AI Benchmark Model
K2 Horizon 3.7B
Benchmark scores, pricing, speed, and model comparisons for K2 Horizon 3.7B.
Key scores
The K2 Horizon 3.7B is a language model developed by the Institute of Foundation Models and released on September 3, 2026. This model features an intelligence index of 16.2 and a coding index of 26.1, while its math index remains unknown. Regarding performance metrics, the output speed and time to first token are currently unspecified. The model is available at no cost, with input, output, and blended pricing all listed at $0.00 per million tokens. Benchmark results for the K2 Horizon 3.7B include a GPQA score of 0.692, an HLE score of 0.139, a SciCode score of 0.22, and an LCR score of 0.623333333333333.
Benchmark results
4 tracked benchmark rows for K2 Horizon 3.7B.
GPQA Reasoning
69.2% LCR Other
62.3% SciCode Other
22.0% HLE Other
13.9%