readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-6 Sol (max)

reasoning · closed weights · Sep 22, 2026

GPT-6 Sol (max) has a Quality Score of 63.3, ranking 21st among 282 scored models. Per 1M tokens, pricing is $2.00 input, $10.00 output, $0.200 cached input, and $2.50 cache write. It accepts text, image, and pdf input, outputs text, and has a 872k token context window. Its Reliability Score is 63.6, ranking 29th among 282 scored models, above average (total average: 36.9). Its Value Score is 42.2, high compared with the total Value average of 30.3.

Quality Score63.3coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1
Value Score42.2
Reliability63.6
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
text, image, pdf
Output modalities
text
Context window
872k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$2.00
Output
$10.00
Cached Input
$0.200
Cache write
$2.50
Cost per task
$1.06

Capability

Intelligence
47.5
Coding
not available
Agentic
not available
Omniscience
27.1
Correct
54.5%
Blended price
$1.54

Answer outcomes

Attempt rate: 81.8%

Correct 54.5%Incorrect 27.4%Abstained 18.2%

Artificial Analysis benchmarks

GDPval-AA v2
49%
SciCode
58%
Humanity’s Last Exam
48%
CritPt
31%
AA-Omniscience
64%
AA-LCR
84%

Similar models

Support me! Ko-Fi