readable AI benchmarks (simplified)

readable AI benchmarks

Google

Gemini 4 Hydrogen (Medium)

reasoning · closed weights · Nov 12, 2026

Gemini 4 Hydrogen (Medium) has a Quality Score of 56.1, ranking 46th 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 71.0, ranking 28th among 288 scored models, above average (total average: 48.2). Its Value Score is 38.8, high compared with the total Value average of 29.3.

Quality Score56.1coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score38.8
Factual reliability71.0
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
$0.798

Capability

Intelligence
41.2
Omniscience (native net)
41.9
Correct
48.3%
Blended price
$1.10

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 54.8%

Correct 48.3%Incorrect 6.4%Partial / not attempted 45.2%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1
1296.8 Elo
AutomationBench-AA
72.0%
private 657-task split from dataset v1.0.6
GDP.pdf
32.8%
FrontierCode v2.0
31.5%
AA Stirrup · 132 tasks, 3 attempts per task
Terminal-Bench v4.0
29.3%
AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
AA-Omniscience v1.1
41.9 native net
HLE-Diamond
47.7%
CritPt v2 Hard
61.0%
AA Stirrup · hard subset, 40 of 70 problems
Terminal-Bench-Science v0.1.0
15.2%

Similar models

Support me! Patreon