Back
FR

Institute of Foundation Models

K2 Horizon 0.9B

Intelligence
3.0
Rank 781 of 782 measured models
Coding
3.4
Rank 294 of 301 measured models
Context window
131K
Rank 745 of 1325 measured models

K2 Horizon 0.9B scores 3.0 on the Artificial Analysis Intelligence Index, ranking 781st of 782 measured models. The closest models on this index are Gemma 3 12B Instruct (3.8), gpt-oss-120b (3.8), and North Mini Code (3.4).

Artificial Analysis Indices
Intelligence3.0
Rank 781 of 782 measured models
Coding3.4
Rank 294 of 301 measured models
Agentic0.8
Rank 176 of 191 measured models
Capability indexes
Performance in specific industries, measured by Artificial Analysis
Finance & Accounting3.7
Rank 254 of 254 measured models
Strategy & Ops1.6
Rank 254 of 254 measured models
Legal4.7
Rank 251 of 254 measured models
Engineering6.4
Rank 251 of 253 measured models
Economics7.5
Rank 259 of 261 measured models
Standard Benchmarks
GPQA Diamond29.3%
Rank 586 of 621 measured models
HLE5.4%
Rank 469 of 682 measured models
SciCode6.9%
Rank 249 of 249 measured models
AA-LCR6.3%
Rank 520 of 593 measured models
Terminal-Bench 2.11.1%
Rank 234 of 246 measured models
Terminal-Bench 4.00.0%
Rank 175 of 245 measured models
τ-Bench Banking4.9%
Rank 190 of 211 measured models
Models at a similar level
The closest models on the Intelligence Index, one configuration per family.

Preferences and analytics

Rybbit: visits, performance, clicks, copies, forms and session replay (masked inputs), with your permission. Refusing does not limit the site.

Privacy

Allow navigation analytics?

With your permission, Rybbit measures visits, performance and interactions (clicks, copies, forms), including session replay, to improve BenchSift. Input values are masked in replays. Refusing does not limit the site.

Your choice is stored for 180 days. Change it at any time using “Privacy preferences” in the footer. Withdrawal reloads the page.

No choice stored: Rybbit is disabled.

Privacy