readable AI benchmarks (simplified)

readable AI benchmarks

SpaceXAI

Grok 4 Fast (Reasoning)

reasoning · closed weights · Sep 19, 2025

Grok 4 Fast (Reasoning) has a Quality Score of 31.3, ranking 245th among 553 scored models. Per 1M tokens, pricing is $0.200 input and $0.500 output. It has a 2M token context window. Its Reliability Score is 35.0, ranking 262nd among 555 scored models, below average (total average: 35.7).

Quality Score31.3coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability35.0
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
2M tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$0.200
Output
$0.500
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
17.9
Coding
not available
Agentic
not available
Omniscience
-29.9
Correct
22.8%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 75.5%

Correct 22.8%Incorrect 52.7%Partial / not attempted 24.5%

Artificial Analysis benchmarks

Humanity’s Last Exam
19%
GPQA Diamond
85%
CritPt
3%
AA-Omniscience
35%
AA-LCR
74%

Similar models

Support me! Patreon