readable AI benchmarks

OpenAI

GPT-5.6 Terra (medium)

reasoning · closed weights · Jul 9, 2026

Quality Score55.6
Value Score37.9
Reliability47.4
Cache Discount90%

Model specification

Reasoning
reasoning
Input modalities
text, image
Output modalities
text
Context window
1M tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$2.00
Output
$12.00
Cached Input
$0.200
Cached Output
$2.50
Cost per task
$0.119

Capability

Intelligence
46.8
Coding
64.7
Agentic
39.1
Omniscience
-5.1
Correct
44.6%
Blended price
$1.74

Answer outcomes

Correct 44.6%Incorrect 49.7%Abstained 5.7%

Artificial Analysis benchmarks

GDPval-AA v2
45%
τ³-Banking
26%
Terminal-Bench v2.1
72%
SciCode
50%
Humanity’s Last Exam
33%
GPQA Diamond
87%
CritPt
17%
AA-Omniscience
47%
AA-LCR
70%

Similar models