Noometry

Model comparison

Claude Opus 4.5 vs Claude Opus 4.7

Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 50.5 on the Noometry Index.

Last verified . 51 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

Claude Opus 4.7 Anthropic

58.3

Rank #19 Confirmed

Summary

  • They share 51 benchmarks with published results for both. Claude Opus 4.5 scores higher in 1 category and Claude Opus 4.7 in 9 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4.7 leads 66.7 to 38.6.
  • The biggest single-benchmark swing is ARC-AGI-2: 37.6% for Claude Opus 4.5 and 75.8% for Claude Opus 4.7.
  • Both cost about the same: $5 input and $25 output per million tokens.
  • Claude Opus 4.7 accepts more context: 1M tokens versus 200K.

Side by side

Claude Opus 4.5Claude Opus 4.7
ProviderAnthropicAnthropic
Noometry Index50.558.3
Released2025-11-012026-04-14
WeightsProprietaryProprietary
Context window200K1M
Max output64K128K
Input $ / M tokens$5$5
Output $ / M tokens$25$25
Results tracked6966

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

Category by category

Coding Claude Opus 4.7 leads

Claude Opus 4.5: 54.8 (#27), Claude Opus 4.7: 59.6 (#13)

BenchmarkClaude Opus 4.5Claude Opus 4.7
SWE-bench Verified76.7%83.5%
LMArena WebDev14941558
GSO26.5%44.1%
WeirdML63.7%76.4%
LMArena Coding15041518
ALE-Bench1,0251,323
FrontierCode—38.5%
SWE-bench Verified (bash only)76.8%—
SWE-bench Multilingual70.7%—
SciCode—54.5%
MirrorCode—31.1%
AlgoTune1.77—

Agentic & Tool Use Too close to call

Claude Opus 4.5: 47.3 (#12), Claude Opus 4.7: 47.9 (#10)

BenchmarkClaude Opus 4.5Claude Opus 4.7
Terminal-Bench63.1%80.2%
τ²-bench Banking24.7%40.2%
LMArena Search11801233
Vending-Bench 24,96710,937
APEX-Agents—49.2%
Berkeley Function Calling Leaderboard77.5%—
OSWorld 2.0—18.2%
GDPval45.5%—
Remote Labor Index3.8%—
τ²-bench Airline84%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
Cybench82%—
DeepResearch Bench54.8%—
OSWorld66.3%—
PostTrainBench—28.6%
BALROG43.5%—
ExploitBench—26.5%
GBAEval—43.8%
GDP.pdf—21%
METR Time Horizons75%—

Reasoning Claude Opus 4.7 leads

Claude Opus 4.5: 42.6 (#51), Claude Opus 4.7: 53.8 (#29)

BenchmarkClaude Opus 4.5Claude Opus 4.7
ARC-AGI-237.6%75.8%
SimpleBench62%61.7%
Kagi LLM Benchmark80.2%80.7%
NYT Connections (extended)52.5%39%
ARC-AGI-180%93.5%
Chess Puzzles12%30%
EBR-Bench14.3%19%
LMArena Hard Prompts14761506
Mystery Game Puzzles22%28%
DTBench89.9%94.7%
LMCA44.5%52.2%
Epoch Capabilities Index150.09156.25
ForecastBench60.760.3
CritPt—12%
EnigmaEval11.9%—
Thematic Generalization—72.8%

Math Claude Opus 4.7 leads

Claude Opus 4.5: 38.6 (#132), Claude Opus 4.7: 66.7 (#26)

BenchmarkClaude Opus 4.5Claude Opus 4.7
FrontierMath (Tiers 1-3)34.4%70.2%
FrontierMath Tier 44.9%31.7%
OTIS Mock AIME 2024-202586.1%97.8%
ProofBench36%54%
LMArena Math14631499
FrontierMath (Feb 2025 set)20.7%43.8%
FrontierMath Tier 4 (v1)4.2%22.9%
MathArena Final-Answer Competitions—73.6%

Knowledge Claude Opus 4.7 leads

Claude Opus 4.5: 56.5 (#44), Claude Opus 4.7: 62.6 (#23)

BenchmarkClaude Opus 4.5Claude Opus 4.7
GPQA Diamond86%90.2%
Humanity's Last Exam25.2%36.2%
SimpleQA Verified45.7%51.7%
Vectara Hallucination Rate10.9%12%
LMArena Expert14871521

Multimodal Claude Opus 4.7 leads

Claude Opus 4.5: 31.4 (#107), Claude Opus 4.7: 41.2 (#38)

BenchmarkClaude Opus 4.5Claude Opus 4.7
Furniture Assembly28.3%33.3%
LMArena Document14621495
LMArena Vision—1316
GeoBench75%—
VPCT40%—
Blueprint-Bench 2—24.5%

Multilingual Claude Opus 4.7 leads

Claude Opus 4.5: 54.3 (#47), Claude Opus 4.7: 57.3 (#10)

BenchmarkClaude Opus 4.5Claude Opus 4.7
LMArena Non-English14381480
LMArena Chinese14701531
LMArena French14711503
LMArena German14491495
LMArena Japanese14161472
LMArena Korean14241464
LMArena Russian14471494
LMArena Spanish14581495

Instruction Following Too close to call

Claude Opus 4.5: 77.5 (#19), Claude Opus 4.7: 78.4 (#10)

BenchmarkClaude Opus 4.5Claude Opus 4.7
LMArena Instruction Following14781498

Long Context Too close to call

Claude Opus 4.5: 46.5 (#22), Claude Opus 4.7: 46.2 (#25)

BenchmarkClaude Opus 4.5Claude Opus 4.7
LMArena Longer Query14801505
CL-bench21.1%—

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.5: 68.1 (#28), Claude Opus 4.7: 75.1 (#8)

BenchmarkClaude Opus 4.5Claude Opus 4.7
LMArena Text14511490
LMArena Creative Writing14451486
EQ-Bench Creative Writing16871914
LMArena Multi-Turn14661505
EQ-Bench 4—1311

Frequently asked questions

Is Claude Opus 4.5 better than Claude Opus 4.7?

Claude Opus 4.7 is the stronger model overall, scoring 58.3 to 50.5 on the Noometry Index.

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

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

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

Claude Opus 4.7 scores higher on coding benchmarks: 59.6 versus 54.8 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 Opus 4.5 and Claude Opus 4.7 share?

51 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Claude Opus 4.7 has 66.

Related comparisons

Go deeper