Noometry

Model comparison

Claude Opus 4.6 vs Claude Sonnet 4.6

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 50.3 on the Noometry Index. Claude Sonnet 4.6 costs 1.7× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Last verified . 49 shared benchmarks.

Claude Opus 4.6 Anthropic

58.2

Rank #20 Confirmed

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

Summary

  • They share 49 benchmarks with published results for both. Claude Opus 4.6 scores higher in 9 categories and Claude Sonnet 4.6 in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Claude Opus 4.6 leads 51.1 to 39.1.
  • The biggest single-benchmark swing is Terminal-Bench: 79.8% for Claude Opus 4.6 and 53.4% 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 4.6.

Side by side

Claude Opus 4.6Claude Sonnet 4.6
ProviderAnthropicAnthropic
Noometry Index58.250.3
Released2026-02-042026-02-17
WeightsProprietaryProprietary
Context window1M1M
Max output128K128K
Input $ / M tokens$5$3
Output $ / M tokens$25$15
Results tracked6857

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 4.6: 46.3 (#67)

BenchmarkClaude Opus 4.6Claude Sonnet 4.6
SWE-bench Verified78.7%75.2%
FrontierCode26.6%24.3%
LMArena WebDev15471522
WeirdML78%66.1%
LMArena Coding15361504
ALE-Bench996.51,327
DeepSWE—29.9%
SWE-bench Verified (bash only)75.6%—
SWE-bench Multilingual72%—
SciCode—46.8%
GSO41.2%—
AlgoTune1.47—

Agentic & Tool Use Claude Opus 4.6 leads

Claude Opus 4.6: 51.1 (#4), Claude Sonnet 4.6: 39.1 (#28)

BenchmarkClaude Opus 4.6Claude Sonnet 4.6
Terminal-Bench79.8%53.4%
APEX-Agents46.3%43%
DeepResearch Bench55.3%54.9%
GBAEval44.1%48.8%
LMArena Search12531221
Vending-Bench 28,0187,204
OSWorld 2.0—9.3%
Remote Labor Index4.2%—
τ²-bench Banking27.3%—
Cybench93%—
OSWorld—72.1%
ExploitBench—23.6%
GDP.pdf—18%
METR Time Horizons78.9%—

Reasoning Claude Opus 4.6 leads

Claude Opus 4.6: 57.8 (#23), Claude Sonnet 4.6: 46.1 (#45)

BenchmarkClaude Opus 4.6Claude Sonnet 4.6
ARC-AGI-269.2%60.4%
NYT Connections (extended)92.1%80.9%
ARC-AGI-194%86.5%
Chess Puzzles17%13%
Thematic Generalization80.6%76.3%
LMArena Hard Prompts15271484
Mystery Game Puzzles25%16%
DTBench91.2%89.9%
LMCA55.8%46.5%
Epoch Capabilities Index155.24152.24
ForecastBench6062
SimpleBench67.6%—
Kagi LLM Benchmark83.6%—
CritPt—3.1%
EnigmaEval7.6%—
EBR-Bench12.7%—

Math Claude Opus 4.6 leads

Claude Opus 4.6: 63.0 (#31), Claude Sonnet 4.6: 52.9 (#49)

BenchmarkClaude Opus 4.6Claude Sonnet 4.6
OTIS Mock AIME 2024-202594.4%85.8%
ProofBench50%45%
LMArena Math15191462
FrontierMath (Feb 2025 set)40.7%32.4%
FrontierMath Tier 4 (v1)22.9%8.3%
FrontierMath (Tiers 1-3)66%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions78.5%—

Knowledge Claude Opus 4.6 leads

Claude Opus 4.6: 61.9 (#26), Claude Sonnet 4.6: 51.7 (#65)

BenchmarkClaude Opus 4.6Claude Sonnet 4.6
GPQA Diamond90.5%87.4%
SimpleQA Verified47%35.5%
Vectara Hallucination Rate12.2%10.6%
LMArena Expert15461500
Humanity's Last Exam34.4%—

Multimodal Too close to call

Claude Opus 4.6: 37.3 (#74), Claude Sonnet 4.6: 38.0 (#68)

BenchmarkClaude Opus 4.6Claude Sonnet 4.6
LMArena Vision13161283
LMArena Document15071482
Blueprint-Bench 2—6.7%
Furniture Assembly28.3%—

Multilingual Claude Opus 4.6 leads

Claude Opus 4.6: 57.9 (#6), Claude Sonnet 4.6: 54.4 (#41)

BenchmarkClaude Opus 4.6Claude Sonnet 4.6
LMArena Non-English14891440
LMArena Chinese15511491
LMArena French15131465
LMArena German15021428
LMArena Japanese14841420
LMArena Korean14641411
LMArena Russian14971440
LMArena Spanish15101464

Instruction Following Claude Opus 4.6 leads

Claude Opus 4.6: 79.5 (#4), Claude Sonnet 4.6: 77.4 (#25)

BenchmarkClaude Opus 4.6Claude Sonnet 4.6
LMArena Instruction Following15231475

Long Context Claude Opus 4.6 leads

Claude Opus 4.6: 48.1 (#13), Claude Sonnet 4.6: 45.3 (#44)

BenchmarkClaude Opus 4.6Claude Sonnet 4.6
LMArena Longer Query15201479
CL-bench20.7%—
CL-bench Life17%—

Writing & Preference Claude Opus 4.6 leads

Claude Opus 4.6: 73.5 (#10), Claude Sonnet 4.6: 70.2 (#22)

BenchmarkClaude Opus 4.6Claude Sonnet 4.6
LMArena Text15031458
LMArena Creative Writing15051435
EQ-Bench Creative Writing18091810
EQ-Bench 412231207
LMArena Multi-Turn15131464

Frequently asked questions

Is Claude Opus 4.6 better than Claude Sonnet 4.6?

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 50.3 on the Noometry Index. Claude Sonnet 4.6 costs 1.7× 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 4.6?

Claude Sonnet 4.6 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; Claude Opus 4.6 lists at $5 and $25.

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

Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 46.3 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 4.6 share?

49 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and Claude Sonnet 4.6 has 57.

Related comparisons

Go deeper