Noometry

Model comparison

Claude Opus 4.5 vs Claude Sonnet 4.6

Claude Opus 4.5 and Claude Sonnet 4.6 score almost the same on the Noometry Index (50.5 vs 50.3), so choose on price, context window or the category you care about most.

Last verified . 44 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

Summary

  • They share 44 benchmarks with published results for both. Claude Opus 4.5 scores higher in 5 categories and Claude Sonnet 4.6 in 5 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 4.6 leads 52.9 to 38.6.
  • The biggest single-benchmark swing is NYT Connections (extended): 52.5% for Claude Opus 4.5 and 80.9% for Claude Sonnet 4.6.
  • Claude Sonnet 4.6 is cheaper at $3 / $15 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
  • Claude Sonnet 4.6 accepts more context: 1M tokens versus 200K.

Side by side

Claude Opus 4.5Claude Sonnet 4.6
ProviderAnthropicAnthropic
Noometry Index50.550.3
Released2025-11-012026-02-17
WeightsProprietaryProprietary
Context window200K1M
Max output64K128K
Input $ / M tokens$5$3
Output $ / M tokens$25$15
Results tracked6957

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: 54.8 (#27), Claude Sonnet 4.6: 46.3 (#67)

BenchmarkClaude Opus 4.5Claude Sonnet 4.6
SWE-bench Verified76.7%75.2%
LMArena WebDev14941522
WeirdML63.7%66.1%
LMArena Coding15041504
ALE-Bench1,0251,327
DeepSWE—29.9%
FrontierCode—24.3%
SWE-bench Verified (bash only)76.8%—
SWE-bench Multilingual70.7%—
SciCode—46.8%
GSO26.5%—
AlgoTune1.77—

Agentic & Tool Use Claude Opus 4.5 leads

Claude Opus 4.5: 47.3 (#12), Claude Sonnet 4.6: 39.1 (#28)

BenchmarkClaude Opus 4.5Claude Sonnet 4.6
Terminal-Bench63.1%53.4%
DeepResearch Bench54.8%54.9%
OSWorld66.3%72.1%
LMArena Search11801221
Vending-Bench 24,9677,204
APEX-Agents—43%
Berkeley Function Calling Leaderboard77.5%—
OSWorld 2.0—9.3%
GDPval45.5%—
Remote Labor Index3.8%—
τ²-bench Airline84%—
τ²-bench Banking24.7%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
Cybench82%—
BALROG43.5%—
ExploitBench—23.6%
GBAEval—48.8%
GDP.pdf—18%
METR Time Horizons75%—

Reasoning Claude Sonnet 4.6 leads

Claude Opus 4.5: 42.6 (#51), Claude Sonnet 4.6: 46.1 (#45)

BenchmarkClaude Opus 4.5Claude Sonnet 4.6
ARC-AGI-237.6%60.4%
NYT Connections (extended)52.5%80.9%
ARC-AGI-180%86.5%
Chess Puzzles12%13%
LMArena Hard Prompts14761484
Mystery Game Puzzles22%16%
DTBench89.9%89.9%
LMCA44.5%46.5%
Epoch Capabilities Index150.09152.24
ForecastBench60.762
SimpleBench62%—
Kagi LLM Benchmark80.2%—
CritPt—3.1%
EnigmaEval11.9%—
Thematic Generalization—76.3%
EBR-Bench14.3%—

Math Claude Sonnet 4.6 leads

Claude Opus 4.5: 38.6 (#132), Claude Sonnet 4.6: 52.9 (#49)

BenchmarkClaude Opus 4.5Claude Sonnet 4.6
OTIS Mock AIME 2024-202586.1%85.8%
ProofBench36%45%
LMArena Math14631462
FrontierMath (Feb 2025 set)20.7%32.4%
FrontierMath Tier 4 (v1)4.2%8.3%
FrontierMath (Tiers 1-3)34.4%—
FrontierMath Tier 44.9%—

Knowledge Claude Opus 4.5 leads

Claude Opus 4.5: 56.5 (#44), Claude Sonnet 4.6: 51.7 (#65)

BenchmarkClaude Opus 4.5Claude Sonnet 4.6
GPQA Diamond86%87.4%
SimpleQA Verified45.7%35.5%
Vectara Hallucination Rate10.9%10.6%
LMArena Expert14871500
Humanity's Last Exam25.2%—

Multimodal Claude Sonnet 4.6 leads

Claude Opus 4.5: 31.4 (#107), Claude Sonnet 4.6: 38.0 (#68)

BenchmarkClaude Opus 4.5Claude Sonnet 4.6
LMArena Document14621482
LMArena Vision—1283
GeoBench75%—
VPCT40%—
Blueprint-Bench 2—6.7%
Furniture Assembly28.3%—

Multilingual Too close to call

Claude Opus 4.5: 54.3 (#47), Claude Sonnet 4.6: 54.4 (#41)

BenchmarkClaude Opus 4.5Claude Sonnet 4.6
LMArena Non-English14381440
LMArena Chinese14701491
LMArena French14711465
LMArena German14491428
LMArena Japanese14161420
LMArena Korean14241411
LMArena Russian14471440
LMArena Spanish14581464

Instruction Following Too close to call

Claude Opus 4.5: 77.5 (#19), Claude Sonnet 4.6: 77.4 (#25)

BenchmarkClaude Opus 4.5Claude Sonnet 4.6
LMArena Instruction Following14781475

Long Context Claude Opus 4.5 leads

Claude Opus 4.5: 46.5 (#22), Claude Sonnet 4.6: 45.3 (#44)

BenchmarkClaude Opus 4.5Claude Sonnet 4.6
LMArena Longer Query14801479
CL-bench21.1%—

Writing & Preference Claude Sonnet 4.6 leads

Claude Opus 4.5: 68.1 (#28), Claude Sonnet 4.6: 70.2 (#22)

BenchmarkClaude Opus 4.5Claude Sonnet 4.6
LMArena Text14511458
LMArena Creative Writing14451435
EQ-Bench Creative Writing16871810
LMArena Multi-Turn14661464
EQ-Bench 4—1207

Frequently asked questions

Is Claude Opus 4.5 better than Claude Sonnet 4.6?

Claude Opus 4.5 and Claude Sonnet 4.6 score almost the same on the Noometry Index (50.5 vs 50.3), so choose on price, context window or the category you care about most.

Which is cheaper, Claude Opus 4.5 or Claude Sonnet 4.6?

Claude Sonnet 4.6 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 4.6 better for coding?

Claude Opus 4.5 scores higher on coding benchmarks: 54.8 versus 46.3 in the Noometry coding category.

Which has the bigger context window?

Claude Sonnet 4.6 does, with 1M tokens against 200K.

How many benchmarks do Claude Opus 4.5 and Claude Sonnet 4.6 share?

44 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Claude Sonnet 4.6 has 57.

Related comparisons

Go deeper