Noometry

Model comparison

Claude Opus 4.7 vs Claude Sonnet 4.6

Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 50.1 on the Noometry Index. Claude Sonnet 4.6 costs 1.7× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Last verified . 54 shared benchmarks.

Claude Opus 4.7 Anthropic

58.4

Rank #17 Confirmed

Claude Sonnet 4.6 Anthropic

50.1

Rank #42 Confirmed

Summary

  • They share 54 benchmarks with published results for both. Claude Opus 4.7 scores higher in 10 categories and Claude Sonnet 4.6 in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4.7 leads 66.5 to 51.9.
  • The biggest single-benchmark swing is NYT Connections (extended): 39% for Claude Opus 4.7 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 4.7.

Side by side

Claude Opus 4.7Claude Sonnet 4.6
ProviderAnthropicAnthropic
Noometry Index58.450.1
Released2026-04-142026-02-17
WeightsProprietaryProprietary
Context window1M1M
Max output128K128K
Input $ / M tokens$5$3
Output $ / M tokens$25$15
Results tracked6657

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

Category by category

Coding Claude Opus 4.7 leads

Claude Opus 4.7: 59.9 (#10), Claude Sonnet 4.6: 46.0 (#62)

BenchmarkClaude Opus 4.7Claude Sonnet 4.6
SWE-bench Verified83.5%75.2%
FrontierCode38.5%24.3%
LMArena WebDev15571521
SciCode54.5%46.8%
WeirdML76.4%66.1%
LMArena Coding15191504
ALE-Bench1,3231,327
DeepSWE—29.9%
GSO44.1%—
MirrorCode31.1%—

Agentic & Tool Use Claude Opus 4.7 leads

Claude Opus 4.7: 47.9 (#8), Claude Sonnet 4.6: 39.1 (#26)

BenchmarkClaude Opus 4.7Claude Sonnet 4.6
Terminal-Bench80.2%53.4%
APEX-Agents49.2%43%
OSWorld 2.018.2%9.3%
ExploitBench26.5%23.6%
GBAEval43.8%48.8%
GDP.pdf21%18%
LMArena Search12331221
Vending-Bench 210,9377,204
τ²-bench Banking40.2%—
DeepResearch Bench—54.9%
OSWorld—72.1%
PostTrainBench28.6%—

Reasoning Claude Opus 4.7 leads

Claude Opus 4.7: 53.7 (#24), Claude Sonnet 4.6: 46.1 (#40)

BenchmarkClaude Opus 4.7Claude Sonnet 4.6
ARC-AGI-275.8%60.4%
NYT Connections (extended)39%80.9%
ARC-AGI-193.5%86.5%
CritPt12%3.1%
Chess Puzzles30%13%
Thematic Generalization72.8%76.3%
LMArena Hard Prompts15071485
Mystery Game Puzzles28%16%
DTBench94.7%89.9%
LMCA52.2%46.5%
Epoch Capabilities Index156.39152.25
ForecastBench60.362
SimpleBench61.7%—
Kagi LLM Benchmark80.7%—
EBR-Bench19%—

Math Claude Opus 4.7 leads

Claude Opus 4.7: 66.5 (#20), Claude Sonnet 4.6: 51.9 (#41)

BenchmarkClaude Opus 4.7Claude Sonnet 4.6
OTIS Mock AIME 2024-202597.8%85.8%
ProofBench54%45%
LMArena Math14991463
FrontierMath (Feb 2025 set)43.8%32.4%
FrontierMath Tier 4 (v1)22.9%8.3%
FrontierMath (Tiers 1-3)70.2%—
FrontierMath Tier 431.7%—
MathArena Final-Answer Competitions73.6%—

Knowledge Claude Opus 4.7 leads

Claude Opus 4.7: 62.6 (#20), Claude Sonnet 4.6: 51.6 (#60)

BenchmarkClaude Opus 4.7Claude Sonnet 4.6
GPQA Diamond90.2%87.4%
SimpleQA Verified51.7%35.5%
Vectara Hallucination Rate12%10.6%
LMArena Expert15211500
Humanity's Last Exam36.2%—

Multimodal Claude Opus 4.7 leads

Claude Opus 4.7: 41.5 (#29), Claude Sonnet 4.6: 38.0 (#61)

BenchmarkClaude Opus 4.7Claude Sonnet 4.6
LMArena Vision13171283
Blueprint-Bench 224.5%6.7%
LMArena Document14951482
Furniture Assembly33.3%—

Multilingual Claude Opus 4.7 leads

Claude Opus 4.7: 57.5 (#9), Claude Sonnet 4.6: 54.6 (#39)

BenchmarkClaude Opus 4.7Claude Sonnet 4.6
LMArena Non-English14811440
LMArena Chinese15301491
LMArena French15051465
LMArena German14941428
LMArena Japanese14721419
LMArena Korean14661411
LMArena Russian14941440
LMArena Spanish14971465

Instruction Following Too close to call

Claude Opus 4.7: 78.6 (#9), Claude Sonnet 4.6: 77.6 (#23)

BenchmarkClaude Opus 4.7Claude Sonnet 4.6
LMArena Instruction Following14981476

Long Context Too close to call

Claude Opus 4.7: 46.1 (#24), Claude Sonnet 4.6: 45.3 (#40)

BenchmarkClaude Opus 4.7Claude Sonnet 4.6
LMArena Longer Query15051479

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.7: 75.3 (#8), Claude Sonnet 4.6: 70.4 (#22)

BenchmarkClaude Opus 4.7Claude Sonnet 4.6
LMArena Text14911458
LMArena Creative Writing14861435
EQ-Bench Creative Writing19141810
EQ-Bench 413111207
LMArena Multi-Turn15061464

Frequently asked questions

Is Claude Opus 4.7 better than Claude Sonnet 4.6?

Claude Opus 4.7 is the stronger model overall, scoring 58.4 to 50.1 on the Noometry Index. Claude Sonnet 4.6 costs 1.7× less per token, which makes it the better buy when Claude Opus 4.7's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.7 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 4.7 lists at $5 and $25.

Is Claude Opus 4.7 or Claude Sonnet 4.6 better for coding?

Claude Opus 4.7 scores higher on coding benchmarks: 59.9 versus 46.0 in the Noometry coding category.

Which has the bigger context window?

Both accept 1M tokens.

How many benchmarks do Claude Opus 4.7 and Claude Sonnet 4.6 share?

54 benchmarks have published results for both models. Claude Opus 4.7 has 66 scored results on Noometry and Claude Sonnet 4.6 has 57.

Related comparisons

Go deeper