Noometry

Model comparison

Claude Opus 4.7 vs Claude Sonnet 5.5

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 58.3 on the Noometry Index.

Last verified . 29 shared benchmarks.

Claude Opus 4.7 Anthropic

58.3

Rank #19 Confirmed

Claude Sonnet 5.5 Anthropic

61.9

Rank #10 Confirmed

Summary

  • They share 29 benchmarks with published results for both. Claude Opus 4.7 scores higher in 5 categories and Claude Sonnet 5.5 in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 5.5 leads 87.9 to 66.7.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 31.7% for Claude Opus 4.7 and 80.5% for Claude Sonnet 5.5.
  • Claude Sonnet 5.5 is cheaper at $2 / $10 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.

Side by side

Claude Opus 4.7Claude Sonnet 5.5
ProviderAnthropicAnthropic
Noometry Index58.361.9
Released2026-04-142026-09-28
WeightsProprietaryProprietary
Context window1M1M
Max output128K128K
Input $ / M tokens$5$2
Output $ / M tokens$25$10
Results tracked6632

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

Category by category

Coding Claude Sonnet 5.5 leads

Claude Opus 4.7: 59.6 (#13), Claude Sonnet 5.5: 67.3 (#6)

BenchmarkClaude Opus 4.7Claude Sonnet 5.5
FrontierCode38.5%52.1%
LMArena WebDev15581774
SciCode54.5%61%
LMArena Coding15181513
ALE-Bench1,3231,819
SWE-bench Verified83.5%—
CursorBench—55.5%
FrontierSWE—61.9%
GSO44.1%—
WeirdML76.4%—
MirrorCode31.1%—

Agentic & Tool Use Claude Opus 4.7 leads

Claude Opus 4.7: 47.9 (#10), Claude Sonnet 5.5: 45.0 (#16)

BenchmarkClaude Opus 4.7Claude Sonnet 5.5
APEX-Agents49.2%75.5%
Terminal-Bench80.2%—
OSWorld 2.018.2%—
τ²-bench Banking40.2%—
PostTrainBench28.6%—
ExploitBench26.5%—
GBAEval43.8%—
GDP.pdf21%—
LMArena Search1233—
Vending-Bench 210,937—

Reasoning Too close to call

Claude Opus 4.7: 53.8 (#29), Claude Sonnet 5.5: 54.0 (#28)

BenchmarkClaude Opus 4.7Claude Sonnet 5.5
NYT Connections (extended)39%80.5%
CritPt12%31.4%
LMArena Hard Prompts15061495
Mystery Game Puzzles28%65%
Epoch Capabilities Index156.25165.03
ARC-AGI-275.8%—
SimpleBench61.7%—
Kagi LLM Benchmark80.7%—
ARC-AGI-193.5%—
Chess Puzzles30%—
Thematic Generalization72.8%—
EBR-Bench19%—
DTBench94.7%—
LMCA52.2%—
ForecastBench60.3—

Math Claude Sonnet 5.5 leads

Claude Opus 4.7: 66.7 (#26), Claude Sonnet 5.5: 87.9 (#6)

BenchmarkClaude Opus 4.7Claude Sonnet 5.5
FrontierMath (Tiers 1-3)70.2%88.8%
FrontierMath Tier 431.7%80.5%
OTIS Mock AIME 2024-202597.8%100%
ProofBench54%100%
LMArena Math14991510
MathArena Final-Answer Competitions73.6%—
FrontierMath (Feb 2025 set)43.8%—
FrontierMath Erdős—2.9%
FrontierMath Tier 4 (v1)22.9%—

Knowledge Claude Sonnet 5.5 leads

Claude Opus 4.7: 62.6 (#23), Claude Sonnet 5.5: 66.0 (#12)

BenchmarkClaude Opus 4.7Claude Sonnet 5.5
GPQA Diamond90.2%95.6%
SimpleQA Verified51.7%46.5%
LMArena Expert15211540
Humanity's Last Exam36.2%—
Vectara Hallucination Rate12%—

Multimodal Claude Sonnet 5.5 leads

Claude Opus 4.7: 41.2 (#38), Claude Sonnet 5.5: 51.5 (#6)

BenchmarkClaude Opus 4.7Claude Sonnet 5.5
LMArena Vision13161289
Furniture Assembly33.3%75%
Blueprint-Bench 224.5%—
LMArena Document1495—

Multilingual Claude Opus 4.7 leads

Claude Opus 4.7: 57.3 (#10), Claude Sonnet 5.5: 55.3 (#30)

BenchmarkClaude Opus 4.7Claude Sonnet 5.5
LMArena Non-English14801452
LMArena Chinese15311522
LMArena Russian14941451
LMArena French1503—
LMArena German1495—
LMArena Japanese1472—
LMArena Korean1464—
LMArena Spanish1495—

Instruction Following Too close to call

Claude Opus 4.7: 78.4 (#10), Claude Sonnet 5.5: 78.3 (#11)

BenchmarkClaude Opus 4.7Claude Sonnet 5.5
LMArena Instruction Following14981495

Long Context Too close to call

Claude Opus 4.7: 46.2 (#25), Claude Sonnet 5.5: 45.9 (#28)

BenchmarkClaude Opus 4.7Claude Sonnet 5.5
LMArena Longer Query15051498

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.7: 75.1 (#8), Claude Sonnet 5.5: 66.0 (#40)

BenchmarkClaude Opus 4.7Claude Sonnet 5.5
LMArena Text14901471
LMArena Creative Writing14861465
LMArena Multi-Turn15051474
EQ-Bench Creative Writing1914—
EQ-Bench 41311—

Frequently asked questions

Is Claude Opus 4.7 better than Claude Sonnet 5.5?

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 58.3 on the Noometry Index.

Which is cheaper, Claude Opus 4.7 or Claude Sonnet 5.5?

Claude Sonnet 5.5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

Is Claude Opus 4.7 or Claude Sonnet 5.5 better for coding?

Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 59.6 in the Noometry coding category.

Which has the bigger context window?

Both accept 1M tokens.

How many benchmarks do Claude Opus 4.7 and Claude Sonnet 5.5 share?

29 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and Claude Sonnet 5.5 has 32.

Related comparisons

Go deeper