Noometry

Model comparison

Claude Opus 4.5 vs Claude Opus 5.5

Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 50.5 on the Noometry Index.

Last verified . 33 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

Claude Opus 5.5 Anthropic

68.6

Rank #3 Confirmed

Summary

  • They share 33 benchmarks with published results for both. Claude Opus 4.5 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 math, where Claude Opus 5.5 leads 91.8 to 38.6.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 4.9% for Claude Opus 4.5 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 4.5.
  • Claude Opus 5.5 accepts more context: 1M tokens versus 200K.

Side by side

Claude Opus 4.5Claude Opus 5.5
ProviderAnthropicAnthropic
Noometry Index50.568.6
Released2025-11-012026-09-22
WeightsProprietaryProprietary
Context window200K1M
Max output64K128K
Input $ / M tokens$5$4
Output $ / M tokens$25$20
Results tracked6944

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

Category by category

Coding Claude Opus 5.5 leads

Claude Opus 4.5: 54.8 (#27), Claude Opus 5.5: 71.9 (#3)

BenchmarkClaude Opus 4.5Claude Opus 5.5
LMArena WebDev14941813
LMArena Coding15041547
ALE-Bench1,0252,147
SWE-bench Verified76.7%—
FrontierCode—54.6%
SWE-bench Verified (bash only)76.8%—
CursorBench—57.8%
SWE-bench Multilingual70.7%—
FrontierSWE—62.3%
SciCode—66.9%
GSO26.5%—
WeirdML63.7%—
MirrorCode—77.4%
AlgoTune1.77—

Agentic & Tool Use Claude Opus 4.5 leads

Claude Opus 4.5: 47.3 (#12), Claude Opus 5.5: 45.3 (#15)

BenchmarkClaude Opus 4.5Claude Opus 5.5
Vending-Bench 24,9679,235
Terminal-Bench63.1%—
APEX-Agents—73.5%
Berkeley Function Calling Leaderboard77.5%—
GDPval45.5%—
Remote Labor Index3.8%—
τ²-bench Airline84%—
τ²-bench Banking24.7%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
Cybench82%—
DeepResearch Bench54.8%—
OSWorld66.3%—
BALROG43.5%—
GDP.pdf—30.6%
LMArena Search1180—
METR Time Horizons75%—

Reasoning Claude Opus 5.5 leads

Claude Opus 4.5: 42.6 (#51), Claude Opus 5.5: 80.2 (#3)

BenchmarkClaude Opus 4.5Claude Opus 5.5
ARC-AGI-237.6%93.3%
NYT Connections (extended)52.5%88.5%
ARC-AGI-180%98.5%
EBR-Bench14.3%71.4%
LMArena Hard Prompts14761535
Mystery Game Puzzles22%71%
DTBench89.9%98.9%
LMCA44.5%68.2%
Epoch Capabilities Index150.09167.33
SimpleBench62%—
Kagi LLM Benchmark80.2%—
CritPt—31.7%
Chess Puzzles12%—
EnigmaEval11.9%—
ForecastBench60.7—

Math Claude Opus 5.5 leads

Claude Opus 4.5: 38.6 (#132), Claude Opus 5.5: 91.8 (#3)

BenchmarkClaude Opus 4.5Claude Opus 5.5
FrontierMath (Tiers 1-3)34.4%91.2%
FrontierMath Tier 44.9%95%
OTIS Mock AIME 2024-202586.1%100%
ProofBench36%100%
LMArena Math14631506
FrontierMath (Feb 2025 set)20.7%—
FrontierMath Erdős—2.9%
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Opus 5.5 leads

Claude Opus 4.5: 56.5 (#44), Claude Opus 5.5: 66.4 (#10)

BenchmarkClaude Opus 4.5Claude Opus 5.5
GPQA Diamond86%90.6%
SimpleQA Verified45.7%72.2%
LMArena Expert14871547
Humanity's Last Exam25.2%—
Vectara Hallucination Rate10.9%—

Multimodal Claude Opus 5.5 leads

Claude Opus 4.5: 31.4 (#107), Claude Opus 5.5: 57.8 (#1)

BenchmarkClaude Opus 4.5Claude Opus 5.5
Furniture Assembly28.3%83.3%
LMArena Vision—1321
GeoBench75%—
VPCT40%—
Blueprint-Bench 2—51.2%
LMArena Document1462—

Multilingual Claude Opus 5.5 leads

Claude Opus 4.5: 54.3 (#47), Claude Opus 5.5: 59.1 (#2)

BenchmarkClaude Opus 4.5Claude Opus 5.5
LMArena Non-English14381507
LMArena Chinese14701588
LMArena French14711514
LMArena Russian14471520
LMArena Spanish14581507
LMArena German1449—
LMArena Japanese1416—
LMArena Korean1424—

Instruction Following Claude Opus 5.5 leads

Claude Opus 4.5: 77.5 (#19), Claude Opus 5.5: 80.0 (#3)

BenchmarkClaude Opus 4.5Claude Opus 5.5
LMArena Instruction Following14781537

Long Context Too close to call

Claude Opus 4.5: 46.5 (#22), Claude Opus 5.5: 47.1 (#19)

BenchmarkClaude Opus 4.5Claude Opus 5.5
LMArena Longer Query14801532
CL-bench21.1%—

Writing & Preference Claude Opus 5.5 leads

Claude Opus 4.5: 68.1 (#28), Claude Opus 5.5: 78.2 (#3)

BenchmarkClaude Opus 4.5Claude Opus 5.5
LMArena Text14511515
LMArena Creative Writing14451533
EQ-Bench Creative Writing16872050
LMArena Multi-Turn14661499

Frequently asked questions

Is Claude Opus 4.5 better than Claude Opus 5.5?

Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 50.5 on the Noometry Index.

Which is cheaper, Claude Opus 4.5 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 4.5 lists at $5 and $25.

Is Claude Opus 4.5 or Claude Opus 5.5 better for coding?

Claude Opus 5.5 scores higher on coding benchmarks: 71.9 versus 54.8 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 5.5 does, with 1M tokens against 200K.

How many benchmarks do Claude Opus 4.5 and Claude Opus 5.5 share?

33 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Claude Opus 5.5 has 44.

Related comparisons

Go deeper