The AI arena is free today

Open Superagent

Claude Haiku 5.5 vs EXAONE 4.5 33B

Claude Haiku 5.5 leads the LLM Stats Score 50.0 to 25.9.

Anthropic · LG AI Research · Updated for 2026

Which is better?

Claude Haiku 5.5 leads the overall LLM Stats Score 50.0 to 25.9, ranking #19 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 50.0 and ranks #19 on LLM Stats
  • your work emphasizes reasoning — it leads those capability indexes
  • you want the most recent training data — it shipped Oct 2026

Choose EXAONE 4.5 33B

  • you are already invested in the LG AI Research ecosystem

At a glance

The differences that matter most.

Claude Haiku 5.5
Anthropic
EXAONE 4.5 33B
LG AI Research
Core performance indexes
LLM Stats Score
50.0
#19
25.9
#168
Reasoning
47.2
#27
26.5
#161
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

4 shared
Index
Claude Haiku 5.5
EXAONE 4.5 33B
Math
25.7#110
28.4#95
Vision
30.4#33
13.3#105
Tool use
20.3#59
10.3#135
Multimodal
31.4#27
16.2#90
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

36 reported for Claude Haiku 5.5 · 15 for EXAONE 4.5 33B

No common benchmarks found

Claude Haiku 5.5 and EXAONE 4.5 33Bdon'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
LG AI Research
EXAONE 4.5 33B
Input- tokens
Output- tokens
Fri Oct 09 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Claude Haiku 5.5 and EXAONE 4.5 33B support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

Claude Haiku 5.5

Text
Images
Audio
Video

EXAONE 4.5 33B

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

Claude Haiku 5.5

Proprietary

Closed source

EXAONE 4.5 33B

Proprietary

Closed source

Release Timeline

When each model was launched

Claude Haiku 5.5 was released on 2026-10-07, while EXAONE 4.5 33B was released on 2026-04-09.

Claude Haiku 5.5 is 6 months newer than EXAONE 4.5 33B.

Claude Haiku 5.5

Oct 7, 2026

1 days ago

6mo newer
EXAONE 4.5 33B

Apr 9, 2026

6 months ago

Knowledge Cutoff

When training data ends

Claude Haiku 5.5 has a knowledge cutoff of 2026-06-01, while EXAONE 4.5 33B has a cutoff of 2024-12-01.

Claude Haiku 5.5 has more recent training data (up to 2026-06-01), making it potentially better informed about events through that date compared to EXAONE 4.5 33B (2024-12-01).

Claude Haiku 5.5

Jun 2026

1.5 yr newer
EXAONE 4.5 33B

Dec 2024

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

Run your own prompts against Claude Haiku 5.5 and EXAONE 4.5 33B side-by-side, then vote on the output you prefer.

Claude Haiku 5.5
✓ Preferred
EXAONE 4.5 33B
Open in Playground

FAQ

Common questions about Claude Haiku 5.5 vs EXAONE 4.5 33B.

Which is better, Claude Haiku 5.5 or EXAONE 4.5 33B?

Claude Haiku 5.5 leads the LLM Stats Score 50.0 to 25.9. Claude Haiku 5.5 is made by Anthropic and EXAONE 4.5 33B is made by LG AI Research. 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 EXAONE 4.5 33B 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%. EXAONE 4.5 33B scores AIME 2025: 92.9%, AIME 2026: 92.6%, IFEval: 89.6%, AI2D: 89.0%, MathVista-Mini: 85.0%.

What are the context window sizes for Claude Haiku 5.5 and EXAONE 4.5 33B?

Claude Haiku 5.5 supports 1.0M tokens and EXAONE 4.5 33B 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 EXAONE 4.5 33B?

Key differences include LLM Stats Score (50.0 vs 25.9). See the full comparison above for benchmark-by-benchmark results.

Who makes Claude Haiku 5.5 and EXAONE 4.5 33B?

Claude Haiku 5.5 is developed by Anthropic and EXAONE 4.5 33B is developed by LG AI Research.

Related comparisons