K2 Horizon 32B (Reasoning)

by Institute of Foundation Models

K2 Horizon 32B (Reasoning) is a reasoning model from Institute of Foundation Models, released on September 3, 2026. It ranks #97 of 247 models by Intelligence Score with a score of 30.3.

K2 Horizon 32B is the large dense member of IFM's (MBZUAI) fully open K2 Horizon family: a 32B-class decoder-only reasoning model (64 layers, 250K vocabulary; about 34.8B parameters in the released safetensors) pretrained on 22.9T tokens, with a native 524,288-token (512K) context window from midtraining onward. Text in, text out, with per-request reasoning effort (high recommended) and JSON/XML tool-call formats. Released 2026-09-03 under Apache 2.0; the main branch was updated on 2026-10-01 to a later SFT checkpoint and its model-card scores were refreshed on 2026-10-07 (they are higher than the launch-blog figures). BF16 weights plus FP8, NVFP4, and GGUF builds, with intermediate checkpoints, training data, code, and logs. No priced provider is cataloged yet.

Key specs

ProviderInstitute of Foundation Models
Release date2026-09-03
Licenseopen source
Intelligence Score30.3
Coding index13.1

Quick answers

Is K2 Horizon 32B (Reasoning) open source?

Yes. K2 Horizon 32B (Reasoning) is an open model released under the open source license.

When was K2 Horizon 32B (Reasoning) released?

Institute of Foundation Models released K2 Horizon 32B (Reasoning) on September 3, 2026.

How does K2 Horizon 32B (Reasoning) compare to Claude Opus 5.5 (Reasoning)?

K2 Horizon 32B (Reasoning) scores 30.3 on the Intelligence Score versus 59.9 for Claude Opus 5.5 (Reasoning), the current #1.

Compare on the AI leaderboard · All AI models

More models from Institute of Foundation Models