Skip to content
Model Pareto

Claude Haiku 5.5

AnthropicProprietaryanthropic.com ↗
Compare with nearest rivalsCompare with…
Input
$0.10/M tok
Output
$0.50/M tok
Blended
$0.20/M tok · 3:1
Speed
~100tok/sest.
Context
1Mtokens

Pricing is the <=100k-token prompt tier ($0.50/$2.50 above 100k). Adjustable effort setting. Context window 1M tokens per https://platform.claude.com/docs/en/about-claude/models/overview.

Rankings

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

SWE-bench VerifiedEstimated
~#2 of 14 (estimated)~86.8%
  1. #1Claude Opus 596.0%
  2. ~#2Claude Haiku 5.5Estimated86.8%
  3. #2Claude Sonnet 585.2%
No published score — estimated from related benchmarks
SWE-bench Pro (Public)Estimated
~#6 of 20 (estimated)~68.1%
  1. #1Claude Opus 5.589.9%
  2. #2Claude Sonnet 5.581.3%
  3. #5Intern-S2-397B68.5%
  4. ~#6Claude Haiku 5.5Estimated68.1%
  5. #6Hy4 preview65.7%
No published score — estimated from related benchmarks
DeepSWE v1.1Estimated
~#22 of 35 (estimated)~63.2%
  1. #1Gemini 4 Argon78.8%
  2. #2DeepSeek V4.1 Flash74.2%
  3. #21GLM-5.3 Flash63.4%
  4. ~#22Claude Haiku 5.5Estimated63.2%
  5. #22Claude Opus 562.5%
No published score — estimated from related benchmarks
LiveCodeBenchEstimated
~#7 of 25 (estimated)~84.4%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #6gpt-oss-120b87.8%
  4. ~#7Claude Haiku 5.5Estimated84.4%
  5. #7Ternary Bonsai 27B82.8%
No published score — estimated from related benchmarks
AA Coding Agent IndexEstimated
~#12 of 18 (estimated)~50.9
  1. #1Claude Opus 5.566.0
  2. #2Gemini 4 Argon63.8
  3. #11Kimi K351.9
  4. ~#12Claude Haiku 5.5Estimated50.9
  5. #12Mistral Large 449.8
No published score — estimated from related benchmarks

Vision

MMMUEstimated
~#2 of 3 (estimated)~71.3%
  1. #1Claude Haiku 4.573.2%
  2. ~#2Claude Haiku 5.5Estimated71.3%
  3. #2Llama 4 Maverick69.4%
No published score — estimated from related benchmarks
MMMU-ProEstimated
~#18 of 86 (estimated)~79.1%
  1. #1Claude Opus 5.587.7%
  2. #2GPT-6 Astra86.9%
  3. #17Apodex 1.179.2%
  4. ~#18Claude Haiku 5.5Estimated79.1%
  5. #18Gemini 3.5 Flash-Lite79.0%
No published score — estimated from related benchmarks
CharXiv ReasoningEstimated
~#3 of 9 (estimated)~84.6%
  1. #1Gemini 3.8 Flash86.2%
  2. #2Kimi K384.8%
  3. ~#3Claude Haiku 5.5Estimated84.6%
  4. #3Qwen3.8 Flash-Next84.6%
No published score — estimated from related benchmarks
OmniDocBench v1.5Estimated
~#4 of 8 (estimated)~89.2%
  1. #1MiniMax-M391.6%
  2. #2Kimi K391.1%
  3. #2Qwen3.8 27B91.1%
  4. ~#4Claude Haiku 5.5Estimated89.2%
  5. #4Gemini 3.1 Pro85.3%
No published score — estimated from related benchmarks
GDP.pdf (AA)Estimated
~#11 of 44 (estimated)~21.3%
  1. #1GPT-6.1 Sol32.0%
  2. #2GPT-6 Astra31.0%
  3. #10Claude Opus 521.6%
  4. ~#11Claude Haiku 5.5Estimated21.3%
  5. #11GPT-5.521.2%
No published score — estimated from related benchmarks

Hard reasoning

GPQA DiamondEstimated
~#3 of 184 (estimated)~95.0%
  1. #1GPT-6 Astra96.1%
  2. #2Gemini 3.8 Flash95.3%
  3. ~#3Claude Haiku 5.5Estimated95.0%
  4. #3Gemini 3.1 Pro94.1%
No published score — estimated from related benchmarks
AIME (latest)Estimated
~#2 of 32 (estimated)~97.9%
  1. #1GLM-5.3 NVFP499.5%
  2. ~#2Claude Haiku 5.5Estimated97.9%
  3. #2Inkling97.1%
No published score — estimated from related benchmarks