readable AI benchmarks (simplified)

readable AI benchmarks

Institute of Foundation Models

K2 Horizon 32B

reasoning · open weights · Sep 3, 2026

K2 Horizon 32B has a Quality Score of 29.1, ranking 192nd among 283 scored models. It has a 524,288 token context window. Its Reliability Score is 44.2, ranking 181st among 288 scored models, below average (total average: 48.2).

Quality Score29.1coverage 100.0%: AA Intelligence and AA-Omniscience outcomes available
Value Scorenot available
Factual reliability44.2
Cache Discountnot available

Model specification

Reasoning
reasoning
Input modalities
none
Output modalities
none
Context window
524,288 tokens
Weights
open weights

Token prices USD per 1M tokens

Input
not available
Output
not available
Cached Input
not available
Cache write
not available
Cost per task
not available

Capability

Intelligence
13.9
Omniscience (native net)
-11.5
Correct
16.5%
Blended price
not available

Answer outcomes

Fully graded outcomes (Correct + Incorrect): 44.5%

Correct 16.5%Incorrect 28.0%Partial / not attempted 55.5%

Artificial Analysis benchmarks aa-v5

Current Intelligence Index components

AA-Briefcase v1.1
1174.8 Elo
AutomationBench-AA
29.4%
private 657-task split from dataset v1.0.6
GDP.pdf
3.8%
FrontierCode v2.0
2.3%
AA Stirrup · 132 tasks, 3 attempts per task
Terminal-Bench v4.0
0.5%
AA mini-swe-agent standardized runs · 66 tasks, pass@1 averaged over 3 repeats per task
AA-Omniscience v1.1
-11.5 native net
HLE-Diamond
8.0%
CritPt v2 Hard
10.0%
AA Stirrup · hard subset, 40 of 70 problems
Terminal-Bench-Science v0.1.0
0.0%

Similar models

Support me! Patreon