Noometry

Model comparison

Claude 3 Sonnet vs Claude Sonnet 5.5

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 29.0 on the Noometry Index.

Last verified . 16 shared benchmarks.

Claude 3 Sonnet Anthropic

29.0

Rank #319 Confirmed

Claude Sonnet 5.5 Anthropic

61.9

Rank #10 Confirmed

Summary

  • They share 16 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Claude Sonnet 5.5 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 5.5 leads 87.9 to 10.7.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.5% for Claude 3 Sonnet and 100% for Claude Sonnet 5.5.

Side by side

Claude 3 SonnetClaude Sonnet 5.5
ProviderAnthropicAnthropic
Noometry Index29.061.9
Released2024-02-292026-09-28
WeightsProprietaryProprietary
Context window—1M
Max output—128K
Input $ / M tokens—$2
Output $ / M tokens—$10
Results tracked3032

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Claude Sonnet 5.5 leads

Claude 3 Sonnet: 29.6 (#302), Claude Sonnet 5.5: 67.3 (#6)

BenchmarkClaude 3 SonnetClaude Sonnet 5.5
LMArena Coding12231513
FrontierCode—52.1%
CursorBench—55.5%
LMArena WebDev—1774
FrontierSWE—61.9%
SciCode—61%
WeirdML10.2%—
BigCodeBench Instruct42.7%—
BigCodeBench Complete53.8%—
ALE-Bench—1,819
HumanEval+64%—
MBPP+69.3%—

Agentic & Tool Use Not comparable

Claude 3 Sonnet: —, Claude Sonnet 5.5: 45.0 (#16)

BenchmarkClaude 3 SonnetClaude Sonnet 5.5
APEX-Agents—75.5%

Reasoning Claude Sonnet 5.5 leads

Claude 3 Sonnet: 20.5 (#237), Claude Sonnet 5.5: 54.0 (#28)

BenchmarkClaude 3 SonnetClaude Sonnet 5.5
LMArena Hard Prompts11971495
Epoch Capabilities Index120.7165.03
NYT Connections (extended)—80.5%
CritPt—31.4%
Mystery Game Puzzles—65%
DTBench53.6%—
WinoGrande75.1%—

Math Claude Sonnet 5.5 leads

Claude 3 Sonnet: 10.7 (#310), Claude Sonnet 5.5: 87.9 (#6)

BenchmarkClaude 3 SonnetClaude Sonnet 5.5
OTIS Mock AIME 2024-20252.5%100%
LMArena Math12131510
FrontierMath (Tiers 1-3)—88.8%
FrontierMath Tier 4—80.5%
ProofBench—100%
MATH Level 518.2%—
FrontierMath Erdős—2.9%

Knowledge Claude Sonnet 5.5 leads

Claude 3 Sonnet: 21.1 (#276), Claude Sonnet 5.5: 66.0 (#12)

BenchmarkClaude 3 SonnetClaude Sonnet 5.5
GPQA Diamond40.6%95.6%
LMArena Expert11731540
SimpleQA Verified—46.5%
MMLU75.9%—

Multimodal Claude Sonnet 5.5 leads

Claude 3 Sonnet: 25.2 (#125), Claude Sonnet 5.5: 51.5 (#6)

BenchmarkClaude 3 SonnetClaude Sonnet 5.5
LMArena Vision9841289
Furniture Assembly—75%

Multilingual Claude Sonnet 5.5 leads

Claude 3 Sonnet: 37.8 (#234), Claude Sonnet 5.5: 55.3 (#30)

BenchmarkClaude 3 SonnetClaude Sonnet 5.5
LMArena Non-English12051452
LMArena Chinese11891522
LMArena Russian12271451
LMArena French1229—
LMArena German1204—
LMArena Japanese1131—
LMArena Korean1128—
LMArena Spanish1204—

Instruction Following Claude Sonnet 5.5 leads

Claude 3 Sonnet: 62.8 (#235), Claude Sonnet 5.5: 78.3 (#11)

BenchmarkClaude 3 SonnetClaude Sonnet 5.5
LMArena Instruction Following11991495

Long Context Claude Sonnet 5.5 leads

Claude 3 Sonnet: 36.7 (#228), Claude Sonnet 5.5: 45.9 (#28)

BenchmarkClaude 3 SonnetClaude Sonnet 5.5
LMArena Longer Query12111498

Writing & Preference Claude Sonnet 5.5 leads

Claude 3 Sonnet: 42.1 (#238), Claude Sonnet 5.5: 66.0 (#40)

BenchmarkClaude 3 SonnetClaude Sonnet 5.5
LMArena Text12181471
LMArena Creative Writing11861465
LMArena Multi-Turn12271474

Frequently asked questions

Is Claude 3 Sonnet better than Claude Sonnet 5.5?

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 29.0 on the Noometry Index.

Is Claude 3 Sonnet or Claude Sonnet 5.5 better for coding?

Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 29.6 in the Noometry coding category.

How many benchmarks do Claude 3 Sonnet and Claude Sonnet 5.5 share?

16 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Claude Sonnet 5.5 has 32.

Related comparisons

Go deeper