The AI arena is free today

Open Superagent

Claude Fable 5.2 vs K2 Horizon 375B-A23B

Claude Fable 5.2 leads the LLM Stats Score 60.6 to 37.6.

Anthropic · Institute of Foundation Models · Updated for 2026

Which is better?

Claude Fable 5.2 leads the overall LLM Stats Score 60.6 to 37.6, ranking #1 overall.

In the 3 individual benchmarks reported for both models, Claude Fable 5.2 wins 3; 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 Claude Fable 5.2

  • overall performance matters — it scores 60.6 and ranks #1 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 3 of 3 exact shared results
  • you want the most recent training data — it shipped Nov 2026

Choose K2 Horizon 375B-A23B

  • you need open weights you can self-host or fine-tune

At a glance

The differences that matter most.

Core performance indexes
60.6
#1
37.6
#102
59.8
#1
36.5
#104
50.2
#1
20.0
#135
46.8
#1
22.2
#95
Cost, coverage & limits
Benchmark wins
3 of 3
0 of 3
Input price
$8.00 / M
— / M
Output price
$40.00 / M
— / M
Context window
1,000,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
Claude Fable 5.2
K2 Horizon 375B-A23B
46.9#2
29.4#98
37.3#4
21.5#76
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

31 reported for Claude Fable 5.2 · 18 for K2 Horizon 375B-A23B

3 shared

Claude Fable 5.2 outperforms in 3 benchmarks (AutomationBench, Humanity's Last Exam, SWE-Bench Pro), while K2 Horizon 375B-A23B is better at 0 benchmarks.

Claude Fable 5.2 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 Claude Fable 5.2 specifies input context (1,000,000 tokens). Only Claude Fable 5.2 specifies output context (128,000 tokens).

Anthropic
Claude Fable 5.2
Input1,000,000 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

Claude Fable 5.2 supports multimodal inputs, whereas K2 Horizon 375B-A23B does not.

Claude Fable 5.2 can handle both text and other forms of data like images, making it suitable for multimodal applications.

Claude Fable 5.2

Text
Images
Audio
Video

K2 Horizon 375B-A23B

Text
Images
Audio
Video

License

Usage and distribution terms

Claude Fable 5.2 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.

Claude Fable 5.2

Proprietary

Closed source

K2 Horizon 375B-A23B

Apache 2.0

Open weights

Release Timeline

When each model was launched

Claude Fable 5.2 was released on 2026-11-09, while K2 Horizon 375B-A23B was released on 2026-09-03.

Claude Fable 5.2 is 2 months newer than K2 Horizon 375B-A23B.

Claude Fable 5.2

Nov 9, 2026

1 weeks ago

2mo newer
K2 Horizon 375B-A23B

Sep 3, 2026

2 months ago

Knowledge Cutoff

When training data ends

Claude Fable 5.2 has a documented knowledge cutoff of 2026-06-01, while K2 Horizon 375B-A23B's cutoff date is not specified.

We can confirm Claude Fable 5.2's training data extends to 2026-06-01, but cannot make a direct comparison without K2 Horizon 375B-A23B's cutoff date.

Claude Fable 5.2

Jun 2026

K2 Horizon 375B-A23B

—

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Claude Fable 5.2 and K2 Horizon 375B-A23B side-by-side, then vote on the output you prefer.

Claude Fable 5.2
✓ Preferred
K2 Horizon 375B-A23B
Open in Playground

FAQ

Common questions about Claude Fable 5.2 vs K2 Horizon 375B-A23B.

Which is better, Claude Fable 5.2 or K2 Horizon 375B-A23B?

Claude Fable 5.2 leads the LLM Stats Score 60.6 to 37.6. Claude Fable 5.2 is made by Anthropic 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 Claude Fable 5.2 compare to K2 Horizon 375B-A23B in benchmarks?

Claude Fable 5.2 scores SWE-bench Multilingual: 96.6%, Global-MMLU: 96.0%, MILU: 94.1%, SWE-Bench Pro: 93.0%, Chartography: 91.6%. 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 Claude Fable 5.2 and K2 Horizon 375B-A23B?

Claude Fable 5.2 supports 1.0M 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 Claude Fable 5.2 and K2 Horizon 375B-A23B?

Key differences include LLM Stats Score (60.6 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 Claude Fable 5.2 and K2 Horizon 375B-A23B?

Claude Fable 5.2 is developed by Anthropic and K2 Horizon 375B-A23B is developed by Institute of Foundation Models.