readable AI benchmarks

SpaceXAI

Grok 4.3 (medium)

reasoning · closed weights · Apr 30, 2026

Quality Score48.7
Value Score33.3
Reliability58.4
Cache Discount84%

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
$1.25
Output
$2.50
Cached Input
$0.200
Cached Output
$1.25
Cost per task
not available

Capability

Intelligence
36.9
Coding
not available
Agentic
not available
Omniscience
16.7
Correct
28.8%
Blended price
$0.640

Answer outcomes

Correct 28.8%Incorrect 12.1%Abstained 59.2%

Artificial Analysis benchmarks

SciCode
45%
Humanity’s Last Exam
30%
GPQA Diamond
89%
CritPt
5%
AA-Omniscience
58%
AA-LCR
68%

Similar models