Value average of 29.3.

Quality Score47.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score32.8
Factual reliability68.0
Cache Discount95%

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
1M tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$1.50
Output
$7.50
Cached Input
$0.075
Cache write
not available
Cost per task
$0.292

Capability

Intelligence
26.9
Omniscience (native net)
36.1
Correct
46.2%
Blended price
$1.10

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 56.4%

Correct 46.2%Incorrect 10.1%Partial / not attempted 43.6%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1
947.6 Elo
AutomationBench-AA
60.5%
private 657-task split from dataset v1.0.6
GDP.pdf
28.2%
FrontierCode v2.0
9.3%
AA Stirrup · 132 tasks, 3 attempts per task
Terminal-Bench v4.0
6.6%
AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
AA-Omniscience v1.1
36.1 native net
HLE-Diamond
32.2%
CritPt v2 Hard
48.0%
AA Stirrup · hard subset, 40 of 70 problems
Terminal-Bench-Science v0.1.0
2.4%

Similar models

Support me! Patreon