The AI arena is free today

Open Superagent

Gemini 2.5 Flash vs K2 Horizon 32B

K2 Horizon 32B leads the LLM Stats Score 30.2 to 21.1.

Google · Institute of Foundation Models · Updated for 2026

Which is better?

K2 Horizon 32B leads the overall LLM Stats Score 30.2 to 21.1, ranking #147 overall.

In the 2 individual benchmarks reported for both models, K2 Horizon 32B 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 Gemini 2.5 Flash

  • you want predictable pricing at $0.30/M input and $2.50/M output

Choose K2 Horizon 32B

  • overall performance matters — it scores 30.2 and ranks #147 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 2 of 2 exact shared results
  • you want the most recent training data — it shipped Sep 2026
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Gemini 2.5 Flash
Google
K2 Horizon 32B
Institute of Foundation Models
Core performance indexes
LLM Stats Score
21.1
#221
30.2
#147
Reasoning
20.7
#215
30.0
#147
Coding
8.1
#211
12.9
#167
Cost, coverage & limits
Benchmark wins
0 of 2
2 of 2
Input price
$0.30 / M
— / M
Output price
$2.50 / M
— / M
Context window
1,000,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Gemini 2.5 Flash
K2 Horizon 32B
Math
15.8#226
22.2#152
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

14 reported for Gemini 2.5 Flash · 9 for K2 Horizon 32B

2 shared

Gemini 2.5 Flash outperforms in 0 benchmarks, while K2 Horizon 32B is better at 1 benchmark (Humanity's Last Exam).

K2 Horizon 32B has a slight edge in benchmark performance.

Fri Oct 30 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Gemini 2.5 Flash specifies input context (1,000,000 tokens). Only Gemini 2.5 Flash specifies output context (1,000,000 tokens).

Google
Gemini 2.5 Flash
Input1,000,000 tokens
Output1,000,000 tokens
Institute of Foundation Models
K2 Horizon 32B
Input- tokens
Output- tokens
Fri Oct 30 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Gemini 2.5 Flash supports multimodal inputs, whereas K2 Horizon 32B does not.

Gemini 2.5 Flash can handle both text and other forms of data like images, making it suitable for multimodal applications.

Gemini 2.5 Flash

Text
Images
Audio
Video

K2 Horizon 32B

Text
Images
Audio
Video

License

Usage and distribution terms

Gemini 2.5 Flash is licensed under a proprietary license, while K2 Horizon 32B uses Apache 2.0.

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

Gemini 2.5 Flash

Proprietary

Closed source

K2 Horizon 32B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Gemini 2.5 Flash was released on 2025-05-20, while K2 Horizon 32B was released on 2026-09-03.

K2 Horizon 32B is 16 months newer than Gemini 2.5 Flash.

Gemini 2.5 Flash

May 20, 2025

1.4 years ago

K2 Horizon 32B

Sep 3, 2026

1 months ago

1.3yr newer

Knowledge Cutoff

When training data ends

Gemini 2.5 Flash has a documented knowledge cutoff of 2025-01-31, while K2 Horizon 32B's cutoff date is not specified.

We can confirm Gemini 2.5 Flash's training data extends to 2025-01-31, but cannot make a direct comparison without K2 Horizon 32B's cutoff date.

Gemini 2.5 Flash

Jan 2025

K2 Horizon 32B

—

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Gemini 2.5 Flash and K2 Horizon 32B side-by-side, then vote on the output you prefer.

Gemini 2.5 Flash
✓ Preferred
K2 Horizon 32B
Open in Playground

FAQ

Common questions about Gemini 2.5 Flash vs K2 Horizon 32B.

Which is better, Gemini 2.5 Flash or K2 Horizon 32B?

K2 Horizon 32B leads the LLM Stats Score 30.2 to 21.1. Gemini 2.5 Flash is made by Google and K2 Horizon 32B is made by Institute of Foundation Models. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Gemini 2.5 Flash compare to K2 Horizon 32B in benchmarks?

Gemini 2.5 Flash scores Global-MMLU-Lite: 88.4%, AIME 2024: 88.0%, FACTS Grounding: 85.3%, GPQA: 82.8%, MMMU: 79.7%. 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%.

What are the context window sizes for Gemini 2.5 Flash and K2 Horizon 32B?

Gemini 2.5 Flash supports 1.0M tokens and K2 Horizon 32B supports an unknown number of tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between Gemini 2.5 Flash and K2 Horizon 32B?

Key differences include LLM Stats Score (21.1 vs 30.2), multimodal support (yes vs no), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes Gemini 2.5 Flash and K2 Horizon 32B?

Gemini 2.5 Flash is developed by Google and K2 Horizon 32B is developed by Institute of Foundation Models.

Related comparisons