Noometry

Model comparison

Claude Opus 4.6 vs Claude Opus 4.7

Claude Opus 4.6 and Claude Opus 4.7 score almost the same on the Noometry Index (58.2 vs 58.3), so choose on price, context window or the category you care about most.

Last verified . 58 shared benchmarks.

Claude Opus 4.6 Anthropic

58.2

Rank #20 Confirmed

Claude Opus 4.7 Anthropic

58.3

Rank #19 Confirmed

Summary

  • They share 58 benchmarks with published results for both. Claude Opus 4.6 scores higher in 5 categories and Claude Opus 4.7 in 5 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.6 leads 57.8 to 53.8.
  • The biggest single-benchmark swing is NYT Connections (extended): 92.1% for Claude Opus 4.6 and 39% for Claude Opus 4.7.
  • Both cost about the same: $5 input and $25 output per million tokens.

Side by side

Claude Opus 4.6Claude Opus 4.7
ProviderAnthropicAnthropic
Noometry Index58.258.3
Released2026-02-042026-04-14
WeightsProprietaryProprietary
Context window1M1M
Max output128K128K
Input $ / M tokens$5$5
Output $ / M tokens$25$25
Results tracked6866

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

Category by category

Coding Claude Opus 4.7 leads

Claude Opus 4.6: 57.2 (#20), Claude Opus 4.7: 59.6 (#13)

BenchmarkClaude Opus 4.6Claude Opus 4.7
SWE-bench Verified78.7%83.5%
FrontierCode26.6%38.5%
LMArena WebDev15471558
GSO41.2%44.1%
WeirdML78%76.4%
LMArena Coding15361518
ALE-Bench996.51,323
SWE-bench Verified (bash only)75.6%—
SWE-bench Multilingual72%—
SciCode—54.5%
MirrorCode—31.1%
AlgoTune1.47—

Agentic & Tool Use Claude Opus 4.6 leads

Claude Opus 4.6: 51.1 (#4), Claude Opus 4.7: 47.9 (#10)

BenchmarkClaude Opus 4.6Claude Opus 4.7
Terminal-Bench79.8%80.2%
APEX-Agents46.3%49.2%
τ²-bench Banking27.3%40.2%
GBAEval44.1%43.8%
LMArena Search12531233
Vending-Bench 28,01810,937
OSWorld 2.0—18.2%
Remote Labor Index4.2%—
Cybench93%—
DeepResearch Bench55.3%—
PostTrainBench—28.6%
ExploitBench—26.5%
GDP.pdf—21%
METR Time Horizons78.9%—

Reasoning Claude Opus 4.6 leads

Claude Opus 4.6: 57.8 (#23), Claude Opus 4.7: 53.8 (#29)

BenchmarkClaude Opus 4.6Claude Opus 4.7
ARC-AGI-269.2%75.8%
SimpleBench67.6%61.7%
Kagi LLM Benchmark83.6%80.7%
NYT Connections (extended)92.1%39%
ARC-AGI-194%93.5%
Chess Puzzles17%30%
Thematic Generalization80.6%72.8%
EBR-Bench12.7%19%
LMArena Hard Prompts15271506
Mystery Game Puzzles25%28%
DTBench91.2%94.7%
LMCA55.8%52.2%
Epoch Capabilities Index155.24156.25
ForecastBench6060.3
CritPt—12%
EnigmaEval7.6%—

Math Claude Opus 4.7 leads

Claude Opus 4.6: 63.0 (#31), Claude Opus 4.7: 66.7 (#26)

BenchmarkClaude Opus 4.6Claude Opus 4.7
FrontierMath (Tiers 1-3)66%70.2%
FrontierMath Tier 426.8%31.7%
MathArena Final-Answer Competitions78.5%73.6%
OTIS Mock AIME 2024-202594.4%97.8%
ProofBench50%54%
LMArena Math15191499
FrontierMath (Feb 2025 set)40.7%43.8%
FrontierMath Tier 4 (v1)22.9%22.9%

Knowledge Too close to call

Claude Opus 4.6: 61.9 (#26), Claude Opus 4.7: 62.6 (#23)

BenchmarkClaude Opus 4.6Claude Opus 4.7
GPQA Diamond90.5%90.2%
Humanity's Last Exam34.4%36.2%
SimpleQA Verified47%51.7%
Vectara Hallucination Rate12.2%12%
LMArena Expert15461521

Multimodal Claude Opus 4.7 leads

Claude Opus 4.6: 37.3 (#74), Claude Opus 4.7: 41.2 (#38)

BenchmarkClaude Opus 4.6Claude Opus 4.7
LMArena Vision13161316
Furniture Assembly28.3%33.3%
LMArena Document15071495
Blueprint-Bench 2—24.5%

Multilingual Too close to call

Claude Opus 4.6: 57.9 (#6), Claude Opus 4.7: 57.3 (#10)

BenchmarkClaude Opus 4.6Claude Opus 4.7
LMArena Non-English14891480
LMArena Chinese15511531
LMArena French15131503
LMArena German15021495
LMArena Japanese14841472
LMArena Korean14641464
LMArena Russian14971494
LMArena Spanish15101495

Instruction Following Claude Opus 4.6 leads

Claude Opus 4.6: 79.5 (#4), Claude Opus 4.7: 78.4 (#10)

BenchmarkClaude Opus 4.6Claude Opus 4.7
LMArena Instruction Following15231498

Long Context Claude Opus 4.6 leads

Claude Opus 4.6: 48.1 (#13), Claude Opus 4.7: 46.2 (#25)

BenchmarkClaude Opus 4.6Claude Opus 4.7
LMArena Longer Query15201505
CL-bench20.7%—
CL-bench Life17%—

Writing & Preference Claude Opus 4.7 leads

Claude Opus 4.6: 73.5 (#10), Claude Opus 4.7: 75.1 (#8)

BenchmarkClaude Opus 4.6Claude Opus 4.7
LMArena Text15031490
LMArena Creative Writing15051486
EQ-Bench Creative Writing18091914
EQ-Bench 412231311
LMArena Multi-Turn15131505

Frequently asked questions

Is Claude Opus 4.6 better than Claude Opus 4.7?

Claude Opus 4.6 and Claude Opus 4.7 score almost the same on the Noometry Index (58.2 vs 58.3), so choose on price, context window or the category you care about most.

Which is cheaper, Claude Opus 4.6 or Claude Opus 4.7?

Claude Opus 4.7 is cheaper. It lists at $5 per million input tokens and $25 per million output tokens; Claude Opus 4.6 lists at $5 and $25.

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

Claude Opus 4.7 scores higher on coding benchmarks: 59.6 versus 57.2 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 Opus 4.7 share?

58 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and Claude Opus 4.7 has 66.

Related comparisons

Go deeper