readable AI benchmarks

SpaceXAI

Grok 4.6 (medium)

reasoning · closed weights · Aug 12, 2026

Quality Score70.3
Value Score47.5
Reliability64.0
Cache Discount75%

Model specification

Reasoning
reasoning
Input modalities
text, image
Output modalities
text
Context window
500k tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$2.00
Output
$6.00
Cached Input
$0.500
Cached Output
not available
Cost per task
$0.668

Capability

Intelligence
59.0
Coding
74.4
Agentic
56.3
Omniscience
28.0
Correct
41.9%
Blended price
$1.35

Answer outcomes

Correct 41.9%Incorrect 13.9%Abstained 44.1%

Artificial Analysis benchmarks

GDPval-AA v2
62%
τ³-Banking
44%
Terminal-Bench v2.1
84%
SciCode
55%
Humanity’s Last Exam
42%
GPQA Diamond
94%
CritPt
18%
AA-Omniscience
64%
AA-LCR
73%

Similar models