Noometry

Model comparison

Claude Opus 4.8 vs Claude Sonnet 4

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 40.8 on the Noometry Index. Claude Sonnet 4 costs 1.7× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.

Last verified . 38 shared benchmarks.

Claude Opus 4.8 Anthropic

60.7

Rank #13 Confirmed

Claude Sonnet 4 Anthropic

40.8

Rank #145 Confirmed

Summary

  • They share 38 benchmarks with published results for both. Claude Opus 4.8 scores higher in 10 categories and Claude Sonnet 4 in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Opus 4.8 leads 64.7 to 22.9.
  • The biggest single-benchmark swing is ARC-AGI-2: 72.1% for Claude Opus 4.8 and 5.9% for Claude Sonnet 4.
  • Claude Sonnet 4 is cheaper at $3 / $15 per million input/output tokens, against $5 / $25 for Claude Opus 4.8.
  • Claude Opus 4.8 accepts more context: 1M tokens versus 200K.

Side by side

Claude Opus 4.8Claude Sonnet 4
ProviderAnthropicAnthropic
Noometry Index60.740.8
Released2026-05-282025-05-22
WeightsProprietaryProprietary
Context window1M200K
Max output128K64K
Input $ / M tokens$5$3
Output $ / M tokens$25$15
Results tracked6558

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

Category by category

Coding Claude Opus 4.8 leads

Claude Opus 4.8: 59.9 (#12), Claude Sonnet 4: 43.5 (#88)

BenchmarkClaude Opus 4.8Claude Sonnet 4
SciCode53.5%40%
GSO47.1%4.9%
WeirdML82.9%46.1%
LMArena Coding14901414
ALE-Bench1,564655.35
DeepSWE59%—
FrontierCode46.5%—
SWE-bench Verified (bash only)—64.9%
Aider Polyglot—61.3%
LMArena WebDev1556—

Agentic & Tool Use Claude Opus 4.8 leads

Claude Opus 4.8: 47.6 (#11), Claude Sonnet 4: 38.5 (#31)

BenchmarkClaude Opus 4.8Claude Sonnet 4
DeepResearch Bench50.2%46.6%
APEX-Agents48.9%—
OSWorld 2.020.6%—
Remote Labor Index8.3%—
TheAgentCompany—33.1%
τ²-bench Banking39.7%—
Cybench—35%
OSWorld—43.9%
PostTrainBench33.8%—
GBAEval70.9%—
GDP.pdf24%—
LMArena Search1204—
METR Time Horizons—62%
Vending-Bench 25,787—

Reasoning Claude Opus 4.8 leads

Claude Opus 4.8: 64.7 (#16), Claude Sonnet 4: 22.9 (#187)

BenchmarkClaude Opus 4.8Claude Sonnet 4
ARC-AGI-272.1%5.9%
SimpleBench64.8%45.5%
Kagi LLM Benchmark88.8%73%
ARC-AGI-192.5%40%
CritPt20.9%0.3%
EnigmaEval23.5%3.1%
LMArena Hard Prompts14821372
DTBench94.9%77.1%
LMCA57.5%29%
Epoch Capabilities Index158.21141.69
ForecastBench59.960.2
NYT Connections (extended)91.1%—
Chess Puzzles34%—
EBR-Bench28.6%—
Mystery Game Puzzles36%—
Surface Evolver Bench87.5%—
Bench to the Future 30.14—

Math Claude Opus 4.8 leads

Claude Opus 4.8: 78.4 (#13), Claude Sonnet 4: 43.3 (#80)

BenchmarkClaude Opus 4.8Claude Sonnet 4
OTIS Mock AIME 2024-202598.3%71.1%
LMArena Math14871375
FrontierMath (Feb 2025 set)47.2%4.1%
FrontierMath Tier 4 (v1)31.3%0%
FrontierMath (Tiers 1-3)80%—
FrontierMath Tier 456.1%—
MathArena Final-Answer Competitions91.8%—
ProofBench69%—
Omni-MATH—60.2%
MATH Level 5—84.4%

Knowledge Claude Opus 4.8 leads

Claude Opus 4.8: 61.3 (#29), Claude Sonnet 4: 41.8 (#108)

BenchmarkClaude Opus 4.8Claude Sonnet 4
GPQA Diamond91%79.2%
LMArena Expert15021372
Humanity's Last Exam—7.8%
SimpleQA Verified53%—
MMLU-Pro—84.3%
Confabulations—13.2%
Vectara Hallucination Rate—10.3%
GPQA (HELM)—70.6%

Multimodal Claude Opus 4.8 leads

Claude Opus 4.8: 42.9 (#26), Claude Sonnet 4: 26.2 (#121)

BenchmarkClaude Opus 4.8Claude Sonnet 4
LMArena Vision12941191
GeoBench—37%
VPCT—34%
Blueprint-Bench 214.5%—
Furniture Assembly42.5%—
LMArena Document1475—
MindCube—44.8%

Multilingual Claude Opus 4.8 leads

Claude Opus 4.8: 55.2 (#33), Claude Sonnet 4: 46.7 (#156)

BenchmarkClaude Opus 4.8Claude Sonnet 4
LMArena Non-English14501333
LMArena Chinese15071350
LMArena French14811363
LMArena German14721331
LMArena Japanese14401302
LMArena Korean14321291
LMArena Russian14741355
LMArena Spanish14661357

Instruction Following Claude Opus 4.8 leads

Claude Opus 4.8: 77.4 (#24), Claude Sonnet 4: 71.7 (#145)

BenchmarkClaude Opus 4.8Claude Sonnet 4
LMArena Instruction Following14761376
IFEval—84%

Long Context Claude Opus 4.8 leads

Claude Opus 4.8: 45.4 (#35), Claude Sonnet 4: 33.7 (#259)

BenchmarkClaude Opus 4.8Claude Sonnet 4
LMArena Longer Query14831398
Fiction.LiveBench—46.9%

Writing & Preference Claude Opus 4.8 leads

Claude Opus 4.8: 72.0 (#16), Claude Sonnet 4: 57.1 (#132)

BenchmarkClaude Opus 4.8Claude Sonnet 4
LMArena Text14611351
LMArena Creative Writing14541345
EQ-Bench Creative Writing18401483
LMArena Multi-Turn14761376
Short-Story Creative Writing—81.4%
WildBench—83.8%
EQ-Bench 41281—

Frequently asked questions

Is Claude Opus 4.8 better than Claude Sonnet 4?

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 40.8 on the Noometry Index. Claude Sonnet 4 costs 1.7× less per token, which makes it the better buy when Claude Opus 4.8's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.8 or Claude Sonnet 4?

Claude Sonnet 4 is cheaper. It lists at $3 per million input tokens and $15 per million output tokens; Claude Opus 4.8 lists at $5 and $25.

Is Claude Opus 4.8 or Claude Sonnet 4 better for coding?

Claude Opus 4.8 scores higher on coding benchmarks: 59.9 versus 43.5 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.8 does, with 1M tokens against 200K.

How many benchmarks do Claude Opus 4.8 and Claude Sonnet 4 share?

38 benchmarks have published results for both models. Claude Opus 4.8 has 65 scored results on Noometry and Claude Sonnet 4 has 58.

Related comparisons

Go deeper