readable AI benchmarks (simplified)

readable AI benchmarks

Google

Gemini 4 Argon (Medium)

reasoning · closed weights · Sep 30, 2026

Gemini 4 Argon (Medium) has a Quality Score of 59.1, ranking 36th among 283 scored models. Per 1M tokens, pricing is $2.00 input, $10.00 output, and $0.100 cached input. It has a 1M token context window. Its Reliability Score is 70.5, ranking 30th among 288 scored models, above average (total average: 48.2). Its Value Score is 39.4, high compared with the total Value average of 29.3.

Quality Score59.1coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score39.4
Factual reliability70.5
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
$2.00
Output
$10.00
Cached Input
$0.100
Cache write
not available
Cost per task
$4.31

Capability

Intelligence
47.6
Omniscience (native net)
41.1
Correct
49.0%
Blended price
$1.47

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 56.8%

Correct 49.0%Incorrect 7.9%Partial / not attempted 43.2%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1
1466.6 Elo
AutomationBench-AA
75.8%
private 657-task split from dataset v1.0.6
GDP.pdf
25.6%
FrontierCode v2.0
25.0%
AA Stirrup · 132 tasks, 3 attempts per task
Terminal-Bench v4.0
55.1%
AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
AA-Omniscience v1.1
41.1 native net
HLE-Diamond
42.5%
CritPt v2 Hard
53.5%
AA Stirrup · hard subset, 40 of 70 problems
Terminal-Bench-Science v0.1.0
48.6%

Standalone evaluations

GDPval-AA v2.1
1578.4 Elo

Historical evaluations

SciCode v1.0.1
58.9%
AA Long Context Reasoning v1.1
78.3%
Humanity's Last Exam
49.9%
CritPt
23.1%

Similar models

Support me! Patreon