Noometry

Anthropic, proprietary

Claude Sonnet 5.5

Claude Sonnet 5.5 by Anthropic ranks 10th of 354 ranked models on the Noometry Index as of October 2026, with a score of 61.9. Its strongest category is coding, where it ranks 6th. API pricing starts at $2 per million input tokens and $10 per million output tokens, with a 1M-token context window.

Last verified

Noometry rank
#10 of 354
Index score
61.9
Evidence
Confirmed 32 results
Provider
Anthropic
Released
September 28, 2026
Weights
Proprietary
Reasoning
Yes
Context window
1M
Max output
128K
Input price
$2 / M
Output price
$10 / M
Blended price
$4 / M
Output speed
Not measured
Value
#162 of 219
Knowledge cutoff
June 2026
Input
text, image, pdf

Category scores

Each category score combines every public result we have in that category.

  1. Coding 67.3
  2. Agentic & Tool Use 45.0
  3. Reasoning 54.0
  4. Math 87.9
  5. Knowledge 66.0
  6. Multimodal 51.5
  7. Multilingual 55.3
  8. Instruction Following 78.3
  9. Long Context 45.9
  10. Writing & Preference 66.0
CategoryScoreRankResults
Coding67.3#66
Agentic & Tool Use45.0#161
Reasoning54.0#284
Math87.9#65
Knowledge66.0#123
Multimodal51.5#62
Multilingual55.3#301
Instruction Following78.3#111
Long Context45.9#281
Writing & Preference66.0#403

Strengths and weaknesses

Categories where Claude Sonnet 5.5 places highest and lowest among the models ranked in each, with its score against that category's median.

Strongest categories

CategoryScorevs medianRank
Coding67.3+28.5#6 of 340, top 2%
Math87.9+51.4#6 of 327, top 2%
Instruction Following78.3+7.0#11 of 305, top 4%

Weakest categories

CategoryScorevs medianRank
Writing & Preference66.0+12.2#40 of 312, top 13%
Agentic & Tool Use45.0+14.7#16 of 154, top 11%
Multilingual55.3+7.9#30 of 297, top 11%

Closest competitors

The models ranked just above and below Claude Sonnet 5.5. When scores are this close, price and speed are often the better way to choose.

ModelRankScoreBlended $/MSpeed
GPT-6.1 Sol#665.6$4—Compare
GPT-5.6 Sol#765.0$810Compare
GPT-5.5 Pro#864.3$67.50—Compare
GPT-5.5#963.4$11.2525Compare
Gemini 3.8 Flash#1161.8$1.50—Compare
GPT-6 Sol#1261.8$4—Compare
Claude Opus 4.8#1360.7$1034Compare
Gemini 3.7 Flash#1459.8$1.50—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

BenchmarkScorePositionSettingSourceDate
FrontierCode52.1%#5 of 37, top 14%xhighEpoch AI
FrontierCode46.2%maxModel card (self-reported)2026-09-28
CursorBench47.8%highEpoch AI
CursorBench35.8%lowEpoch AI
CursorBench55.5%#2 of 14, top 15%maxEpoch AI
CursorBench39.2%mediumEpoch AI
CursorBench53.1%xhighEpoch AI
LMArena WebDev1774#3 of 113, top 3%xhighLMArena2026-10-08
FrontierSWE61.9%#3 of 18, top 17%maxEpoch AI
SciCode53.7%highEpoch AI
SciCode49.1%lowEpoch AI
SciCode61%#5 of 121, top 5%maxEpoch AI
SciCode52.9%mediumEpoch AI
SciCode57.3%xhighEpoch AI
LMArena Coding1513#10 of 294, top 4%xhighLMArena2026-10-08
ALE-Bench1,819#10 of 105, top 10%highEpoch AI

Agentic & Tool Use

BenchmarkScorePositionSettingSourceDate
APEX-Agents75.5%#2 of 49, top 5%maxEpoch AI
APEX-Agents44.6%mediumEpoch AI

