The AI arena is free today

Open Superagent

K2 Horizon 375B-A23B vs LongCat-2.5

LongCat-2.5 leads the LLM Stats Score 50.0 to 38.4.

Institute of Foundation Models · Meituan · Updated for 2026

Which is better?

LongCat-2.5 leads the overall LLM Stats Score 50.0 to 38.4, ranking #20 overall.

In the 3 individual benchmarks reported for both models, LongCat-2.5 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 K2 Horizon 375B-A23B

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

Choose LongCat-2.5

  • overall performance matters — it scores 50.0 and ranks #20 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

At a glance

The differences that matter most.

K2 Horizon 375B-A23B
Institute of Foundation Models
LongCat-2.5
Meituan
Core performance indexes
LLM Stats Score
38.4
#86
50.0
#20
Reasoning
37.2
#90
48.3
#21
Coding
21.1
#115
38.6
#27
Agents
23.5
#79
36.3
#23
Cost, coverage & limits
Benchmark wins
0 of 3
3 of 3
Input price
— / M
$0.30 / M
Output price
— / M
$1.20 / M
Context window
—
1,048,576

Capability indexes

Additional strengths measured across groups of related public benchmarks

2 shared
Index
K2 Horizon 375B-A23B
LongCat-2.5
Math
29.8#90
37.2#37
Tool use
22.0#65
30.2#15
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

18 reported for K2 Horizon 375B-A23B · 23 for LongCat-2.5

3 shared

K2 Horizon 375B-A23B outperforms in 0 benchmarks, while LongCat-2.5 is better at 3 benchmarks (BrowseComp, SWE Atlas - Codebase QnA, Terminal-Bench 2.1).

LongCat-2.5 significantly outperforms across most benchmarks.

Wed Nov 04 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Model Size

Parameter count comparison

1225.0B diff

LongCat-2.5 has 1225.0B more parameters than K2 Horizon 375B-A23B, making it 326.7% larger.

Institute of Foundation Models
K2 Horizon 375B-A23B
375.0Bparameters
Meituan
LongCat-2.5
1.6Tparameters
375.0B
K2 Horizon 375B-A23B
1600.0B
LongCat-2.5

Context Window

Maximum input and output token capacity

Only LongCat-2.5 specifies input context (1,048,576 tokens). Only LongCat-2.5 specifies output context (131,072 tokens).

Institute of Foundation Models
K2 Horizon 375B-A23B
Input- tokens
Output- tokens
Meituan
LongCat-2.5
Input1,048,576 tokens
Output131,072 tokens
Wed Nov 04 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

LongCat-2.5 supports multimodal inputs, whereas K2 Horizon 375B-A23B does not.

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

K2 Horizon 375B-A23B

Text
Images
Audio
Video

LongCat-2.5

Text
Images
Audio
Video

Release Timeline

When each model was launched

K2 Horizon 375B-A23B was released on 2026-09-03, while LongCat-2.5 was released on 2026-11-01.

LongCat-2.5 is 2 months newer than K2 Horizon 375B-A23B.

K2 Horizon 375B-A23B

Sep 3, 2026

2 months ago

LongCat-2.5

Nov 1, 2026

3 days ago

1mo newer

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 375B-A23B and LongCat-2.5 side-by-side, then vote on the output you prefer.

K2 Horizon 375B-A23B
✓ Preferred
LongCat-2.5
Open in Playground

FAQ

Common questions about K2 Horizon 375B-A23B vs LongCat-2.5.

Which is better, K2 Horizon 375B-A23B or LongCat-2.5?

LongCat-2.5 leads the LLM Stats Score 50.0 to 38.4. K2 Horizon 375B-A23B is made by Institute of Foundation Models and LongCat-2.5 is made by Meituan. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does K2 Horizon 375B-A23B compare to LongCat-2.5 in benchmarks?

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%. LongCat-2.5 scores MathVision: 96.5%, BrowseComp: 91.9%, CharXiv-R: 90.2%, Terminal-Bench 2.1: 88.4%, Video-MME: 85.2%.

What are the context window sizes for K2 Horizon 375B-A23B and LongCat-2.5?

K2 Horizon 375B-A23B supports an unknown number of tokens and LongCat-2.5 supports 1.0M 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 375B-A23B and LongCat-2.5?

Key differences include LLM Stats Score (38.4 vs 50.0), multimodal support (no vs yes), licensing (Apache 2.0 vs Unknown). See the full comparison above for benchmark-by-benchmark results.

Who makes K2 Horizon 375B-A23B and LongCat-2.5?

K2 Horizon 375B-A23B is developed by Institute of Foundation Models and LongCat-2.5 is developed by Meituan.

Related comparisons