Noometry

Model comparison

Claude Sonnet 5.5 vs Llama 3-8B

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 25.5 on the Noometry Index.

Last verified . 15 shared benchmarks.

Claude Sonnet 5.5 Anthropic

61.9

Rank #10 Confirmed

Llama 3-8B Meta

25.5

Rank #344 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Claude Sonnet 5.5 scores higher in 8 categories and Llama 3-8B in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 5.5 leads 87.9 to 8.8.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for Claude Sonnet 5.5 and 1.9% for Llama 3-8B.
  • Llama 3-8B has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 5.5Llama 3-8B
ProviderAnthropicMeta
Noometry Index61.925.5
Released2026-09-282024-04-18
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked3234

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

Category by category

Coding Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 67.3 (#6), Llama 3-8B: 31.0 (#289)

BenchmarkClaude Sonnet 5.5Llama 3-8B
LMArena Coding15131152
FrontierCode52.1%—
CursorBench55.5%—
LMArena WebDev1774—
FrontierSWE61.9%—
SciCode61%—
BigCodeBench Instruct—31.9%
BigCodeBench Complete—36.9%
ALE-Bench1,819—
HumanEval+—56.7%
MBPP+—54.8%

Agentic & Tool Use Not comparable

Claude Sonnet 5.5: 45.0 (#16), Llama 3-8B: —

BenchmarkClaude Sonnet 5.5Llama 3-8B
APEX-Agents75.5%—

Reasoning Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 54.0 (#28), Llama 3-8B: 14.3 (#326)

BenchmarkClaude Sonnet 5.5Llama 3-8B
LMArena Hard Prompts14951133
Epoch Capabilities Index165.03116.45
NYT Connections (extended)80.5%—
CritPt31.4%—
Chess Puzzles—0%
Mystery Game Puzzles65%—
DTBench—43.9%
Adversarial NLI—57.3%
ForecastBench—58.6
WinoGrande—75.7%

Math Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 87.9 (#6), Llama 3-8B: 8.8 (#323)

BenchmarkClaude Sonnet 5.5Llama 3-8B
OTIS Mock AIME 2024-2025100%1.9%
LMArena Math15101151
FrontierMath (Tiers 1-3)88.8%—
FrontierMath Tier 480.5%—
ProofBench100%—
MATH Level 5—6.1%
FrontierMath Erdős2.9%—

Knowledge Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 66.0 (#12), Llama 3-8B: 7.8 (#308)

BenchmarkClaude Sonnet 5.5Llama 3-8B
GPQA Diamond95.6%26.1%
LMArena Expert15401113
SimpleQA Verified46.5%—
ARC (AI2) Challenge—82.8%
MMLU—68.8%
OpenBookQA—82.6%
TriviaQA—67.7%

Multimodal Not comparable

Claude Sonnet 5.5: 51.5 (#6), Llama 3-8B: —

BenchmarkClaude Sonnet 5.5Llama 3-8B
LMArena Vision1289—
Furniture Assembly75%—

Multilingual Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 55.3 (#30), Llama 3-8B: 30.8 (#261)

BenchmarkClaude Sonnet 5.5Llama 3-8B
LMArena Non-English14521098
LMArena Chinese15221076
LMArena Russian14511109
LMArena French—1159
LMArena German—1104
LMArena Japanese—967
LMArena Korean—1004
LMArena Spanish—1173

Instruction Following Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 78.3 (#11), Llama 3-8B: 58.4 (#260)

BenchmarkClaude Sonnet 5.5Llama 3-8B
LMArena Instruction Following14951127

Long Context Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 45.9 (#28), Llama 3-8B: 34.2 (#251)

BenchmarkClaude Sonnet 5.5Llama 3-8B
LMArena Longer Query14981128

Writing & Preference Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 66.0 (#40), Llama 3-8B: 37.5 (#256)

BenchmarkClaude Sonnet 5.5Llama 3-8B
LMArena Text14711166
LMArena Creative Writing14651150
LMArena Multi-Turn14741152

Frequently asked questions

Is Claude Sonnet 5.5 better than Llama 3-8B?

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 25.5 on the Noometry Index.

Is Claude Sonnet 5.5 or Llama 3-8B better for coding?

Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 31.0 in the Noometry coding category.

How many benchmarks do Claude Sonnet 5.5 and Llama 3-8B share?

15 benchmarks have published results for both models. Claude Sonnet 5.5 has 32 scored results on Noometry and Llama 3-8B has 34.

Related comparisons

Go deeper