readable AI benchmarks (simplified)

readable AI benchmarks

Google

Gemini 4 Neon (High)

reasoning · closed weights · Nov 18, 2026

Gemini 4 Neon (High) has a Quality Score of 68.3, ranking 8th among 283 scored models. Per 1M tokens, pricing is $3.00 input, $15.00 output, $0.150 cached input, and $3.00 cache write. It has a 1M token context window. Its Reliability Score is 76.9, ranking 7th among 288 scored models, above average (total average: 48.2). Its Value Score is 43.4, high compared with the total Value average of 29.3.

Quality Score68.3coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score43.4
Factual reliability76.9
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
$3.00
Output
$15.00
Cached Input
$0.150
Cache write
$3.00
Cost per task
$3.74

Capability

Intelligence
59.6
Omniscience (native net)
53.8
Correct
59.4%
Blended price
$2.21

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 65.0%

Correct 59.4%Incorrect 5.6%Partial / not attempted 35.0%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1
1632.0 Elo
AutomationBench-AA
79.2%
private 657-task split from dataset v1.0.6
GDP.pdf
33.4%
FrontierCode v2.0
43.3%
AA Stirrup · 132 tasks, 3 attempts per task
Terminal-Bench v4.0
61.6%
AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
AA-Omniscience v1.1
53.8 native net
HLE-Diamond
68.4%
CritPt v2 Hard
59.0%
AA Stirrup · hard subset, 40 of 70 problems
Terminal-Bench-Science v0.1.0
65.7%

Similar models

Support me! Patreon