Reasoning

BenchmarkScorePositionSettingSourceDate
NYT Connections (extended)80.5%#34 of 91, top 38%high reasoningLech Mazur benchmarks
CritPt24.6%highEpoch AI
CritPt11.4%lowEpoch AI
CritPt31.4%#5 of 134, top 4%maxEpoch AI
CritPt16.9%mediumEpoch AI
CritPt31.1%xhighEpoch AI
LMArena Hard Prompts1495#13 of 297, top 5%xhighLMArena2026-10-08
Mystery Game Puzzles65%#4 of 74, top 6%maxEpoch AI2026-09-29
Epoch Capabilities Index165.03#4 of 213, top 2%Epoch AI2026-09-28

Math

BenchmarkScorePositionSettingSourceDate
FrontierMath (Tiers 1-3)88.8%#7 of 81, top 9%maxEpoch AI2026-09-29
FrontierMath Tier 480.5%#8 of 63, top 13%maxEpoch AI2026-09-29
OTIS Mock AIME 2024-2025100%#4 of 173, top 3%maxEpoch AI2026-09-29
ProofBench100%#3 of 77, top 4%maxEpoch AI
LMArena Math1510#7 of 285, top 3%xhighLMArena2026-10-08
FrontierMath Erdős2.9%#3 of 7, top 43%maxEpoch AI2026-10-08

Knowledge

BenchmarkScorePositionSettingSourceDate
GPQA Diamond95.6%#2 of 186, top 2%maxEpoch AI2026-09-29
SimpleQA Verified46.5%#33 of 77, top 43%maxEpoch AI2026-09-29
LMArena Expert1540#6 of 273, top 3%xhighLMArena2026-10-08

Multimodal

BenchmarkScorePositionSettingSourceDate
LMArena Vision1289#22 of 122, top 19%xhighLMArena2026-10-09
Furniture Assembly75%#4 of 31, top 13%maxEpoch AI2026-09-29

Multilingual

BenchmarkScorePositionSettingSourceDate
LMArena Non-English1452#30 of 297, top 11%xhighLMArena2026-10-08
LMArena Chinese1522#24 of 285, top 9%xhighLMArena2026-10-08
LMArena Russian1451#41 of 283, top 15%xhighLMArena2026-10-08

Instruction Following

BenchmarkScorePositionSettingSourceDate
LMArena Instruction Following1495#8 of 298, top 3%xhighLMArena2026-10-08

Long Context

BenchmarkScorePositionSettingSourceDate
LMArena Longer Query1498#10 of 291, top 4%xhighLMArena2026-10-08

Writing & Preference

BenchmarkScorePositionSettingSourceDate
LMArena Text1471#23 of 297, top 8%xhighLMArena2026-10-08
LMArena Creative Writing1465#16 of 295, top 6%xhighLMArena2026-10-08
LMArena Multi-Turn1474#26 of 295, top 9%xhighLMArena2026-10-08

API pricing by provider

RouteInput $/MOutput $/MCached input $/MChecked
anthropic$2$10$0.102026-10-10
azure$2$10$0.202026-10-10
bedrock$2$10$0.102026-10-10
openrouter$2$10$0.102026-10-10
vertex$2$10$0.202026-10-10

All Anthropic API prices → Estimate your cost →

Compare Claude Sonnet 5.5

Other Anthropic models

Frequently asked questions

How good is Claude Sonnet 5.5?

Claude Sonnet 5.5 by Anthropic ranks 10th of 354 ranked models on the Noometry Index as of October 2026, with a score of 61.9. Its strongest category is coding, where it ranks 6th. API pricing starts at $2 per million input tokens and $10 per million output tokens, with a 1M-token context window.

How much does Claude Sonnet 5.5 cost?

Claude Sonnet 5.5 costs $2 per million input tokens and $10 per million output tokens on Anthropic's own API, with cached input at $0.10.

What is Claude Sonnet 5.5's context window?

Claude Sonnet 5.5 accepts up to 1M tokens of input and can write up to 128K tokens in one response.

Is Claude Sonnet 5.5 open source?

No. Claude Sonnet 5.5 is proprietary and available only through Anthropic's API and partner platforms.

What are Claude Sonnet 5.5's strengths and weaknesses?

Relative to other ranked models, Claude Sonnet 5.5 places best in coding, math, instruction following and lowest in writing & preference, agentic & tool use, multilingual.

What is Claude Sonnet 5.5 best at?

Its best category is coding, where it ranks 6th on Noometry.