readable AI benchmarks (simplified)

readable AI benchmarks

SpaceXAI

Grok 3 mini Reasoning (high)

reasoning · closed weights · Feb 19, 2025

Grok 3 mini Reasoning (high) has a Quality Score of 34.5, ranking 215th among 551 scored models. Per 1M tokens, pricing is $0.300 input, $0.500 output, and $0.075 cached input. It has a 1M token context window. Its Reliability Score is 46.6, ranking 147th among 553 scored models, above average (total average: 35.6). Its Value Score is 29.7, around average compared with the total Value average of 30.7.

Quality Score34.5coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Score29.7
Factual reliability46.6
Cache Discount75%

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
1M tokens
Weights
closed weights

Token prices USD per 1M tokens

Input
$0.300
Output
$0.500
Cached Input
$0.075
Cache write
not available
Cost per task
not available

Capability

Intelligence
14.6
Coding
not available
Agentic
not available
Omniscience
-6.8
Correct
15.1%
Blended price
$0.163

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 37.0%

Correct 15.1%Incorrect 21.9%Partial / not attempted 63.0%

Artificial Analysis benchmarks

Humanity’s Last Exam
11%
GPQA Diamond
79%
CritPt
1%
AA-Omniscience
47%
AA-LCR
55%

Similar models

Support me! Patreon