Noometry

Model comparison

Claude Opus 4.5 vs Claude Opus 4.6

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 50.5 on the Noometry Index.

Last verified . 60 shared benchmarks.

Claude Opus 4.5 Anthropic

50.5

Rank #47 Confirmed

Claude Opus 4.6 Anthropic

58.2

Rank #20 Confirmed

Summary

  • They share 60 benchmarks with published results for both. Claude Opus 4.5 scores higher in 0 categories and Claude Opus 4.6 in 10 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4.6 leads 63.0 to 38.6.
  • The biggest single-benchmark swing is NYT Connections (extended): 52.5% for Claude Opus 4.5 and 92.1% for Claude Opus 4.6.
  • Both cost about the same: $5 input and $25 output per million tokens.
  • Claude Opus 4.6 accepts more context: 1M tokens versus 200K.

Side by side

Claude Opus 4.5Claude Opus 4.6
ProviderAnthropicAnthropic
Noometry Index50.558.2
Released2025-11-012026-02-04
WeightsProprietaryProprietary
Context window200K1M
Max output64K128K
Input $ / M tokens$5$5
Output $ / M tokens$25$25
Results tracked6968

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

Category by category

Coding Claude Opus 4.6 leads

Claude Opus 4.5: 54.8 (#27), Claude Opus 4.6: 57.2 (#20)

BenchmarkClaude Opus 4.5Claude Opus 4.6
SWE-bench Verified76.7%78.7%
SWE-bench Verified (bash only)76.8%75.6%
LMArena WebDev14941547
SWE-bench Multilingual70.7%72%
GSO26.5%41.2%
WeirdML63.7%78%
LMArena Coding15041536
ALE-Bench1,025996.5
AlgoTune1.771.47
FrontierCode—26.6%

Agentic & Tool Use Claude Opus 4.6 leads

Claude Opus 4.5: 47.3 (#12), Claude Opus 4.6: 51.1 (#4)

BenchmarkClaude Opus 4.5Claude Opus 4.6
Terminal-Bench63.1%79.8%
Remote Labor Index3.8%4.2%
τ²-bench Banking24.7%27.3%
Cybench82%93%
DeepResearch Bench54.8%55.3%
LMArena Search11801253
METR Time Horizons75%78.9%
Vending-Bench 24,9678,018
APEX-Agents—46.3%
Berkeley Function Calling Leaderboard77.5%—
GDPval45.5%—
τ²-bench Airline84%—
τ²-bench Retail79.6%—
τ²-bench Telecom92.3%—
OSWorld66.3%—
BALROG43.5%—
GBAEval—44.1%

Reasoning Claude Opus 4.6 leads

Claude Opus 4.5: 42.6 (#51), Claude Opus 4.6: 57.8 (#23)

BenchmarkClaude Opus 4.5Claude Opus 4.6
ARC-AGI-237.6%69.2%
SimpleBench62%67.6%
Kagi LLM Benchmark80.2%83.6%
NYT Connections (extended)52.5%92.1%
ARC-AGI-180%94%
Chess Puzzles12%17%
EnigmaEval11.9%7.6%
EBR-Bench14.3%12.7%
LMArena Hard Prompts14761527
Mystery Game Puzzles22%25%
DTBench89.9%91.2%
LMCA44.5%55.8%
Epoch Capabilities Index150.09155.24
ForecastBench60.760
Thematic Generalization—80.6%

Math Claude Opus 4.6 leads

Claude Opus 4.5: 38.6 (#132), Claude Opus 4.6: 63.0 (#31)

BenchmarkClaude Opus 4.5Claude Opus 4.6
FrontierMath (Tiers 1-3)34.4%66%
FrontierMath Tier 44.9%26.8%
OTIS Mock AIME 2024-202586.1%94.4%
ProofBench36%50%
LMArena Math14631519
FrontierMath (Feb 2025 set)20.7%40.7%
FrontierMath Tier 4 (v1)4.2%22.9%
MathArena Final-Answer Competitions—78.5%

Knowledge Claude Opus 4.6 leads

Claude Opus 4.5: 56.5 (#44), Claude Opus 4.6: 61.9 (#26)

BenchmarkClaude Opus 4.5Claude Opus 4.6
GPQA Diamond86%90.5%
Humanity's Last Exam25.2%34.4%
SimpleQA Verified45.7%47%
Vectara Hallucination Rate10.9%12.2%
LMArena Expert14871546

Multimodal Claude Opus 4.6 leads

Claude Opus 4.5: 31.4 (#107), Claude Opus 4.6: 37.3 (#74)

BenchmarkClaude Opus 4.5Claude Opus 4.6
Furniture Assembly28.3%28.3%
LMArena Document14621507
LMArena Vision—1316
GeoBench75%—
VPCT40%—

Multilingual Claude Opus 4.6 leads

Claude Opus 4.5: 54.3 (#47), Claude Opus 4.6: 57.9 (#6)

BenchmarkClaude Opus 4.5Claude Opus 4.6
LMArena Non-English14381489
LMArena Chinese14701551
LMArena French14711513
LMArena German14491502
LMArena Japanese14161484
LMArena Korean14241464
LMArena Russian14471497
LMArena Spanish14581510

Instruction Following Claude Opus 4.6 leads

Claude Opus 4.5: 77.5 (#19), Claude Opus 4.6: 79.5 (#4)

BenchmarkClaude Opus 4.5Claude Opus 4.6
LMArena Instruction Following14781523

Long Context Claude Opus 4.6 leads

Claude Opus 4.5: 46.5 (#22), Claude Opus 4.6: 48.1 (#13)

BenchmarkClaude Opus 4.5Claude Opus 4.6
CL-bench21.1%20.7%
LMArena Longer Query14801520
CL-bench Life—17%

Writing & Preference Claude Opus 4.6 leads

Claude Opus 4.5: 68.1 (#28), Claude Opus 4.6: 73.5 (#10)

BenchmarkClaude Opus 4.5Claude Opus 4.6
LMArena Text14511503
LMArena Creative Writing14451505
EQ-Bench Creative Writing16871809
LMArena Multi-Turn14661513
EQ-Bench 4—1223

Frequently asked questions

Is Claude Opus 4.5 better than Claude Opus 4.6?

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 50.5 on the Noometry Index.

Which is cheaper, Claude Opus 4.5 or Claude Opus 4.6?

Claude Opus 4.6 is cheaper. It lists at $5 per million input tokens and $25 per million output tokens; Claude Opus 4.5 lists at $5 and $25.

Is Claude Opus 4.5 or Claude Opus 4.6 better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 54.8 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.6 does, with 1M tokens against 200K.

How many benchmarks do Claude Opus 4.5 and Claude Opus 4.6 share?

60 benchmarks have published results for both models. Claude Opus 4.5 has 69 scored results on Noometry and Claude Opus 4.6 has 68.

Related comparisons

Go deeper