Noometry

Model comparison

Claude Opus 4.5 vs Claude Sonnet 4.5

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 44.0 on the Noometry Index. Claude Sonnet 4.5 costs 1.7× less per token, which makes it the better buy when Claude Opus 4.5's lead doesn't matter for your workload.

Last verified . 65 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #39 Confirmed

Claude Sonnet 4.5 Anthropic

44.0

Rank #76 Confirmed

Summary

  • They share 65 benchmarks with published results for both. Claude Opus 4.5 scores higher in 9 categories and Claude Sonnet 4.5 in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.5 leads 42.5 to 26.9.
  • The biggest single-benchmark swing is ARC-AGI-2: 37.6% for Claude Opus 4.5 and 13.6% for Claude Sonnet 4.5.
  • Claude Sonnet 4.5 is cheaper at $3 / $15 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
  • Claude Sonnet 4.5 accepts more context: 1M tokens versus 200K.

Side by side

Claude Opus 4.5Claude Sonnet 4.5
ProviderAnthropicAnthropic
Noometry Index50.544.0
Released2025-11-012025-09-29
WeightsProprietaryProprietary
Context window200K1M
Max output64K64K
Input $ / M tokens$5$3
Output $ / M tokens$25$15
Results tracked6973

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

Category by category

Coding Claude Opus 4.5 leads

Claude Opus 4.5: 55.4 (#21), Claude Sonnet 4.5: 47.8 (#54)

BenchmarkClaude Opus 4.5Claude Sonnet 4.5
SWE-bench Verified76.7%71.3%
SWE-bench Verified (bash only)76.8%71.4%
LMArena WebDev14931393
SWE-bench Multilingual70.7%67%
GSO26.5%14.7%
WeirdML63.7%47.7%
LMArena Coding15041489
ALE-Bench1,025796.15
AlgoTune1.771.52
SciCode—44.7%

Agentic & Tool Use Claude Opus 4.5 leads

Claude Opus 4.5: 47.2 (#11), Claude Sonnet 4.5: 38.1 (#30)

BenchmarkClaude Opus 4.5Claude Sonnet 4.5
Terminal-Bench63.1%46.5%
Berkeley Function Calling Leaderboard77.5%73.2%
GDPval45.5%42.5%
Remote Labor Index3.8%2.1%
τ²-bench Airline84%72%
τ²-bench Banking24.7%25.3%
τ²-bench Retail79.6%72.4%
τ²-bench Telecom92.3%84.9%
Cybench82%60%
DeepResearch Bench54.8%52.6%
OSWorld66.3%62.9%
LMArena Search11801159
METR Time Horizons75%67.4%
Vending-Bench 24,9673,839
BALROG43.5%—

Reasoning Claude Opus 4.5 leads

Claude Opus 4.5: 42.5 (#43), Claude Sonnet 4.5: 26.9 (#113)

BenchmarkClaude Opus 4.5Claude Sonnet 4.5
ARC-AGI-237.6%13.6%
SimpleBench62%54.3%
Kagi LLM Benchmark80.2%57.9%
NYT Connections (extended)52.5%37.3%
ARC-AGI-180%63.7%
Chess Puzzles12%12%
EnigmaEval11.9%6%
EBR-Bench14.3%2.4%
LMArena Hard Prompts14761462
Mystery Game Puzzles22%17%
DTBench89.9%83.2%
LMCA44.5%38.8%
Epoch Capabilities Index150.1146.84
ForecastBench60.761.9
CritPt—1.1%

Math Claude Opus 4.5 leads

Claude Opus 4.5: 38.5 (#85), Claude Sonnet 4.5: 31.9 (#190)

BenchmarkClaude Opus 4.5Claude Sonnet 4.5
FrontierMath (Tiers 1-3)34.4%23.9%
FrontierMath Tier 44.9%2.4%
OTIS Mock AIME 2024-202586.1%77.8%
ProofBench36%19%
LMArena Math14631448
FrontierMath (Feb 2025 set)20.7%15.2%
FrontierMath Tier 4 (v1)4.2%4.2%
Omni-MATH—55.3%
MATH Level 5—97.7%

Knowledge Claude Opus 4.5 leads

Claude Opus 4.5: 56.4 (#38), Claude Sonnet 4.5: 48.4 (#70)

BenchmarkClaude Opus 4.5Claude Sonnet 4.5
GPQA Diamond86%82.3%
Humanity's Last Exam25.2%13.7%
SimpleQA Verified45.7%30.7%
Vectara Hallucination Rate10.9%12%
LMArena Expert14881483
MMLU-Pro—86.9%
GPQA (HELM)—68.6%

Multimodal Claude Sonnet 4.5 leads

Claude Opus 4.5: 31.1 (#99), Claude Sonnet 4.5: 34.1 (#84)

BenchmarkClaude Opus 4.5Claude Sonnet 4.5
VPCT40%39.8%
LMArena Document14621450
GeoBench75%—
Furniture Assembly28.3%—

Multilingual Too close to call

Claude Opus 4.5: 54.5 (#45), Claude Sonnet 4.5: 53.6 (#65)

BenchmarkClaude Opus 4.5Claude Sonnet 4.5
LMArena Non-English14381425
LMArena Chinese14701459
LMArena French14711459
LMArena German14491427
LMArena Japanese14151390
LMArena Korean14241403
LMArena Russian14481436
LMArena Spanish14551457

Instruction Following Claude Opus 4.5 leads

Claude Opus 4.5: 77.7 (#20), Claude Sonnet 4.5: 75.2 (#74)

BenchmarkClaude Opus 4.5Claude Sonnet 4.5
LMArena Instruction Following14781459
IFEval—85%

Long Context Claude Opus 4.5 leads

Claude Opus 4.5: 46.4 (#21), Claude Sonnet 4.5: 45.2 (#45)

BenchmarkClaude Opus 4.5Claude Sonnet 4.5
LMArena Longer Query14801476
CL-bench21.1%—

Writing & Preference Claude Opus 4.5 leads

Claude Opus 4.5: 68.2 (#28), Claude Sonnet 4.5: 66.7 (#33)

BenchmarkClaude Opus 4.5Claude Sonnet 4.5
LMArena Text14511439
LMArena Creative Writing14451442
EQ-Bench Creative Writing16871678
LMArena Multi-Turn14661465
WildBench—85.4%

Frequently asked questions

Is Claude Opus 4.5 better than Claude Sonnet 4.5?

Claude Opus 4.5 is the stronger model overall, scoring 50.5 to 44.0 on the Noometry Index. Claude Sonnet 4.5 costs 1.7× 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 Opus 4.5 or Claude Sonnet 4.5?

Claude Sonnet 4.5 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

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

Claude Opus 4.5 scores higher on coding benchmarks: 55.4 versus 47.8 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.5 does, with 1M tokens against 200K.

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

65 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Claude Sonnet 4.5 has 73.

Related comparisons

Go deeper