readable AI benchmarks (simplified)

readable AI benchmarks

MBZUAI Institute of Foundation Models

K2 Horizon 3.7B

reasoning · open weights · release date not listed

K2 Horizon 3.7B has a Quality Score of 15.5, ranking 159th among 295 scored models. It has a 524,288 token context window. Its Reliability Score is 35.7, ranking 139th among 295 scored models, above average (total average: 35.6).

Quality Score15.5coverage 78.8%: missing Epoch General ECI, Coding, CursorBench 3.2, Agentic and DeepSWE v1.1
Value Scorenot available
Reliability35.7
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
16.2
Coding
not available
Agentic
not available
Omniscience
-28.6
Correct
10.8%
Blended price
not available

Answer outcomes

Attempt rate: 50.1%

Correct 10.8%Incorrect 39.4%Abstained 49.8%

Artificial Analysis benchmarks

GDPval-AA v2
23%
τ³-Banking
20%
Terminal-Bench v2.1
28%
SciCode
22%
Humanity’s Last Exam
14%
GPQA Diamond
69%
CritPt
0%
AA-Omniscience
36%
AA-LCR
62%

Similar models