The AI arena is free today

Open Superagent

GPT-5.6 Terra vs K2 Horizon 375B-A23B

GPT-5.6 Terra leads the LLM Stats Score 47.8 to 37.6.

OpenAI · Institute of Foundation Models · Updated for 2026

Which is better?

GPT-5.6 Terra leads the overall LLM Stats Score 47.8 to 37.6, ranking #34 overall.

In the 5 individual benchmarks reported for both models, GPT-5.6 Terra wins 4; 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-5.6 Terra

  • overall performance matters — it scores 47.8 and ranks #34 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 4 of 5 exact shared results

Choose K2 Horizon 375B-A23B

  • 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.

Core performance indexes
47.8
#34
37.6
#102
46.1
#38
36.5
#104
36.9
#32
20.0
#135
34.0
#36
22.2
#95
Cost, coverage & limits
Benchmark wins
4 of 5
1 of 5
Input price
$2.00 / M
— / M
Output price
$12.00 / M
— / M
Context window
1,050,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
GPT-5.6 Terra
K2 Horizon 375B-A23B
31.6#75
29.4#98
26.3#46
21.5#76
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

46 reported for GPT-5.6 Terra · 18 for K2 Horizon 375B-A23B

5 shared

GPT-5.6 Terra outperforms in 4 benchmarks (BrowseComp, GPQA, SWE-Bench Pro, Terminal-Bench 2.1), while K2 Horizon 375B-A23B is better at 1 benchmark (AutomationBench).

GPT-5.6 Terra significantly outperforms across most benchmarks.

Sun Nov 22 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only GPT-5.6 Terra specifies input context (1,050,000 tokens). Only GPT-5.6 Terra specifies output context (128,000 tokens).

OpenAI
GPT-5.6 Terra
Input1,050,000 tokens
Output128,000 tokens
Institute of Foundation Models
K2 Horizon 375B-A23B
Input- tokens
Output- tokens
Sun Nov 22 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

GPT-5.6 Terra supports multimodal inputs, whereas K2 Horizon 375B-A23B does not.

GPT-5.6 Terra can handle both text and other forms of data like images, making it suitable for multimodal applications.

GPT-5.6 Terra

Text
Images
Audio
Video

K2 Horizon 375B-A23B

Text
Images
Audio
Video

License

Usage and distribution terms

GPT-5.6 Terra 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-5.6 Terra

Proprietary

Closed source

K2 Horizon 375B-A23B

Apache 2.0

Open weights

Release Timeline

When each model was launched

GPT-5.6 Terra was released on 2026-07-09, while K2 Horizon 375B-A23B was released on 2026-09-03.

K2 Horizon 375B-A23B is 2 months newer than GPT-5.6 Terra.

GPT-5.6 Terra

Jul 9, 2026

4 months ago

K2 Horizon 375B-A23B

Sep 3, 2026

2 months ago

1mo newer

Knowledge Cutoff

When training data ends

GPT-5.6 Terra has a documented knowledge cutoff of 2026-02-16, while K2 Horizon 375B-A23B's cutoff date is not specified.

We can confirm GPT-5.6 Terra's training data extends to 2026-02-16, but cannot make a direct comparison without K2 Horizon 375B-A23B's cutoff date.

GPT-5.6 Terra

Feb 2026

K2 Horizon 375B-A23B

—

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against GPT-5.6 Terra and K2 Horizon 375B-A23B side-by-side, then vote on the output you prefer.

GPT-5.6 Terra
✓ Preferred
K2 Horizon 375B-A23B
Open in Playground

FAQ

Common questions about GPT-5.6 Terra vs K2 Horizon 375B-A23B.

Which is better, GPT-5.6 Terra or K2 Horizon 375B-A23B?

GPT-5.6 Terra leads the LLM Stats Score 47.8 to 37.6. GPT-5.6 Terra 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-5.6 Terra compare to K2 Horizon 375B-A23B in benchmarks?

GPT-5.6 Terra scores Connectors: 100.0%, HealthBench Consensus: 95.1%, Search and Function-Calling: 94.6%, GPQA: 92.9%, Capture-the-Flag Challenges (Internal): 91.8%. 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 context window sizes for GPT-5.6 Terra and K2 Horizon 375B-A23B?

GPT-5.6 Terra supports 1.1M tokens and K2 Horizon 375B-A23B 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 GPT-5.6 Terra and K2 Horizon 375B-A23B?

Key differences include LLM Stats Score (47.8 vs 37.6), multimodal support (yes vs no), licensing (Proprietary vs Apache 2.0). See the full comparison above for benchmark-by-benchmark results.

Who makes GPT-5.6 Terra and K2 Horizon 375B-A23B?

GPT-5.6 Terra is developed by OpenAI and K2 Horizon 375B-A23B is developed by Institute of Foundation Models.