K2 Horizon 3.7B

Institute of Foundation Models

K2 Horizon 3.7B is the small dense member of IFM's (MBZUAI) fully open K2 Horizon family: a 3.7B-core decoder-only reasoning model (36 layers; about 5.1B parameters in the released safetensors including its 250K-token vocabulary embeddings) 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; on 2026-10-01 the main branch was updated to an anti-doom-loop (FTPO) checkpoint, and the model-card scores were refreshed on 2026-10-28 (they differ from the launch-blog figures). BF16 weights plus a GGUF build, intermediate checkpoints, training data, code, and logs. No priced provider is cataloged yet.

Key Specifications

Parameters
3.7B
Context
-
Release Date
September 3, 2026
Average Score
46.4%

Timeline

Key dates in the model's history
Announcement
September 3, 2026
Last Update
October 31, 2026
Today
November 20, 2026

Technical Specifications

Parameters
3.7B
Training Tokens
22.9T tokens
Knowledge Cutoff
-
Family
-
Capabilities
MultimodalZeroEval

Benchmark Results

Model performance metrics across various tests and benchmarks

Programming

Programming skills tests
SWE-Bench Verified
IFM K2-Horizon-3.7B Hugging Face model card, final checkpoint; reasoning_effort=high, temperature=1.0, top_p=0.95 • Self-reported
65.6%

Reasoning

Logical reasoning and analysis
GPQA
IFM K2-Horizon-3.7B Hugging Face model card, final checkpoint; reasoning_effort=high, temperature=1.0, top_p=0.95; GPQA Diamond • Self-reported
68.9%

Other Tests

Specialized benchmarks
BFCL-V4
IFM K2-Horizon-3.7B Hugging Face model card, final checkpoint; reasoning_effort=high, temperature=1.0, top_p=0.95 • Self-reported
64.6%
HMMT Feb 26
IFM K2-Horizon-3.7B Hugging Face model card, final checkpoint; reasoning_effort=high, temperature=1.0, top_p=0.95; HMMT Feb 2026 • Self-reported
75.2%
Humanity's Last Exam
IFM K2-Horizon-3.7B Hugging Face model card, final checkpoint; reasoning_effort=high, temperature=1.0, top_p=0.95; without tools • Self-reported
14.0%
SciCode
IFM K2-Horizon-3.7B Hugging Face model card, final checkpoint; reasoning_effort=high, temperature=1.0, top_p=0.95 • Self-reported
25.8%
Tau3 Banking
IFM K2-Horizon-3.7B Hugging Face model card, final checkpoint; reasoning_effort=high, temperature=1.0, top_p=0.95 • Self-reported
17.7%
Terminal-Bench 2.1
IFM K2-Horizon-3.7B Hugging Face model card, final checkpoint; reasoning_effort=high, temperature=1.0, top_p=0.95 • Self-reported
39.7%

License & Metadata

License
apache_2_0
Announcement Date
September 3, 2026
Last Updated
October 31, 2026

Similar Models

All Models

Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.