BenchLeader
Institute of Foundation ModelsOpen weightsReasoning modelNewFirst measured 18 Sept 2026

K2 Horizon 0.9B

K2 Horizon 0.9B is an Institute of Foundation Models open-weights reasoning model. It is not yet ranked: 3 independent results so far, and the index needs at least five across two categories.

Blended price
Output speed
First answer
Context
131k
Released
date not published by our sources
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Knowledge30
  2. Long context28
  3. Composite33

Benchmark results

One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

BenchmarkdefaultSource
GPQA Diamond (AA)not in index29.3%#511Artificial Analysis
Humanity's Last Exam (AA)not in index5.4%#367Artificial Analysis

Coding

BenchmarkdefaultSource
SciCode (AA)not in index6.9%#174Artificial Analysis

Knowledge

BenchmarkdefaultSource
AA-Omniscience-72.8#461Artificial Analysis

Long context

BenchmarkdefaultSource
AA-LCR6.3%#418Artificial Analysis

Composite

BenchmarkdefaultSource
AA Intelligence Index3.0#562Artificial Analysis

See also

Data as of 18 Sept 2026. Compare with another model.

Cite as: BenchLeader, “K2 Horizon 0.9B: benchmarks, pricing, speed and rank”, https://www.benchleader.com/models/k2-horizon-0-9b, data as of 18 Sept 2026.