Noometry

Model comparison

Claude Haiku 4.5 vs Claude Opus 4.5

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 39.5 on the Noometry Index. Claude Haiku 4.5 costs 5.0× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Last verified . 42 shared benchmarks.

Claude Haiku 4.5 Anthropic

39.5

Rank #165 Confirmed

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

Summary

  • They share 42 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 1 category and Claude Opus 4.5 in 9 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.5 leads 42.6 to 15.1.
  • The biggest single-benchmark swing is NYT Connections (extended): 14.3% for Claude Haiku 4.5 and 52.5% for Claude Opus 4.5.
  • Claude Haiku 4.5 is cheaper at $1 / $5 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.

Side by side

Claude Haiku 4.5Claude Opus 4.5
ProviderAnthropicAnthropic
Noometry Index39.550.5
Released2025-10-152025-11-01
WeightsProprietaryProprietary
Context window200K200K
Max output64K64K
Input $ / M tokens$1$5
Output $ / M tokens$5$25
Results tracked5369

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

Category by category

Coding Claude Opus 4.5 leads

Claude Haiku 4.5: 44.0 (#78), Claude Opus 4.5: 54.8 (#27)

BenchmarkClaude Haiku 4.5Claude Opus 4.5
SWE-bench Verified (bash only)66.6%76.8%
LMArena WebDev13301494
SWE-bench Multilingual64.7%70.7%
WeirdML45.4%63.7%
LMArena Coding14531504
ALE-Bench653.481,025
SWE-bench Verified—76.7%
SciCode43.3%—
GSO—26.5%
AlgoTune—1.77

Agentic & Tool Use Claude Opus 4.5 leads

Claude Haiku 4.5: 33.6 (#52), Claude Opus 4.5: 47.3 (#12)

BenchmarkClaude Haiku 4.5Claude Opus 4.5
Terminal-Bench35.5%63.1%
Berkeley Function Calling Leaderboard68.7%77.5%
DeepResearch Bench45.5%54.8%
BALROG31.2%43.5%
Vending-Bench 2458.894,967
GDPval—45.5%
Remote Labor Index—3.8%
τ²-bench Airline—84%
τ²-bench Banking—24.7%
τ²-bench Retail—79.6%
τ²-bench Telecom—92.3%
Cybench—82%
OSWorld—66.3%
ExploitBench13.7%—
LMArena Search—1180
METR Time Horizons—75%

Reasoning Claude Opus 4.5 leads

Claude Haiku 4.5: 15.1 (#320), Claude Opus 4.5: 42.6 (#51)

BenchmarkClaude Haiku 4.5Claude Opus 4.5
ARC-AGI-24%37.6%
NYT Connections (extended)14.3%52.5%
ARC-AGI-147.7%80%
Chess Puzzles8%12%
LMArena Hard Prompts14201476
DTBench73.6%89.9%
LMCA30.9%44.5%
Epoch Capabilities Index142.41150.09
ForecastBench61.460.7
SimpleBench—62%
Kagi LLM Benchmark—80.2%
CritPt0%—
EnigmaEval—11.9%
EBR-Bench—14.3%
Mystery Game Puzzles—22%

Math Claude Haiku 4.5 leads

Claude Haiku 4.5: 44.9 (#78), Claude Opus 4.5: 38.6 (#132)

BenchmarkClaude Haiku 4.5Claude Opus 4.5
OTIS Mock AIME 2024-202566.7%86.1%
LMArena Math13961463
FrontierMath (Feb 2025 set)5.9%20.7%
FrontierMath Tier 4 (v1)2.1%4.2%
FrontierMath (Tiers 1-3)—34.4%
FrontierMath Tier 4—4.9%
ProofBench—36%
Omni-MATH56.1%—
MATH Level 596.4%—

Knowledge Claude Opus 4.5 leads

Claude Haiku 4.5: 37.7 (#153), Claude Opus 4.5: 56.5 (#44)

BenchmarkClaude Haiku 4.5Claude Opus 4.5
GPQA Diamond71.2%86%
SimpleQA Verified13.2%45.7%
Vectara Hallucination Rate9.8%10.9%
LMArena Expert14421487
Humanity's Last Exam—25.2%
MMLU-Pro77.7%—
GPQA (HELM)60.5%—

Multimodal Claude Opus 4.5 leads

Claude Haiku 4.5: 26.8 (#118), Claude Opus 4.5: 31.4 (#107)

BenchmarkClaude Haiku 4.5Claude Opus 4.5
LMArena Document14201462
GeoBench—75%
VPCT—40%
Blueprint-Bench 20%—
Furniture Assembly—28.3%

Multilingual Claude Opus 4.5 leads

Claude Haiku 4.5: 49.9 (#129), Claude Opus 4.5: 54.3 (#47)

BenchmarkClaude Haiku 4.5Claude Opus 4.5
LMArena Non-English13771438
LMArena Chinese14171470
LMArena French14081471
LMArena German13751449
LMArena Japanese13391416
LMArena Korean13471424
LMArena Russian13811447
LMArena Spanish14201458

Instruction Following Claude Opus 4.5 leads

Claude Haiku 4.5: 71.4 (#149), Claude Opus 4.5: 77.5 (#19)

BenchmarkClaude Haiku 4.5Claude Opus 4.5
LMArena Instruction Following14141478
IFEval80.1%—

Long Context Claude Opus 4.5 leads

Claude Haiku 4.5: 43.6 (#92), Claude Opus 4.5: 46.5 (#22)

BenchmarkClaude Haiku 4.5Claude Opus 4.5
LMArena Longer Query14271480
CL-bench—21.1%

Writing & Preference Claude Opus 4.5 leads

Claude Haiku 4.5: 57.9 (#123), Claude Opus 4.5: 68.1 (#28)

BenchmarkClaude Haiku 4.5Claude Opus 4.5
LMArena Text13961451
LMArena Creative Writing13721445
LMArena Multi-Turn14091466
EQ-Bench Creative Writing—1687
WildBench83.9%—
EQ-Bench 41064—

Frequently asked questions

Is Claude Haiku 4.5 better than Claude Opus 4.5?

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 39.5 on the Noometry Index. Claude Haiku 4.5 costs 5.0× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Which is cheaper, Claude Haiku 4.5 or Claude Opus 4.5?

Claude Haiku 4.5 is cheaper. It lists at $1 per million input tokens and $5 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

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

Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 44.0 in the Noometry coding category.

Which has the bigger context window?

Both accept 200K tokens.

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

42 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Claude Opus 4.5 has 69.

Related comparisons

Go deeper