The AI arena is free today

Open Superagent

K2 Horizon 32B vs MAI-Code-1.1-Flash

K2 Horizon 32B and MAI-Code-1.1-Flash are closely matched at 30.2 and 27.4 on the LLM Stats Score.

Institute of Foundation Models · Microsoft · Updated for 2026

Which is better?

K2 Horizon 32B and MAI-Code-1.1-Flash are closely matched on the overall LLM Stats Score at 30.2 and 27.4.

In the 1 individual benchmarks reported for both models, MAI-Code-1.1-Flash wins 1; 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 32B

  • you want the most recent training data — it shipped Sep 2026
  • you need open weights you can self-host or fine-tune

Choose MAI-Code-1.1-Flash

  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results

At a glance

The differences that matter most.

K2 Horizon 32B
Institute of Foundation Models
MAI-Code-1.1-Flash
Microsoft
Core performance indexes
LLM Stats Score
30.2
#147
27.4
#170
Reasoning
30.0
#147
27.3
#165
Coding
12.9
#167
18.7
#135
Agents
14.2
#120
11.4
#139
Cost, coverage & limits
Benchmark wins
0 of 1
1 of 1
Input price
— / M
$0.20 / M
Output price
— / M
$1.20 / M
Context window
—
256,000

Individual benchmarks

9 reported for K2 Horizon 32B · 2 for MAI-Code-1.1-Flash

1 shared

K2 Horizon 32B outperforms in 0 benchmarks, while MAI-Code-1.1-Flash is better at 1 benchmark (Terminal-Bench 2.1).

MAI-Code-1.1-Flash significantly outperforms across most benchmarks.

Fri Oct 30 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

106.0B diff

MAI-Code-1.1-Flash has 106.0B more parameters than K2 Horizon 32B, making it 331.3% larger.

Institute of Foundation Models
K2 Horizon 32B
32.0Bparameters
Microsoft
MAI-Code-1.1-Flash
138.0Bparameters
32.0B
K2 Horizon 32B
138.0B
MAI-Code-1.1-Flash

Context Window

Maximum input and output token capacity

Only MAI-Code-1.1-Flash specifies input context (256,000 tokens).

Institute of Foundation Models
K2 Horizon 32B
Input- tokens
Output- tokens
Microsoft
MAI-Code-1.1-Flash
Input256,000 tokens
Output- tokens
Fri Oct 30 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

MAI-Code-1.1-Flash supports multimodal inputs, whereas K2 Horizon 32B does not.

MAI-Code-1.1-Flash can handle both text and other forms of data like images, making it suitable for multimodal applications.

K2 Horizon 32B

Text
Images
Audio
Video

MAI-Code-1.1-Flash

Text
Images
Audio
Video

License

Usage and distribution terms

K2 Horizon 32B is licensed under Apache 2.0, while MAI-Code-1.1-Flash uses a proprietary license.

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

K2 Horizon 32B

Apache 2.0

Open weights

MAI-Code-1.1-Flash

Proprietary

Closed source

Release Timeline

When each model was launched

K2 Horizon 32B was released on 2026-09-03, while MAI-Code-1.1-Flash was released on 2026-08-11.

K2 Horizon 32B is 1 month newer than MAI-Code-1.1-Flash.

K2 Horizon 32B

Sep 3, 2026

1 months ago

3w newer
MAI-Code-1.1-Flash

Aug 11, 2026

2 months 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 32B and MAI-Code-1.1-Flash side-by-side, then vote on the output you prefer.

K2 Horizon 32B
✓ Preferred
MAI-Code-1.1-Flash
Open in Playground

FAQ

Common questions about K2 Horizon 32B vs MAI-Code-1.1-Flash.

Which is better, K2 Horizon 32B or MAI-Code-1.1-Flash?

K2 Horizon 32B and MAI-Code-1.1-Flash are closely matched on the LLM Stats Score at 30.2 and 27.4. K2 Horizon 32B is made by Institute of Foundation Models and MAI-Code-1.1-Flash is made by Microsoft. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does K2 Horizon 32B compare to MAI-Code-1.1-Flash in benchmarks?

K2 Horizon 32B scores GPQA: 82.8%, OmniScience (non-hallucination rate): 69.7%, AA-LCR: 68.0%, Terminal-Bench 2.1: 62.6%, SciCode: 37.9%. MAI-Code-1.1-Flash scores SWE-Bench Verified: 72.6%, Terminal-Bench 2.1: 62.9%.

What are the context window sizes for K2 Horizon 32B and MAI-Code-1.1-Flash?

K2 Horizon 32B supports an unknown number of tokens and MAI-Code-1.1-Flash supports 256K tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between K2 Horizon 32B and MAI-Code-1.1-Flash?

Key differences include LLM Stats Score (30.2 vs 27.4), multimodal support (no vs yes), licensing (Apache 2.0 vs Proprietary). See the full comparison above for benchmark-by-benchmark results.

Who makes K2 Horizon 32B and MAI-Code-1.1-Flash?

K2 Horizon 32B is developed by Institute of Foundation Models and MAI-Code-1.1-Flash is developed by Microsoft.

Related comparisons