Noometry

Model comparison

Claude Opus 4.5 vs Claude Opus 5

Claude Opus 5 is the stronger model overall, scoring 67.8 to 50.5 on the Noometry Index.

Last verified . 42 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

Claude Opus 5 Anthropic

67.8

Rank #4 Confirmed

Summary

  • They share 42 benchmarks with published results for both. Claude Opus 4.5 scores higher in 0 categories and Claude Opus 5 in 10 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 5 leads 86.2 to 38.6.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 4.9% for Claude Opus 4.5 and 73.2% for Claude Opus 5.
  • Both cost about the same: $5 input and $25 output per million tokens.
  • Claude Opus 5 accepts more context: 1M tokens versus 200K.

Side by side

Claude Opus 4.5Claude Opus 5
ProviderAnthropicAnthropic
Noometry Index50.567.8
Released2025-11-012026-07-24
WeightsProprietaryProprietary
Context window200K1M
Max output64K128K
Input $ / M tokens$5$5
Output $ / M tokens$25$25
Results tracked6957

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

Category by category

Coding Claude Opus 5 leads

Claude Opus 4.5: 54.8 (#27), Claude Opus 5: 67.5 (#5)

BenchmarkClaude Opus 4.5Claude Opus 5
LMArena WebDev14941691
WeirdML63.7%91.8%
LMArena Coding15041534
ALE-Bench1,0252,165
SWE-bench Verified76.7%—
DeepSWE—73.6%
FrontierCode—53.4%
SWE-bench Verified (bash only)76.8%—
CursorBench—46.6%
SWE-bench Multilingual70.7%—
FrontierSWE—52%
SciCode—56.4%
GSO26.5%—
AlgoTune1.77—

Agentic & Tool Use Claude Opus 5 leads

Claude Opus 4.5: 47.3 (#12), Claude Opus 5: 55.6 (#1)

BenchmarkClaude Opus 4.5Claude Opus 5
τ²-bench Banking24.7%48.7%
BALROG43.5%63.4%
Vending-Bench 24,96711,182
Terminal-Bench63.1%—
APEX-Agents—65.8%
Berkeley Function Calling Leaderboard77.5%—
OSWorld 2.0—31.4%
GDPval45.5%—
Remote Labor Index3.8%—
τ²-bench Airline84%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
Cybench82%—
DeepResearch Bench54.8%—
OSWorld66.3%—
PostTrainBench—35%
GBAEval—79.6%
GDP.pdf—24%
LMArena Search1180—
METR Time Horizons75%—

Reasoning Claude Opus 5 leads

Claude Opus 4.5: 42.6 (#51), Claude Opus 5: 77.2 (#4)

BenchmarkClaude Opus 4.5Claude Opus 5
ARC-AGI-237.6%90.4%
SimpleBench62%80.6%
NYT Connections (extended)52.5%94.3%
ARC-AGI-180%97.5%
Chess Puzzles12%42%
EBR-Bench14.3%45.7%
LMArena Hard Prompts14761526
Mystery Game Puzzles22%59%
DTBench89.9%97.9%
LMCA44.5%64.5%
Epoch Capabilities Index150.09162.78
Kagi LLM Benchmark80.2%—
CritPt—29.1%
EnigmaEval11.9%—
Bench to the Future 3—0.12
ForecastBench60.7—

Math Claude Opus 5 leads

Claude Opus 4.5: 38.6 (#132), Claude Opus 5: 86.2 (#8)

BenchmarkClaude Opus 4.5Claude Opus 5
FrontierMath (Tiers 1-3)34.4%85.6%
FrontierMath Tier 44.9%73.2%
OTIS Mock AIME 2024-202586.1%98.9%
ProofBench36%99%
LMArena Math14631531
FrontierMath (Feb 2025 set)20.7%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Claude Opus 5 leads

Claude Opus 4.5: 56.5 (#44), Claude Opus 5: 66.8 (#9)

BenchmarkClaude Opus 4.5Claude Opus 5
GPQA Diamond86%93.9%
SimpleQA Verified45.7%59.9%
LMArena Expert14871557
Humanity's Last Exam25.2%—
Vectara Hallucination Rate10.9%—

Multimodal Claude Opus 5 leads

Claude Opus 4.5: 31.4 (#107), Claude Opus 5: 50.8 (#8)

BenchmarkClaude Opus 4.5Claude Opus 5
Furniture Assembly28.3%60.8%
LMArena Document14621516
LMArena Vision—1319
GeoBench75%—
VPCT40%—
Blueprint-Bench 2—30.4%

Multilingual Claude Opus 5 leads

Claude Opus 4.5: 54.3 (#47), Claude Opus 5: 58.8 (#4)

BenchmarkClaude Opus 4.5Claude Opus 5
LMArena Non-English14381501
LMArena Chinese14701574
LMArena French14711519
LMArena German14491524
LMArena Japanese14161516
LMArena Korean14241521
LMArena Russian14471507
LMArena Spanish14581519

Instruction Following Claude Opus 5 leads

Claude Opus 4.5: 77.5 (#19), Claude Opus 5: 79.2 (#7)

BenchmarkClaude Opus 4.5Claude Opus 5
LMArena Instruction Following14781517

Long Context Too close to call

Claude Opus 4.5: 46.5 (#22), Claude Opus 5: 46.5 (#21)

BenchmarkClaude Opus 4.5Claude Opus 5
LMArena Longer Query14801515
CL-bench21.1%—

Writing & Preference Claude Opus 5 leads

Claude Opus 4.5: 68.1 (#28), Claude Opus 5: 79.2 (#1)

BenchmarkClaude Opus 4.5Claude Opus 5
LMArena Text14511507
LMArena Creative Writing14451491
EQ-Bench Creative Writing16872133
LMArena Multi-Turn14661499
EQ-Bench 4—1385

Frequently asked questions

Is Claude Opus 4.5 better than Claude Opus 5?

Claude Opus 5 is the stronger model overall, scoring 67.8 to 50.5 on the Noometry Index.

Which is cheaper, Claude Opus 4.5 or Claude Opus 5?

Claude Opus 5 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 5 better for coding?

Claude Opus 5 scores higher on coding benchmarks: 67.5 versus 54.8 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 5 does, with 1M tokens against 200K.

How many benchmarks do Claude Opus 4.5 and Claude Opus 5 share?

42 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Claude Opus 5 has 57.

Related comparisons

Go deeper