Back
FR

Institute of Foundation Models

K2 Horizon 7B

ReasoningOpen weights
Intelligence
20.6
Rank 247 of 768 measured models
Coding
38.6
Rank 160 of 299 measured models
Context window
524K
Rank 589 of 1296 measured models

K2 Horizon 7B scores 20.6 on the Artificial Analysis Intelligence Index, ranking 247th of 768 measured models. The closest models on this index are Claude 4.5 Sonnet (20.7), GPT-5.4 nano (20.7), and GPT-5 mini (20.6).

Artificial Analysis Indices
Intelligence20.6
Rank 247 of 768 measured models
Coding38.6
Rank 160 of 299 measured models
Agentic26.1
Rank 81 of 190 measured models
Capability indexes
Performance in specific industries, measured by Artificial Analysis
Finance & Accounting21.1
Rank 175 of 241 measured models
Strategy & Ops20.3
Rank 161 of 241 measured models
Legal22.8
Rank 171 of 241 measured models
Engineering24.3
Rank 160 of 240 measured models
Economics31.3
Rank 153 of 248 measured models
Standard Benchmarks
GPQA Diamond75.3%
Rank 265 of 620 measured models
HLE18.2%
Rank 254 of 681 measured models
SciCode27.5%
Rank 232 of 248 measured models
AA-LCR69.7%
Rank 238 of 592 measured models
Terminal-Bench 2.144.2%
Rank 137 of 245 measured models
Terminal-Bench 4.01.0%
Rank 144 of 240 measured models
τ-Bench Banking27.6%
Rank 78 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