Skip to content
VECTOR WIREAI INTELLIGENCE
UTC

K2 Horizon 3.7B

Score basis

K2 Horizon 3.7B is behind the leaders in long context, factuality, agentic tasks, and coding. Too few results yet to rate reasoning, safety, math, multimodal tasks, multilingual tasks, or instruction following.

Capability profile

Bars show the model's median result as a share of the leading model's, per capability. Select a row to see its results.

Limited4 capabilities
  1. Long Context−30.7%1 of 3
  2. Factuality−38.5%2 of 4
  3. Agentic−41.2%3 of 7
  4. Coding−44.8%2 of 10
Not rated6 capabilities

Too few results yet to rate Reasoning, Safety, Math, Multimodal, Multilingual or Instruction Following.

Price

No current price is tracked for this model. See the rate card

Evidence

13results on13benchmarks

  • 13 aggregator

From 1 source · latest Oct 8, 2026 · How verification works

K2 Horizon 3.7B benchmark results

13 results on 13 benchmarks, grouped by capability. Each bar is the result as a share of the capability leader's; every result links to its source.

Long Context

LimitedFull long context ranking

30.7% behind the leader1 of 3 ranked benchmarks measured

Factuality

LimitedFull factuality ranking

38.5% behind the leader2 of 4 ranked benchmarks measured

Agentic

LimitedFull agentic ranking

41.2% behind the leader3 of 7 ranked benchmarks measured

Coding

LimitedFull coding ranking

44.8% behind the leader2 of 10 ranked benchmarks measured

Reasoning

Not enough dataFull reasoning ranking

0 of 6 ranked benchmarks measured

More results

Benchmarks outside the capability baskets. They are not ranked against a leader.

K2 Horizon 3.7B: common questions

Who makes K2 Horizon 3.7B?

K2 Horizon 3.7B is made by MBZUAI.

When was K2 Horizon 3.7B released?

K2 Horizon 3.7B was released on Sep 3, 2026, according to Artificial Analysis.

What is K2 Horizon 3.7B good at?

K2 Horizon 3.7B is behind the leaders in long context, factuality, agentic tasks, and coding. Too few results yet to rate reasoning, safety, math, multimodal tasks, multilingual tasks, or instruction following.

How many benchmarks has K2 Horizon 3.7B been tested on?

We track 13 results for K2 Horizon 3.7B on 13 benchmarks from 1 source. The latest was recorded on Oct 8, 2026.

About this record

Where K2 Horizon 3.7B's numbers come from, and every name it appears under.

Tracked since
Sep 15, 2026
Newest source mention
Sep 23, 2026

Where the results come from

Verification: 13 scores · 0 independently verified · 13 aggregator-attributed. How these tiers are assigned

From 1 source on 1 site. Artificial Analysis supplies all of them. Bars are coloured by trust tier.

  • artificialanalysis.ai13

Also known as

k2-horizon-3.7b-gguf