readable AI benchmarks

OpenAI

GPT-5.6 Terra (high)

reasoning · closed weights · Jul 9, 2026

Quality Score58.6
Value Score40.1
Reliability48.3
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
$0.218

Capability

Intelligence
50.1
Coding
67.1
Agentic
43.5
Omniscience
-3.5
Correct
45.5%
Blended price
$1.74

Answer outcomes

Correct 45.5%Incorrect 48.9%Abstained 5.6%

Artificial Analysis benchmarks

GDPval-AA v2
51%
τ³-Banking
29%
Terminal-Bench v2.1
76%
SciCode
50%
Humanity’s Last Exam
39%
GPQA Diamond
90%
CritPt
23%
AA-Omniscience
48%
AA-LCR
73%

Similar models