readable AI benchmarks (simplified)

readable AI benchmarks

Google

Gemini 4 Neon (Medium)

reasoning · closed weights · Nov 18, 2026

Gemini 4 Neon (Medium) has a Quality Score of 65.2, ranking 14th 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 75.5, ranking 9th among 288 scored models, above average (total average: 48.2). Its Value Score is 41.5, high compared with the total Value average of 29.3.

Quality Score65.2coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score41.5
Factual reliability75.5
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
$1.90

Capability

Intelligence
54.9
Omniscience (native net)
51.1
Correct
57.9%
Blended price
$2.21

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 64.8%

Correct 57.9%Incorrect 6.8%Partial / not attempted 35.2%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1
1517.9 Elo
AutomationBench-AA
77.8%
private 657-task split from dataset v1.0.6
GDP.pdf
32.8%
FrontierCode v2.0
36.9%
AA Stirrup · 132 tasks, 3 attempts per task
Terminal-Bench v4.0
54.5%
AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
AA-Omniscience v1.1
51.1 native net
HLE-Diamond
63.6%
CritPt v2 Hard
61.5%
AA Stirrup · hard subset, 40 of 70 problems
Terminal-Bench-Science v0.1.0
54.8%

Similar models

Support me! Patreon