The AI arena is free today

Open Superagent

K2 Horizon 3.7B vs Kimi K2-Instruct-0905

K2 Horizon 3.7B and Kimi K2-Instruct-0905 are closely matched at 21.4 and 20.9 on the LLM Stats Score.

Institute of Foundation Models · Moonshot AI · Updated for 2026

Which is better?

K2 Horizon 3.7B and Kimi K2-Instruct-0905 are closely matched on the overall LLM Stats Score at 21.4 and 20.9.

In the 3 individual benchmarks reported for both models, Kimi K2-Instruct-0905 wins 2; this is a narrower head-to-head signal than the composite indexes.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose K2 Horizon 3.7B

  • you want the most recent training data — it shipped Sep 2026

Choose Kimi K2-Instruct-0905

  • you value its reported benchmark strengths — it wins 2 of 3 exact shared results

At a glance

The differences that matter most.

K2 Horizon 3.7B
Institute of Foundation Models
Kimi K2-Instruct-0905
Moonshot AI
Core performance indexes
LLM Stats Score
21.4
#215
20.9
#222
Reasoning
20.2
#217
21.2
#210
Coding
6.4
#220
9.6
#199
Agents
9.7
#152
-4.6
#216
Cost, coverage & limits
Benchmark wins
1 of 3
2 of 3
Input price
— / M
— / M
Output price
— / M
— / M
Context window
—
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
K2 Horizon 3.7B
Kimi K2-Instruct-0905
Math
13.3#245
21.4#159
Tool use
8.5#163
5.9#177
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

8 reported for K2 Horizon 3.7B · 29 for Kimi K2-Instruct-0905

3 shared

K2 Horizon 3.7B outperforms in 1 benchmarks (Humanity's Last Exam), while Kimi K2-Instruct-0905 is better at 2 benchmarks (GPQA, SWE-Bench Verified).

Kimi K2-Instruct-0905 shows notably better performance in the majority of benchmarks.

Fri Oct 30 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

996.3B diff

Kimi K2-Instruct-0905 has 996.3B more parameters than K2 Horizon 3.7B, making it 26927.0% larger.

Institute of Foundation Models
K2 Horizon 3.7B
3.7Bparameters
Moonshot AI
Kimi K2-Instruct-0905
1.0Tparameters
3.7B
K2 Horizon 3.7B
1000.0B
Kimi K2-Instruct-0905

License

Usage and distribution terms

K2 Horizon 3.7B is licensed under Apache 2.0, while Kimi K2-Instruct-0905 uses MIT.

License differences may affect how you can use these models in commercial or open-source projects.

K2 Horizon 3.7B

Apache 2.0

Open weights

Kimi K2-Instruct-0905

MIT

Open weights

Release Timeline

When each model was launched

K2 Horizon 3.7B was released on 2026-09-03, while Kimi K2-Instruct-0905 was released on 2025-09-05.

K2 Horizon 3.7B is 12 months newer than Kimi K2-Instruct-0905.

K2 Horizon 3.7B

Sep 3, 2026

1 months ago

12mo newer
Kimi K2-Instruct-0905

Sep 5, 2025

1.1 years ago

Knowledge Cutoff

When training data ends

Neither model specifies a knowledge cutoff date.

Unable to compare the recency of their training data.

No cutoff dates available

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against K2 Horizon 3.7B and Kimi K2-Instruct-0905 side-by-side, then vote on the output you prefer.

K2 Horizon 3.7B
✓ Preferred
Kimi K2-Instruct-0905
Open in Playground

FAQ

Common questions about K2 Horizon 3.7B vs Kimi K2-Instruct-0905.

Which is better, K2 Horizon 3.7B or Kimi K2-Instruct-0905?

K2 Horizon 3.7B and Kimi K2-Instruct-0905 are closely matched on the LLM Stats Score at 21.4 and 20.9. K2 Horizon 3.7B is made by Institute of Foundation Models and Kimi K2-Instruct-0905 is made by Moonshot AI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does K2 Horizon 3.7B compare to Kimi K2-Instruct-0905 in benchmarks?

K2 Horizon 3.7B scores HMMT Feb 26: 75.2%, GPQA: 68.9%, SWE-Bench Verified: 65.6%, BFCL-V4: 64.6%, Terminal-Bench 2.1: 39.7%. Kimi K2-Instruct-0905 scores MATH-500: 97.4%, MMLU-Redux: 92.7%, IFEval: 89.8%, AutoLogi: 89.5%, MMLU: 89.5%.

What are the main differences between K2 Horizon 3.7B and Kimi K2-Instruct-0905?

Key differences include LLM Stats Score (21.4 vs 20.9), licensing (Apache 2.0 vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes K2 Horizon 3.7B and Kimi K2-Instruct-0905?

K2 Horizon 3.7B is developed by Institute of Foundation Models and Kimi K2-Instruct-0905 is developed by Moonshot AI.

Related comparisons