The AI arena is free today

Open Superagent

Claude Haiku 5.5 vs Kimi K2 Base

Claude Haiku 5.5 leads the LLM Stats Score 49.9 to 13.0.

Anthropic · Moonshot AI · Updated for 2026

Which is better?

Claude Haiku 5.5 leads the overall LLM Stats Score 49.9 to 13.0, ranking #20 overall.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose Claude Haiku 5.5

  • overall performance matters — it scores 49.9 and ranks #20 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Oct 2026

Choose Kimi K2 Base

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

At a glance

The differences that matter most.

Claude Haiku 5.5
Anthropic
Kimi K2 Base
Moonshot AI
Core performance indexes
LLM Stats Score
49.9
#20
13.0
#270
Reasoning
47.5
#25
12.1
#268
Coding
39.2
#15
10.5
#185
Cost, coverage & limits
Benchmark wins
—
—
Input price
$0.10 / M
— / M
Output price
$0.50 / M
— / M
Context window
1,000,000
—

Capability indexes

Additional strengths measured across groups of related public benchmarks

1 shared
Index
Claude Haiku 5.5
Kimi K2 Base
Math
29.0#95
14.2#231
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

36 reported for Claude Haiku 5.5 · 13 for Kimi K2 Base

No common benchmarks found

Claude Haiku 5.5 and Kimi K2 Basedon't have any common benchmark datasets to compare. They may have been evaluated on different testing suites.

Human preference

Blind head-to-head votes and playground preference scores

Context Window

Maximum input and output token capacity

Only Claude Haiku 5.5 specifies input context (1,000,000 tokens). Only Claude Haiku 5.5 specifies output context (128,000 tokens).

Anthropic
Claude Haiku 5.5
Input1,000,000 tokens
Output128,000 tokens
Moonshot AI
Kimi K2 Base
Input- tokens
Output- tokens
Fri Oct 23 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Claude Haiku 5.5 supports multimodal inputs, whereas Kimi K2 Base does not.

Claude Haiku 5.5 can handle both text and other forms of data like images, making it suitable for multimodal applications.

Claude Haiku 5.5

Text
Images
Audio
Video

Kimi K2 Base

Text
Images
Audio
Video

License

Usage and distribution terms

Claude Haiku 5.5 is licensed under a proprietary license, while Kimi K2 Base uses MIT.

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

Claude Haiku 5.5

Proprietary

Closed source

Kimi K2 Base

MIT

Open weights

Release Timeline

When each model was launched

Claude Haiku 5.5 was released on 2026-10-07, while Kimi K2 Base was released on 2025-07-11.

Claude Haiku 5.5 is 15 months newer than Kimi K2 Base.

Claude Haiku 5.5

Oct 7, 2026

2 weeks ago

1.2yr newer
Kimi K2 Base

Jul 11, 2025

1.3 years ago

Knowledge Cutoff

When training data ends

Claude Haiku 5.5 has a documented knowledge cutoff of 2026-06-01, while Kimi K2 Base's cutoff date is not specified.

We can confirm Claude Haiku 5.5's training data extends to 2026-06-01, but cannot make a direct comparison without Kimi K2 Base's cutoff date.

Claude Haiku 5.5

Jun 2026

Kimi K2 Base

—

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Claude Haiku 5.5 and Kimi K2 Base side-by-side, then vote on the output you prefer.

Claude Haiku 5.5
✓ Preferred
Kimi K2 Base
Open in Playground

FAQ

Common questions about Claude Haiku 5.5 vs Kimi K2 Base.

Which is better, Claude Haiku 5.5 or Kimi K2 Base?

Claude Haiku 5.5 leads the LLM Stats Score 49.9 to 13.0. Claude Haiku 5.5 is made by Anthropic and Kimi K2 Base is made by Moonshot AI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does Claude Haiku 5.5 compare to Kimi K2 Base in benchmarks?

Claude Haiku 5.5 scores Global-MMLU: 87.8%, MILU: 87.6%, BenchCAD (with Python tool): 87.0%, Chartography: 86.2%, SWE-bench Multilingual: 83.7%. Kimi K2 Base scores C-Eval: 92.5%, GSM8k: 92.1%, MMLU-redux-2.0: 90.2%, MMLU: 87.8%, TriviaQA: 85.1%.

What are the context window sizes for Claude Haiku 5.5 and Kimi K2 Base?

Claude Haiku 5.5 supports 1.0M tokens and Kimi K2 Base 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 Haiku 5.5 and Kimi K2 Base?

Key differences include LLM Stats Score (49.9 vs 13.0), multimodal support (yes vs no), licensing (Proprietary vs MIT). See the full comparison above for benchmark-by-benchmark results.

Who makes Claude Haiku 5.5 and Kimi K2 Base?

Claude Haiku 5.5 is developed by Anthropic and Kimi K2 Base is developed by Moonshot AI.

Related comparisons