Anthropic, proprietary
Claude Haiku 5.5
Claude Haiku 5.5 by Anthropic ranks 52nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 49.5. Its strongest category is math, where it ranks 18th. API pricing starts at $0.10 per million input tokens and $0.50 per million output tokens, with a 1M-token context window.
Last verified
Specifications
- Noometry rank
- #52 of 354
- Index score
- 49.5
- Evidence
- Confirmed 9 results
- Provider
- Anthropic
- Released
- October 7, 2026
- Weights
- Proprietary
- Reasoning
- Yes
- Context window
- 1M
- Max output
- 128K
- Input price
- $0.10 / M
- Output price
- $0.50 / M
- Blended price
- $0.20 / M
- Output speed
- Not measured
- Value
- #30 of 219
- Knowledge cutoff
- June 2026
- Input
- text, image, pdf
Category scores
Each category score combines every public result we have in that category.
- Coding 49.2
- Reasoning 35.2
- Math 73.6
- Knowledge 50.8
- Multimodal 43.7
| Category | Score | Rank | Results |
|---|---|---|---|
| Coding | 49.2 | #50 | 1 |
| Reasoning | 35.2 | #69 | 2 |
| Math | 73.6 | #18 | 3 |
| Knowledge | 50.8 | #70 | 2 |
| Multimodal | 43.7 | #21 | 1 |
Strengths and weaknesses
Categories where Claude Haiku 5.5 places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
Closest competitors
The models ranked just above and below Claude Haiku 5.5. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Muse Spark 1.2 | #48 | 50.3 | $2 | — | Compare |
| MiMo-V2.6-Pro | #49 | 50.3 | $0.54 | — | Compare |
| Claude Sonnet 4.6 | #50 | 50.3 | $6 | — | Compare |
| Muse Spark 1.1 | #51 | 49.9 | $2 | — | Compare |
| GPT-5.1 | #53 | 49.0 | $3.44 | — | Compare |
| Grok 4.20 (Non-Reasoning) | #54 | 48.6 | $1.56 | 61 | Compare |
| MiMo-V2.6-Flash | #55 | 48.5 | $0.18 | — | Compare |
| Grok 4 | #56 | 48.1 | — | 1 | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Coding
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| LMArena WebDev | 1587 | #25 of 113, top 23% | high | LMArena | 2026-10-08 |
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| NYT Connections (extended) | 65.7% | #53 of 91, top 59% | high reasoning | Lech Mazur benchmarks | |
| Mystery Game Puzzles | 30% | #26 of 74, top 36% | max | Epoch AI | 2026-10-07 |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| FrontierMath (Tiers 1-3) | 75.1% | #18 of 81, top 23% | max | Epoch AI | 2026-10-07 |
| FrontierMath Tier 4 | 46.3% | #19 of 63, top 31% | max | Epoch AI | 2026-10-07 |
| OTIS Mock AIME 2024-2025 | 97.2% | high | Epoch AI | 2026-10-07 | |
| OTIS Mock AIME 2024-2025 | 98.9% | #15 of 173, top 9% | xhigh | Epoch AI | 2026-10-07 |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| GPQA Diamond | 89.6% | #42 of 186, top 23% | max | Epoch AI | 2026-10-09 |
| SimpleQA Verified | 23.8% | #62 of 77, top 81% | max | Epoch AI | 2026-10-09 |
Multimodal
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Furniture Assembly | 47.5% | #10 of 31, top 33% | max | Epoch AI | 2026-10-07 |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| anthropic | $0.10 | $0.50 | $0.01 | 2026-10-10 |
| azure | $0.10 | $0.50 | $0.01 | 2026-10-10 |
| bedrock | $0.10 | $0.50 | $0.01 | 2026-10-10 |
| openrouter | $0.10 | $0.50 | $0.01 | 2026-10-10 |
| vertex | $0.10 | $0.50 | $0.01 | 2026-10-10 |
Compare Claude Haiku 5.5
- Claude Haiku 5.5 vs Claude Haiku 4.5
- Claude Haiku 5.5 vs Muse Spark 1.1
- Claude Haiku 5.5 vs GPT-5.1
- Claude Haiku 5.5 vs Claude Sonnet 4.6
- Claude Haiku 5.5 vs Grok 4.20 (Non-Reasoning)
- Claude Haiku 5.5 vs MiMo-V2.6-Pro
- Claude Haiku 5.5 vs MiMo-V2.6-Flash
- Claude Haiku 5.5 vs GPT-6 Astra
- Claude Haiku 5.5 vs Gemini 3.8 Flash
- Claude Haiku 5.5 vs Kimi K3
- Claude Haiku 5.5 vs Grok 4.6
- Claude Haiku 5.5 vs Qwen3.8 Max
- Claude Haiku 5.5 vs GLM-5.3
- Claude Haiku 5.5 vs Muse Spark 1.3
Other Anthropic models
- Claude Fable 5.169.0
- Claude Opus 5.568.6
- Claude Opus 567.8
- Claude Fable 566.8
- Claude Sonnet 5.561.9
- Claude Opus 4.860.7
- Claude Opus 4.758.3
- Claude Opus 4.658.2
Frequently asked questions
How good is Claude Haiku 5.5?
Claude Haiku 5.5 by Anthropic ranks 52nd of 354 ranked models on the Noometry Index as of October 2026, with a score of 49.5. Its strongest category is math, where it ranks 18th. API pricing starts at $0.10 per million input tokens and $0.50 per million output tokens, with a 1M-token context window.
How much does Claude Haiku 5.5 cost?
Claude Haiku 5.5 costs $0.10 per million input tokens and $0.50 per million output tokens on Anthropic's own API, with cached input at $0.01.
What is Claude Haiku 5.5's context window?
Claude Haiku 5.5 accepts up to 1M tokens of input and can write up to 128K tokens in one response.
Is Claude Haiku 5.5 open source?
No. Claude Haiku 5.5 is proprietary and available only through Anthropic's API and partner platforms.
What are Claude Haiku 5.5's strengths and weaknesses?
Relative to other ranked models, Claude Haiku 5.5 places best in math, coding and lowest in knowledge, reasoning.
What is Claude Haiku 5.5 best at?
Its best category is math, where it ranks 18th on Noometry.