readable AI benchmarks (simplified)

readable AI benchmarks

OpenAI

GPT-6 Sol (medium)

reasoning · closed weights · Sep 22, 2026

GPT-6 Sol (medium) has a Quality Score of 59.5, ranking 35th 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 has a 872k token context window. Its Reliability Score is 63.5, ranking 30th among 282 scored models, above average (total average: 36.9). Its Value Score is 37.3, high compared with the total Value average of 30.3.

Quality Score59.5coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1
Value Score37.3
Reliability63.5
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
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
$0.248

Capability

Intelligence
39.8
Coding
not available
Agentic
not available
Omniscience
27.0
Correct
53.4%
Blended price
$1.54

Answer outcomes

Attempt rate: 79.9%

Correct 53.4%Incorrect 26.4%Abstained 20.1%

Artificial Analysis benchmarks

GDPval-AA v2
41%
SciCode
54%
Humanity’s Last Exam
41%
CritPt
25%
AA-Omniscience
64%
AA-LCR
82%

Similar models

Support me! Ko-Fi