The AI arena is free today

Open Superagent

Claude Haiku 5.5 vs Claude Sonnet 5.5

Claude Sonnet 5.5 leads the LLM Stats Score 58.5 to 50.3. Claude Haiku 5.5 is 20.0x cheaper per token.

Anthropic · Anthropic · Updated for 2026

Which is better?

Claude Sonnet 5.5 leads the overall LLM Stats Score 58.5 to 50.3, ranking #2 overall.

In the 36 individual benchmarks reported for both models, Claude Sonnet 5.5 wins 34; this is a narrower head-to-head signal than the composite indexes.

On price, Claude Haiku 5.5 is roughly 20.0x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

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

Choose Claude Haiku 5.5

  • cost matters — it's about 20.0x cheaper per token
  • you want the most recent training data — it shipped Oct 2026

Choose Claude Sonnet 5.5

  • overall performance matters — it scores 58.5 and ranks #2 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 34 of 36 exact shared results

At a glance

The differences that matter most.

Claude Haiku 5.5
Anthropic
Claude Sonnet 5.5
Anthropic
Core performance indexes
LLM Stats Score
50.3
#18
58.5
#2
Reasoning
47.4
#26
57.1
#2
Coding
40.7
#12
48.9
#2
Agents
33.7
#27
42.7
#3
Cost, coverage & limits
Benchmark wins
2 of 36
34 of 36
Input price
$0.10 / M
$2.00 / M
Output price
$0.50 / M
$10.00 / M
Context window
1,000,000
1,000,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

4 shared
Index
Claude Haiku 5.5
Claude Sonnet 5.5
Math
25.7#110
37.6#30
Vision
30.5#32
41.1#2
Tool use
20.8#57
34.1#2
Multimodal
31.6#25
40.6#2
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

36 reported for Claude Haiku 5.5 · 47 for Claude Sonnet 5.5

36 shared

Claude Haiku 5.5 outperforms in 2 benchmarks (Morphology-to-molecule matching, Program Bench), while Claude Sonnet 5.5 is better at 34 benchmarks (AA-Briefcase v1.1, BenchCAD, BenchCAD (with Python tool), Biomedical image analysis, Chartography, Chartography (no tools), FrontierCode 1.1, FrontierCode 1.1 (Extended), FrontierSWE V2, GDPval-AA 2.1, Global-MMLU, HealthBench, HealthBench Professional, HealthBench Professional (raw), Humanity's Last Exam (no tools, text-only), Humanity's Last Exam (with tools), LatchBio SingleCellBench, LatchBio SpatialBench Verified, Medicinal Chemistry (ADME), MILU, OfficeQA, OfficeQA Pro, OSWorld 2.1 (partial), OSWorld 2.1 (strict), PhysicianBench, Protein Design — Library Ranking, Protein Design — Sequence Generation, Protocols Troubleshooting, Protocols Understanding (V2), SWE-bench Multilingual, SWE-Bench Multimodal, SWE-Bench Pro, Terminal-Bench 4.0, Terminal-Bench-Science 0.1).

Claude Sonnet 5.5 significantly outperforms across most benchmarks.

Wed Oct 07 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

Claude Haiku 5.5 costs less

For input processing, Claude Haiku 5.5 ($0.10/1M tokens) is 20.0x cheaper than Claude Sonnet 5.5 ($2.00/1M tokens).

For output processing, Claude Haiku 5.5 ($0.50/1M tokens) is 20.0x cheaper than Claude Sonnet 5.5 ($10.00/1M tokens).

In conclusion, Claude Sonnet 5.5 is more expensive than Claude Haiku 5.5.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Wed Oct 07 2026 • llm-stats.com
Anthropic
Claude Haiku 5.5
Input tokens$0.10
Output tokens$0.50
Best providerAnthropic
Anthropic
Claude Sonnet 5.5
Input tokens$2.00
Output tokens$10.00
Best providerAnthropic
Notice missing or incorrect data?

Context Window

Maximum input and output token capacity

Both models have the same input context window of 1,000,000 tokens. Both models can generate responses up to 128,000 tokens.

Anthropic
Claude Haiku 5.5
Input1,000,000 tokens
Output128,000 tokens
Anthropic
Claude Sonnet 5.5
Input1,000,000 tokens
Output128,000 tokens
Wed Oct 07 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both Claude Haiku 5.5 and Claude Sonnet 5.5 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

Claude Sonnet 5.5

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

Claude Sonnet 5.5

Proprietary

Closed source

Release Timeline

When each model was launched

Claude Haiku 5.5 was released on 2026-10-07, while Claude Sonnet 5.5 was released on 2026-09-28.

Claude Haiku 5.5 is 0 month newer than Claude Sonnet 5.5.

Claude Haiku 5.5

Oct 7, 2026

0 days ago

1w newer
Claude Sonnet 5.5

Sep 28, 2026

1 weeks ago

Knowledge Cutoff

When training data ends

Both models have the same knowledge cutoff date of 2026-06-01.

They should have similar awareness of historical events and information up to this date.

Claude Haiku 5.5

Jun 2026

Claude Sonnet 5.5

Jun 2026

Provider Availability

Claude Haiku 5.5 is available from Anthropic. Claude Sonnet 5.5 is available from Anthropic.

Claude Haiku 5.5

anthropic logo
Anthropic
Input Price:Input: $0.10/1MOutput Price:Output: $0.50/1M

Claude Sonnet 5.5

anthropic logo
Anthropic
Input Price:Input: $2.00/1MOutput Price:Output: $10.00/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?

Judge for yourself.

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

Claude Haiku 5.5
✓ Preferred
Claude Sonnet 5.5
Open in Playground

FAQ

Common questions about Claude Haiku 5.5 vs Claude Sonnet 5.5.

Which is better, Claude Haiku 5.5 or Claude Sonnet 5.5?

Claude Sonnet 5.5 leads the LLM Stats Score 58.5 to 50.3. Claude Haiku 5.5 is made by Anthropic and Claude Sonnet 5.5 is made by Anthropic. 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 Claude Sonnet 5.5 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%. Claude Sonnet 5.5 scores BenchCAD (with Python tool): 96.3%, ArXivMath (with tools): 95.2%, Global-MMLU: 92.1%, MILU: 91.6%, SWE-bench Multilingual: 90.3%.

Is Claude Haiku 5.5 cheaper than Claude Sonnet 5.5?

Claude Haiku 5.5 is 20.0x cheaper for input tokens. Claude Haiku 5.5 costs $0.10/M input and $0.50/M output via anthropic. Claude Sonnet 5.5 costs $2.00/M input and $10.00/M output via anthropic.

What are the context window sizes for Claude Haiku 5.5 and Claude Sonnet 5.5?

Claude Haiku 5.5 supports 1.0M tokens and Claude Sonnet 5.5 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 Claude Haiku 5.5 and Claude Sonnet 5.5?

Key differences include LLM Stats Score (50.3 vs 58.5), input pricing ($0.10 vs $2.00/M). See the full comparison above for benchmark-by-benchmark results.

Related comparisons