The AI arena is free today

Open Superagent

GPT-Live-1 vs K2 Horizon 375B-A23B

K2 Horizon 375B-A23B significantly outperforms across most benchmarks.

OpenAI · Institute of Foundation Models · Updated for 2026

Which is better?

GPT-Live-1 and K2 Horizon 375B-A23B trade strengths across price, capabilities, and technical limits. The better choice depends on the workload.

In the 1 individual benchmarks reported for both models, K2 Horizon 375B-A23B 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 GPT-Live-1

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

Choose K2 Horizon 375B-A23B

  • you value its reported benchmark strengths — it wins 1 of 1 exact shared results
  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Benchmark wins
0 of 1
1 of 1
Input price
— / M
— / M
Output price
— / M
— / M
Context window
—
—

Individual benchmarks

2 reported for GPT-Live-1 · 18 for K2 Horizon 375B-A23B

1 shared

GPT-Live-1 outperforms in 0 benchmarks, while K2 Horizon 375B-A23B is better at 1 benchmark (Tau3 Banking).

K2 Horizon 375B-A23B significantly outperforms across most benchmarks.

Wed Nov 04 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Input capabilities

Documented input modalities across available providers

GPT-Live-1 supports multimodal inputs, whereas K2 Horizon 375B-A23B does not.

GPT-Live-1 can handle both text and other forms of data like images, making it suitable for multimodal applications.

GPT-Live-1

Text
Images
Audio
Video

K2 Horizon 375B-A23B

Text
Images
Audio
Video

License

Usage and distribution terms

GPT-Live-1 is licensed under a proprietary license, while K2 Horizon 375B-A23B uses Apache 2.0.

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

GPT-Live-1

Proprietary

Closed source

K2 Horizon 375B-A23B

Apache 2.0

Open weights

Release Timeline

When each model was launched

GPT-Live-1 was released on 2026-09-10, while K2 Horizon 375B-A23B was released on 2026-09-03.

GPT-Live-1 is 0 month newer than K2 Horizon 375B-A23B.

GPT-Live-1

Sep 10, 2026

1 months ago

1w newer
K2 Horizon 375B-A23B

Sep 3, 2026

2 months ago

Knowledge Cutoff

When training data ends

GPT-Live-1 has a documented knowledge cutoff of 2025-07-31, while K2 Horizon 375B-A23B's cutoff date is not specified.

We can confirm GPT-Live-1's training data extends to 2025-07-31, but cannot make a direct comparison without K2 Horizon 375B-A23B's cutoff date.

GPT-Live-1

Jul 2025

K2 Horizon 375B-A23B

—

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against GPT-Live-1 and K2 Horizon 375B-A23B side-by-side, then vote on the output you prefer.

GPT-Live-1
✓ Preferred
K2 Horizon 375B-A23B
Open in Playground

FAQ

Common questions about GPT-Live-1 vs K2 Horizon 375B-A23B.

Which is better, GPT-Live-1 or K2 Horizon 375B-A23B?

K2 Horizon 375B-A23B significantly outperforms across most benchmarks. GPT-Live-1 is made by OpenAI and K2 Horizon 375B-A23B 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 GPT-Live-1 compare to K2 Horizon 375B-A23B in benchmarks?

GPT-Live-1 scores TAU3-Bench: 86.2%, Tau3 Banking: 32.0%. K2 Horizon 375B-A23B scores GPQA: 87.3%, AA-LCR: 76.0%, OmniScience (non-hallucination rate): 74.7%, BrowseComp: 72.8%, Terminal-Bench 2.1: 70.2%.

What are the main differences between GPT-Live-1 and K2 Horizon 375B-A23B?

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

Who makes GPT-Live-1 and K2 Horizon 375B-A23B?

GPT-Live-1 is developed by OpenAI and K2 Horizon 375B-A23B is developed by Institute of Foundation Models.