Noometry

Model comparison

Claude Haiku 4.5 vs Claude Opus 4.7

Claude Opus 4.7 is the stronger model overall, scoring 58.3 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 4.7'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 4.7 Anthropic

58.3

Rank #19 Confirmed

Summary

  • They share 42 benchmarks with published results for both. Claude Haiku 4.5 scores higher in 0 categories and Claude Opus 4.7 in 10 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.7 leads 53.8 to 15.1.
  • The biggest single-benchmark swing is ARC-AGI-2: 4% for Claude Haiku 4.5 and 75.8% for Claude Opus 4.7.
  • Claude Haiku 4.5 is cheaper at $1 / $5 per million input/output tokens, against $5 / $25 for Claude Opus 4.7.
  • Claude Opus 4.7 accepts more context: 1M tokens versus 200K.

Side by side

Claude Haiku 4.5Claude Opus 4.7
ProviderAnthropicAnthropic
Noometry Index39.558.3
Released2025-10-152026-04-14
WeightsProprietaryProprietary
Context window200K1M
Max output64K128K
Input $ / M tokens$1$5
Output $ / M tokens$5$25
Results tracked5366

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

Category by category

Coding Claude Opus 4.7 leads

Claude Haiku 4.5: 44.0 (#78), Claude Opus 4.7: 59.6 (#13)

BenchmarkClaude Haiku 4.5Claude Opus 4.7
LMArena WebDev13301558
SciCode43.3%54.5%
WeirdML45.4%76.4%
LMArena Coding14531518
ALE-Bench653.481,323
SWE-bench Verified—83.5%
FrontierCode—38.5%
SWE-bench Verified (bash only)66.6%—
SWE-bench Multilingual64.7%—
GSO—44.1%
MirrorCode—31.1%

Agentic & Tool Use Claude Opus 4.7 leads

Claude Haiku 4.5: 33.6 (#52), Claude Opus 4.7: 47.9 (#10)

BenchmarkClaude Haiku 4.5Claude Opus 4.7
Terminal-Bench35.5%80.2%
ExploitBench13.7%26.5%
Vending-Bench 2458.8910,937
APEX-Agents—49.2%
Berkeley Function Calling Leaderboard68.7%—
OSWorld 2.0—18.2%
τ²-bench Banking—40.2%
DeepResearch Bench45.5%—
PostTrainBench—28.6%
BALROG31.2%—
GBAEval—43.8%
GDP.pdf—21%
LMArena Search—1233

Reasoning Claude Opus 4.7 leads

Claude Haiku 4.5: 15.1 (#320), Claude Opus 4.7: 53.8 (#29)

BenchmarkClaude Haiku 4.5Claude Opus 4.7
ARC-AGI-24%75.8%
NYT Connections (extended)14.3%39%
ARC-AGI-147.7%93.5%
CritPt0%12%
Chess Puzzles8%30%
LMArena Hard Prompts14201506
DTBench73.6%94.7%
LMCA30.9%52.2%
Epoch Capabilities Index142.41156.25
ForecastBench61.460.3
SimpleBench—61.7%
Kagi LLM Benchmark—80.7%
Thematic Generalization—72.8%
EBR-Bench—19%
Mystery Game Puzzles—28%

Math Claude Opus 4.7 leads

Claude Haiku 4.5: 44.9 (#78), Claude Opus 4.7: 66.7 (#26)

BenchmarkClaude Haiku 4.5Claude Opus 4.7
OTIS Mock AIME 2024-202566.7%97.8%
LMArena Math13961499
FrontierMath (Feb 2025 set)5.9%43.8%
FrontierMath Tier 4 (v1)2.1%22.9%
FrontierMath (Tiers 1-3)—70.2%
FrontierMath Tier 4—31.7%
MathArena Final-Answer Competitions—73.6%
ProofBench—54%
Omni-MATH56.1%—
MATH Level 596.4%—

Knowledge Claude Opus 4.7 leads

Claude Haiku 4.5: 37.7 (#153), Claude Opus 4.7: 62.6 (#23)

BenchmarkClaude Haiku 4.5Claude Opus 4.7
GPQA Diamond71.2%90.2%
SimpleQA Verified13.2%51.7%
Vectara Hallucination Rate9.8%12%
LMArena Expert14421521
Humanity's Last Exam—36.2%
MMLU-Pro77.7%—
GPQA (HELM)60.5%—

Multimodal Claude Opus 4.7 leads

Claude Haiku 4.5: 26.8 (#118), Claude Opus 4.7: 41.2 (#38)

BenchmarkClaude Haiku 4.5Claude Opus 4.7
Blueprint-Bench 20%24.5%
LMArena Document14201495
LMArena Vision—1316
Furniture Assembly—33.3%

Multilingual Claude Opus 4.7 leads

Claude Haiku 4.5: 49.9 (#129), Claude Opus 4.7: 57.3 (#10)

BenchmarkClaude Haiku 4.5Claude Opus 4.7
LMArena Non-English13771480
LMArena Chinese14171531
LMArena French14081503
LMArena German13751495
LMArena Japanese13391472
LMArena Korean13471464
LMArena Russian13811494
LMArena Spanish14201495

Instruction Following Claude Opus 4.7 leads

Claude Haiku 4.5: 71.4 (#149), Claude Opus 4.7: 78.4 (#10)

BenchmarkClaude Haiku 4.5Claude Opus 4.7
LMArena Instruction Following14141498
IFEval80.1%—

Long Context Claude Opus 4.7 leads

Claude Haiku 4.5: 43.6 (#92), Claude Opus 4.7: 46.2 (#25)

BenchmarkClaude Haiku 4.5Claude Opus 4.7
LMArena Longer Query14271505

Writing & Preference Claude Opus 4.7 leads

Claude Haiku 4.5: 57.9 (#123), Claude Opus 4.7: 75.1 (#8)

BenchmarkClaude Haiku 4.5Claude Opus 4.7
LMArena Text13961490
LMArena Creative Writing13721486
EQ-Bench 410641311
LMArena Multi-Turn14091505
EQ-Bench Creative Writing—1914
WildBench83.9%—

Frequently asked questions

Is Claude Haiku 4.5 better than Claude Opus 4.7?

Claude Opus 4.7 is the stronger model overall, scoring 58.3 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 4.7's lead doesn't matter for your workload.

Which is cheaper, Claude Haiku 4.5 or Claude Opus 4.7?

Claude Haiku 4.5 is cheaper. It lists at $1 per million input tokens and $5 per million output tokens; Claude Opus 4.7 lists at $5 and $25.

Is Claude Haiku 4.5 or Claude Opus 4.7 better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.6 versus 44.0 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.7 does, with 1M tokens against 200K.

How many benchmarks do Claude Haiku 4.5 and Claude Opus 4.7 share?

42 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Claude Opus 4.7 has 66.

Related comparisons

Go deeper