AI Benchmark Model

K2 Horizon 375B A23B

Benchmark scores, pricing, speed, and model comparisons for K2 Horizon 375B A23B.

Key scores

Intelligence47.3Index score
Coding61.5Index score

The K2 Horizon 375B A23B is a large language model developed by the MBZUAI Institute of Foundation Models, released on September 3, 2026. This model is currently listed with an intelligence index of 47.3 and a coding index of 61.5, while its math index remains unknown. Performance metrics for output speed and time to first token are also not available. The model is provided at no cost, with input, output, and blended pricing all set at 0.00 dollars per million tokens. Benchmark results for the K2 Horizon 375B A23B include a GPQA score of 0.873, an HLE score of 0.32, a SciCode score of 0.407, and an LCR score of approximately 0.757.

Benchmark results

4 tracked benchmark rows for K2 Horizon 375B A23B.

GPQA Reasoning
87.3%
LCR Other
75.7%
SciCode Other
40.7%
HLE Other
32.0%

Comments (0)

No comments yet

Be the first to share your thoughts!