Noometry

Model comparison

Claude 3.5 Sonnet vs Claude Opus 4.8

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 34.6 on the Noometry Index.

Last verified . 30 shared benchmarks.

Claude 3.5 Sonnet Anthropic

34.6

Rank #231 Confirmed

Claude Opus 4.8 Anthropic

60.7

Rank #13 Confirmed

Summary

  • They share 30 benchmarks with published results for both. Claude 3.5 Sonnet scores higher in 0 categories and Claude Opus 4.8 in 10 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Opus 4.8 leads 78.4 to 19.2.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 8.5% for Claude 3.5 Sonnet and 98.3% for Claude Opus 4.8.

Side by side

Claude 3.5 SonnetClaude Opus 4.8
ProviderAnthropicAnthropic
Noometry Index34.660.7
Released2024-06-202026-05-28
WeightsProprietaryProprietary
Context window—1M
Max output—128K
Input $ / M tokens—$5
Output $ / M tokens—$25
Results tracked6065

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

Category by category

Coding Claude Opus 4.8 leads

Claude 3.5 Sonnet: 39.0 (#165), Claude Opus 4.8: 59.9 (#12)

BenchmarkClaude 3.5 SonnetClaude Opus 4.8
GSO4.6%47.1%
WeirdML40%82.9%
LMArena Coding13421490
DeepSWE—59%
FrontierCode—46.5%
Aider Polyglot51.6%—
LMArena WebDev—1556
SciCode—53.5%
BigCodeBench Instruct46.8%—
LiveBench Coding67.1%—
BigCodeBench Complete58.6%—
CadEval48%—
ALE-Bench—1,564
HumanEval+81.7%—
MBPP+74.3%—

Agentic & Tool Use Claude Opus 4.8 leads

Claude 3.5 Sonnet: 32.3 (#67), Claude Opus 4.8: 47.6 (#11)

BenchmarkClaude 3.5 SonnetClaude Opus 4.8
APEX-Agents—48.9%
OSWorld 2.0—20.6%
Remote Labor Index—8.3%
TheAgentCompany24%—
τ²-bench Banking—39.7%
Cybench17.5%—
DeepResearch Bench—50.2%
PostTrainBench—33.8%
BALROG32.6%—
GBAEval—70.9%
GDP.pdf—24%
LMArena Search—1204
METR Time Horizons45.2%—
Vending-Bench 2—5,787

Reasoning Claude Opus 4.8 leads

Claude 3.5 Sonnet: 23.1 (#183), Claude Opus 4.8: 64.7 (#16)

BenchmarkClaude 3.5 SonnetClaude Opus 4.8
SimpleBench41.4%64.8%
EnigmaEval0.9%23.5%
LMArena Hard Prompts13051482
DTBench67.8%94.9%
Epoch Capabilities Index133.55158.21
ForecastBench60.759.9
ARC-AGI-2—72.1%
Kagi LLM Benchmark—88.8%
NYT Connections (extended)—91.1%
ARC-AGI-1—92.5%
CritPt—20.9%
Chess Puzzles—34%
EBR-Bench—28.6%
LiveBench Reasoning56.7%—
Mystery Game Puzzles—36%
LiveBench Data Analysis55%—
LMCA—57.5%
Surface Evolver Bench—87.5%
Bench to the Future 3—0.14
LiveBench59%—

Math Claude Opus 4.8 leads

Claude 3.5 Sonnet: 19.2 (#288), Claude Opus 4.8: 78.4 (#13)

BenchmarkClaude 3.5 SonnetClaude Opus 4.8
OTIS Mock AIME 2024-20258.5%98.3%
LMArena Math13071487
FrontierMath (Feb 2025 set)2.1%47.2%
FrontierMath Tier 4 (v1)0%31.3%
FrontierMath (Tiers 1-3)—80%
FrontierMath Tier 4—56.1%
MathArena Final-Answer Competitions—91.8%
ProofBench—69%
Omni-MATH27.6%—
LiveBench Math52.3%—
MATH Level 556.9%—

Knowledge Claude Opus 4.8 leads

Claude 3.5 Sonnet: 28.6 (#245), Claude Opus 4.8: 61.3 (#29)

BenchmarkClaude 3.5 SonnetClaude Opus 4.8
GPQA Diamond55.3%91%
LMArena Expert12651502
Humanity's Last Exam4.1%—
SimpleQA Verified—53%
MMLU-Pro77.7%—
Confabulations19.9%—
GPQA (HELM)56.5%—
MMLU87.3%—

Multimodal Claude Opus 4.8 leads

Claude 3.5 Sonnet: 26.5 (#120), Claude Opus 4.8: 42.9 (#26)

BenchmarkClaude 3.5 SonnetClaude Opus 4.8
LMArena Vision11251294
Video-MME60%—
GeoBench62%—
VPCT33%—
Blueprint-Bench 2—14.5%
Furniture Assembly—42.5%
LMArena Document—1475

Multilingual Claude Opus 4.8 leads

Claude 3.5 Sonnet: 43.2 (#185), Claude Opus 4.8: 55.2 (#33)

BenchmarkClaude 3.5 SonnetClaude Opus 4.8
LMArena Non-English12831450
LMArena Chinese12721507
LMArena French13051481
LMArena German12971472
LMArena Japanese12341440
LMArena Korean12001432
LMArena Russian13061474
LMArena Spanish12901466

Instruction Following Claude Opus 4.8 leads

Claude 3.5 Sonnet: 68.8 (#182), Claude Opus 4.8: 77.4 (#24)

BenchmarkClaude 3.5 SonnetClaude Opus 4.8
LMArena Instruction Following12971476
LiveBench Instruction Following69.3%—
IFEval85.5%—

Long Context Claude Opus 4.8 leads

Claude 3.5 Sonnet: 39.9 (#167), Claude Opus 4.8: 45.4 (#35)

BenchmarkClaude 3.5 SonnetClaude Opus 4.8
LMArena Longer Query13111483

Writing & Preference Claude Opus 4.8 leads

Claude 3.5 Sonnet: 52.9 (#164), Claude Opus 4.8: 72.0 (#16)

BenchmarkClaude 3.5 SonnetClaude Opus 4.8
LMArena Text12981461
LMArena Creative Writing12921454
EQ-Bench Creative Writing14511840
LMArena Multi-Turn13261476
Short-Story Creative Writing80.3%—
WildBench79.2%—
EQ-Bench 4—1281
LiveBench Language53.8%—

Frequently asked questions

Is Claude 3.5 Sonnet better than Claude Opus 4.8?

Claude Opus 4.8 is the stronger model overall, scoring 60.7 to 34.6 on the Noometry Index.

Is Claude 3.5 Sonnet or Claude Opus 4.8 better for coding?

Claude Opus 4.8 scores higher on coding benchmarks: 59.9 versus 39.0 in the Noometry coding category.

How many benchmarks do Claude 3.5 Sonnet and Claude Opus 4.8 share?

30 benchmarks have published results for both models. Claude 3.5 Sonnet has 60 scored results on Noometry and Claude Opus 4.8 has 65.

Related comparisons

Go deeper