Noometry

Model comparison

Claude Opus 4.5 vs Claude Sonnet 5

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 50.5 on the Noometry Index.

Last verified . 39 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

Claude Sonnet 5 Anthropic

54.6

Rank #29 Confirmed

Summary

  • They share 39 benchmarks with published results for both. Claude Opus 4.5 scores higher in 5 categories and Claude Sonnet 5 in 5 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 5 leads 66.2 to 38.6.
  • The biggest single-benchmark swing is ProofBench: 36% for Claude Opus 4.5 and 77% for Claude Sonnet 5.
  • Claude Sonnet 5 is cheaper at $2 / $10 per million input/output tokens, against $5 / $25 for Claude Opus 4.5.
  • Claude Sonnet 5 accepts more context: 1M tokens versus 200K.

Side by side

Claude Opus 4.5Claude Sonnet 5
ProviderAnthropicAnthropic
Noometry Index50.554.6
Released2025-11-012026-06-29
WeightsProprietaryProprietary
Context window200K1M
Max output64K128K
Input $ / M tokens$5$2
Output $ / M tokens$25$10
Results tracked6951

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

Category by category

Coding Too close to call

Claude Opus 4.5: 54.8 (#27), Claude Sonnet 5: 55.5 (#26)

BenchmarkClaude Opus 4.5Claude Sonnet 5
LMArena WebDev14941541
GSO26.5%37.3%
WeirdML63.7%68.8%
LMArena Coding15041483
ALE-Bench1,0251,463
SWE-bench Verified76.7%—
DeepSWE—53.8%
FrontierCode—42.7%
SWE-bench Verified (bash only)76.8%—
CursorBench—34.1%
SWE-bench Multilingual70.7%—
SciCode—54.3%
AlgoTune1.77—

Agentic & Tool Use Claude Opus 4.5 leads

Claude Opus 4.5: 47.3 (#12), Claude Sonnet 5: 42.8 (#18)

BenchmarkClaude Opus 4.5Claude Sonnet 5
LMArena Search11801194
Vending-Bench 24,9676,378
Terminal-Bench63.1%—
APEX-Agents—54.5%
Berkeley Function Calling Leaderboard77.5%—
GDPval45.5%—
Remote Labor Index3.8%—
τ²-bench Airline84%—
τ²-bench Banking24.7%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
Cybench82%—
DeepResearch Bench54.8%—
OSWorld66.3%—
BALROG43.5%—
GBAEval—65.3%
METR Time Horizons75%—

Reasoning Claude Sonnet 5 leads

Claude Opus 4.5: 42.6 (#51), Claude Sonnet 5: 49.1 (#39)

BenchmarkClaude Opus 4.5Claude Sonnet 5
SimpleBench62%60.6%
NYT Connections (extended)52.5%75.1%
Chess Puzzles12%35%
LMArena Hard Prompts14761461
Mystery Game Puzzles22%35%
DTBench89.9%92.5%
LMCA44.5%50%
Epoch Capabilities Index150.09156.21
ForecastBench60.761.1
ARC-AGI-237.6%—
Kagi LLM Benchmark80.2%—
ARC-AGI-180%—
CritPt—16.9%
EnigmaEval11.9%—
EBR-Bench14.3%—
Surface Evolver Bench—60%
Bench to the Future 3—0.14

Math Claude Sonnet 5 leads

Claude Opus 4.5: 38.6 (#132), Claude Sonnet 5: 66.2 (#27)

BenchmarkClaude Opus 4.5Claude Sonnet 5
FrontierMath (Tiers 1-3)34.4%65.6%
FrontierMath Tier 44.9%29.3%
OTIS Mock AIME 2024-202586.1%94.7%
ProofBench36%77%
LMArena Math14631467
FrontierMath (Feb 2025 set)20.7%—
FrontierMath Tier 4 (v1)4.2%—

Knowledge Too close to call

Claude Opus 4.5: 56.5 (#44), Claude Sonnet 5: 55.6 (#47)

BenchmarkClaude Opus 4.5Claude Sonnet 5
GPQA Diamond86%90.5%
SimpleQA Verified45.7%33.7%
LMArena Expert14871490
Humanity's Last Exam25.2%—
Vectara Hallucination Rate10.9%—

Multimodal Claude Sonnet 5 leads

Claude Opus 4.5: 31.4 (#107), Claude Sonnet 5: 42.4 (#31)

BenchmarkClaude Opus 4.5Claude Sonnet 5
LMArena Document14621466
LMArena Vision—1274
GeoBench75%—
VPCT40%—
Blueprint-Bench 2—24.9%
Furniture Assembly28.3%—

Multilingual Too close to call

Claude Opus 4.5: 54.3 (#47), Claude Sonnet 5: 53.8 (#55)

BenchmarkClaude Opus 4.5Claude Sonnet 5
LMArena Non-English14381431
LMArena Chinese14701477
LMArena French14711460
LMArena German14491440
LMArena Japanese14161422
LMArena Korean14241411
LMArena Russian14471451
LMArena Spanish14581437

Instruction Following Claude Opus 4.5 leads

Claude Opus 4.5: 77.5 (#19), Claude Sonnet 5: 76.3 (#41)

BenchmarkClaude Opus 4.5Claude Sonnet 5
LMArena Instruction Following14781452

Long Context Claude Opus 4.5 leads

Claude Opus 4.5: 46.5 (#22), Claude Sonnet 5: 44.8 (#55)

BenchmarkClaude Opus 4.5Claude Sonnet 5
LMArena Longer Query14801463
CL-bench21.1%—

Writing & Preference Claude Sonnet 5 leads

Claude Opus 4.5: 68.1 (#28), Claude Sonnet 5: 69.2 (#25)

BenchmarkClaude Opus 4.5Claude Sonnet 5
LMArena Text14511442
LMArena Creative Writing14451416
EQ-Bench Creative Writing16871794
LMArena Multi-Turn14661454
EQ-Bench 4—1236

Frequently asked questions

Is Claude Opus 4.5 better than Claude Sonnet 5?

Claude Sonnet 5 is the stronger model overall, scoring 54.6 to 50.5 on the Noometry Index.

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

Claude Sonnet 5 is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

Is Claude Opus 4.5 or Claude Sonnet 5 better for coding?

They score almost the same on coding (54.8 vs 55.5); test both on your own repository before choosing.

Which has the bigger context window?

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

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

39 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Claude Sonnet 5 has 51.

Related comparisons

Go deeper