Noometry

Model comparison

Claude Opus 4.6 vs Claude Sonnet 5

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 54.6 on the Noometry Index. Claude Sonnet 5 costs 2.5× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Last verified . 44 shared benchmarks.

Claude Opus 4.6 Anthropic

58.2

Rank #20 Confirmed

Claude Sonnet 5 Anthropic

54.6

Rank #29 Confirmed

Summary

  • They share 44 benchmarks with published results for both. Claude Opus 4.6 scores higher in 8 categories and Claude Sonnet 5 in 2 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.6 leads 57.8 to 49.1.
  • The biggest single-benchmark swing is ProofBench: 50% for Claude Opus 4.6 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 4.6.

Side by side

Claude Opus 4.6Claude Sonnet 5
ProviderAnthropicAnthropic
Noometry Index58.254.6
Released2026-02-042026-06-29
WeightsProprietaryProprietary
Context window1M1M
Max output128K128K
Input $ / M tokens$5$2
Output $ / M tokens$25$10
Results tracked6851

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

Category by category

Coding Claude Opus 4.6 leads

Claude Opus 4.6: 57.2 (#20), Claude Sonnet 5: 55.5 (#26)

BenchmarkClaude Opus 4.6Claude Sonnet 5
FrontierCode26.6%42.7%
LMArena WebDev15471541
GSO41.2%37.3%
WeirdML78%68.8%
LMArena Coding15361483
ALE-Bench996.51,463
SWE-bench Verified78.7%—
DeepSWE—53.8%
SWE-bench Verified (bash only)75.6%—
CursorBench—34.1%
SWE-bench Multilingual72%—
SciCode—54.3%
AlgoTune1.47—

Agentic & Tool Use Claude Opus 4.6 leads

Claude Opus 4.6: 51.1 (#4), Claude Sonnet 5: 42.8 (#18)

BenchmarkClaude Opus 4.6Claude Sonnet 5
APEX-Agents46.3%54.5%
GBAEval44.1%65.3%
LMArena Search12531194
Vending-Bench 28,0186,378
Terminal-Bench79.8%—
Remote Labor Index4.2%—
τ²-bench Banking27.3%—
Cybench93%—
DeepResearch Bench55.3%—
METR Time Horizons78.9%—

Reasoning Claude Opus 4.6 leads

Claude Opus 4.6: 57.8 (#23), Claude Sonnet 5: 49.1 (#39)

BenchmarkClaude Opus 4.6Claude Sonnet 5
SimpleBench67.6%60.6%
NYT Connections (extended)92.1%75.1%
Chess Puzzles17%35%
LMArena Hard Prompts15271461
Mystery Game Puzzles25%35%
DTBench91.2%92.5%
LMCA55.8%50%
Epoch Capabilities Index155.24156.21
ForecastBench6061.1
ARC-AGI-269.2%—
Kagi LLM Benchmark83.6%—
ARC-AGI-194%—
CritPt—16.9%
EnigmaEval7.6%—
Thematic Generalization80.6%—
EBR-Bench12.7%—
Surface Evolver Bench—60%
Bench to the Future 3—0.14

Math Claude Sonnet 5 leads

Claude Opus 4.6: 63.0 (#31), Claude Sonnet 5: 66.2 (#27)

BenchmarkClaude Opus 4.6Claude Sonnet 5
FrontierMath (Tiers 1-3)66%65.6%
FrontierMath Tier 426.8%29.3%
OTIS Mock AIME 2024-202594.4%94.7%
ProofBench50%77%
LMArena Math15191467
MathArena Final-Answer Competitions78.5%—
FrontierMath (Feb 2025 set)40.7%—
FrontierMath Tier 4 (v1)22.9%—

Knowledge Claude Opus 4.6 leads

Claude Opus 4.6: 61.9 (#26), Claude Sonnet 5: 55.6 (#47)

BenchmarkClaude Opus 4.6Claude Sonnet 5
GPQA Diamond90.5%90.5%
SimpleQA Verified47%33.7%
LMArena Expert15461490
Humanity's Last Exam34.4%—
Vectara Hallucination Rate12.2%—

Multimodal Claude Sonnet 5 leads

Claude Opus 4.6: 37.3 (#74), Claude Sonnet 5: 42.4 (#31)

BenchmarkClaude Opus 4.6Claude Sonnet 5
LMArena Vision13161274
LMArena Document15071466
Blueprint-Bench 2—24.9%
Furniture Assembly28.3%—

Multilingual Claude Opus 4.6 leads

Claude Opus 4.6: 57.9 (#6), Claude Sonnet 5: 53.8 (#55)

BenchmarkClaude Opus 4.6Claude Sonnet 5
LMArena Non-English14891431
LMArena Chinese15511477
LMArena French15131460
LMArena German15021440
LMArena Japanese14841422
LMArena Korean14641411
LMArena Russian14971451
LMArena Spanish15101437

Instruction Following Claude Opus 4.6 leads

Claude Opus 4.6: 79.5 (#4), Claude Sonnet 5: 76.3 (#41)

BenchmarkClaude Opus 4.6Claude Sonnet 5
LMArena Instruction Following15231452

Long Context Claude Opus 4.6 leads

Claude Opus 4.6: 48.1 (#13), Claude Sonnet 5: 44.8 (#55)

BenchmarkClaude Opus 4.6Claude Sonnet 5
LMArena Longer Query15201463
CL-bench20.7%—
CL-bench Life17%—

Writing & Preference Claude Opus 4.6 leads

Claude Opus 4.6: 73.5 (#10), Claude Sonnet 5: 69.2 (#25)

BenchmarkClaude Opus 4.6Claude Sonnet 5
LMArena Text15031442
LMArena Creative Writing15051416
EQ-Bench Creative Writing18091794
EQ-Bench 412231236
LMArena Multi-Turn15131454

Frequently asked questions

Is Claude Opus 4.6 better than Claude Sonnet 5?

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 54.6 on the Noometry Index. Claude Sonnet 5 costs 2.5× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.6 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 4.6 lists at $5 and $25.

Is Claude Opus 4.6 or Claude Sonnet 5 better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 55.5 in the Noometry coding category.

Which has the bigger context window?

Both accept 1M tokens.

How many benchmarks do Claude Opus 4.6 and Claude Sonnet 5 share?

44 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and Claude Sonnet 5 has 51.

Related comparisons

Go deeper