Noometry

Model comparison

Claude Opus 4.7 vs Claude Opus 5.5

Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 58.3 on the Noometry Index.

Last verified . 41 shared benchmarks.

Claude Opus 4.7 Anthropic

58.3

Rank #19 Confirmed

Claude Opus 5.5 Anthropic

68.6

Rank #3 Confirmed

Summary

  • They share 41 benchmarks with published results for both. Claude Opus 4.7 scores higher in 1 category and Claude Opus 5.5 in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 5.5 leads 80.2 to 53.8.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 31.7% for Claude Opus 4.7 and 95% for Claude Opus 5.5.
  • Claude Opus 5.5 is cheaper at $4 / $20 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.

Side by side

Claude Opus 4.7Claude Opus 5.5
ProviderAnthropicAnthropic
Noometry Index58.368.6
Released2026-04-142026-09-22
WeightsProprietaryProprietary
Context window1M1M
Max output128K128K
Input $ / M tokens$5$4
Output $ / M tokens$25$20
Results tracked6644

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

Category by category

Coding Claude Opus 5.5 leads

Claude Opus 4.7: 59.6 (#13), Claude Opus 5.5: 71.9 (#3)

BenchmarkClaude Opus 4.7Claude Opus 5.5
FrontierCode38.5%54.6%
LMArena WebDev15581813
SciCode54.5%66.9%
LMArena Coding15181547
MirrorCode31.1%77.4%
ALE-Bench1,3232,147
SWE-bench Verified83.5%—
CursorBench—57.8%
FrontierSWE—62.3%
GSO44.1%—
WeirdML76.4%—

Agentic & Tool Use Claude Opus 4.7 leads

Claude Opus 4.7: 47.9 (#10), Claude Opus 5.5: 45.3 (#15)

BenchmarkClaude Opus 4.7Claude Opus 5.5
APEX-Agents49.2%73.5%
GDP.pdf21%30.6%
Vending-Bench 210,9379,235
Terminal-Bench80.2%—
OSWorld 2.018.2%—
τ²-bench Banking40.2%—
PostTrainBench28.6%—
ExploitBench26.5%—
GBAEval43.8%—
LMArena Search1233—

Reasoning Claude Opus 5.5 leads

Claude Opus 4.7: 53.8 (#29), Claude Opus 5.5: 80.2 (#3)

BenchmarkClaude Opus 4.7Claude Opus 5.5
ARC-AGI-275.8%93.3%
NYT Connections (extended)39%88.5%
ARC-AGI-193.5%98.5%
CritPt12%31.7%
EBR-Bench19%71.4%
LMArena Hard Prompts15061535
Mystery Game Puzzles28%71%
DTBench94.7%98.9%
LMCA52.2%68.2%
Epoch Capabilities Index156.25167.33
SimpleBench61.7%—
Kagi LLM Benchmark80.7%—
Chess Puzzles30%—
Thematic Generalization72.8%—
ForecastBench60.3—

Math Claude Opus 5.5 leads

Claude Opus 4.7: 66.7 (#26), Claude Opus 5.5: 91.8 (#3)

BenchmarkClaude Opus 4.7Claude Opus 5.5
FrontierMath (Tiers 1-3)70.2%91.2%
FrontierMath Tier 431.7%95%
OTIS Mock AIME 2024-202597.8%100%
ProofBench54%100%
LMArena Math14991506
MathArena Final-Answer Competitions73.6%—
FrontierMath (Feb 2025 set)43.8%—
FrontierMath Erdős—2.9%
FrontierMath Tier 4 (v1)22.9%—

Knowledge Claude Opus 5.5 leads

Claude Opus 4.7: 62.6 (#23), Claude Opus 5.5: 66.4 (#10)

BenchmarkClaude Opus 4.7Claude Opus 5.5
GPQA Diamond90.2%90.6%
SimpleQA Verified51.7%72.2%
LMArena Expert15211547
Humanity's Last Exam36.2%—
Vectara Hallucination Rate12%—

Multimodal Claude Opus 5.5 leads

Claude Opus 4.7: 41.2 (#38), Claude Opus 5.5: 57.8 (#1)

BenchmarkClaude Opus 4.7Claude Opus 5.5
LMArena Vision13161321
Blueprint-Bench 224.5%51.2%
Furniture Assembly33.3%83.3%
LMArena Document1495—

Multilingual Claude Opus 5.5 leads

Claude Opus 4.7: 57.3 (#10), Claude Opus 5.5: 59.1 (#2)

BenchmarkClaude Opus 4.7Claude Opus 5.5
LMArena Non-English14801507
LMArena Chinese15311588
LMArena French15031514
LMArena Russian14941520
LMArena Spanish14951507
LMArena German1495—
LMArena Japanese1472—
LMArena Korean1464—

Instruction Following Claude Opus 5.5 leads

Claude Opus 4.7: 78.4 (#10), Claude Opus 5.5: 80.0 (#3)

BenchmarkClaude Opus 4.7Claude Opus 5.5
LMArena Instruction Following14981537

Long Context Too close to call

Claude Opus 4.7: 46.2 (#25), Claude Opus 5.5: 47.1 (#19)

BenchmarkClaude Opus 4.7Claude Opus 5.5
LMArena Longer Query15051532

Writing & Preference Claude Opus 5.5 leads

Claude Opus 4.7: 75.1 (#8), Claude Opus 5.5: 78.2 (#3)

BenchmarkClaude Opus 4.7Claude Opus 5.5
LMArena Text14901515
LMArena Creative Writing14861533
EQ-Bench Creative Writing19142050
LMArena Multi-Turn15051499
EQ-Bench 41311—

Frequently asked questions

Is Claude Opus 4.7 better than Claude Opus 5.5?

Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 58.3 on the Noometry Index.

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

Claude Opus 5.5 is cheaper. It lists at $4 per million input tokens and $20 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

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

Claude Opus 5.5 scores higher on coding benchmarks: 71.9 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 Opus 5.5 share?

41 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and Claude Opus 5.5 has 44.

Related comparisons

Go deeper