Noometry

Model comparison

Claude Sonnet 5.5 vs Llama 2-70B

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 24.4 on the Noometry Index.

Last verified . 15 shared benchmarks.

Claude Sonnet 5.5 Anthropic

61.9

Rank #10 Confirmed

Llama 2-70B Meta

24.4

Rank #349 Confirmed

Summary

  • They share 15 benchmarks with published results for both. Claude Sonnet 5.5 scores higher in 8 categories and Llama 2-70B 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 8.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for Claude Sonnet 5.5 and 0% for Llama 2-70B.
  • Llama 2-70B has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 5.5Llama 2-70B
ProviderAnthropicMeta
Noometry Index61.924.4
Released2026-09-282023-07-18
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$2—
Output $ / M tokens$10—
Results tracked3235

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 2-70B: 31.4 (#286)

BenchmarkClaude Sonnet 5.5Llama 2-70B
LMArena Coding15131079
FrontierCode52.1%—
CursorBench55.5%—
LMArena WebDev1774—
FrontierSWE61.9%—
SciCode61%—
ALE-Bench1,819—

Agentic & Tool Use Not comparable

Claude Sonnet 5.5: 45.0 (#16), Llama 2-70B: —

BenchmarkClaude Sonnet 5.5Llama 2-70B
APEX-Agents75.5%—

Reasoning Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 54.0 (#28), Llama 2-70B: 14.4 (#325)

BenchmarkClaude Sonnet 5.5Llama 2-70B
LMArena Hard Prompts14951073
Epoch Capabilities Index165.03113.79
NYT Connections (extended)80.5%—
CritPt31.4%—
Mystery Game Puzzles65%—
DTBench—41.6%
BIG-Bench Hard—64.9%
CommonsenseQA 2.0—50%
ForecastBench—51.4
HellaSwag—85.3%
LAMBADA—78.9%
PIQA—82.8%
WinoGrande—80.2%

Math Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 87.9 (#6), Llama 2-70B: 8.1 (#326)

BenchmarkClaude Sonnet 5.5Llama 2-70B
OTIS Mock AIME 2024-2025100%0%
LMArena Math15101091
FrontierMath (Tiers 1-3)88.8%—
FrontierMath Tier 480.5%—
ProofBench100%—
MATH Level 5—3.3%
FrontierMath Erdős2.9%—
GSM8K—69.6%

Knowledge Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 66.0 (#12), Llama 2-70B: 7.4 (#310)

BenchmarkClaude Sonnet 5.5Llama 2-70B
GPQA Diamond95.6%26.3%
LMArena Expert15401039
SimpleQA Verified46.5%—
ARC (AI2) Challenge—78.3%
BoolQ—88.6%
MMLU—69.9%
OpenBookQA—60.2%
TriviaQA—87.6%

Multimodal Not comparable

Claude Sonnet 5.5: 51.5 (#6), Llama 2-70B: —

BenchmarkClaude Sonnet 5.5Llama 2-70B
LMArena Vision1289—
Furniture Assembly75%—

Multilingual Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 55.3 (#30), Llama 2-70B: 27.7 (#274)

BenchmarkClaude Sonnet 5.5Llama 2-70B
LMArena Non-English14521045
LMArena Chinese1522995
LMArena Russian14511083
LMArena French—1090
LMArena German—1041
LMArena Japanese—927
LMArena Korean—964
LMArena Spanish—1143

Instruction Following Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 78.3 (#11), Llama 2-70B: 54.9 (#278)

BenchmarkClaude Sonnet 5.5Llama 2-70B
LMArena Instruction Following14951071

Long Context Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 45.9 (#28), Llama 2-70B: 32.3 (#270)

BenchmarkClaude Sonnet 5.5Llama 2-70B
LMArena Longer Query14981062

Writing & Preference Claude Sonnet 5.5 leads

Claude Sonnet 5.5: 66.0 (#40), Llama 2-70B: 32.3 (#279)

BenchmarkClaude Sonnet 5.5Llama 2-70B
LMArena Text14711115
LMArena Creative Writing14651075
LMArena Multi-Turn14741088

Frequently asked questions

Is Claude Sonnet 5.5 better than Llama 2-70B?

Claude Sonnet 5.5 is the stronger model overall, scoring 61.9 to 24.4 on the Noometry Index.

Is Claude Sonnet 5.5 or Llama 2-70B better for coding?

Claude Sonnet 5.5 scores higher on coding benchmarks: 67.3 versus 31.4 in the Noometry coding category.

How many benchmarks do Claude Sonnet 5.5 and Llama 2-70B share?

15 benchmarks have published results for both models. Claude Sonnet 5.5 has 32 scored results on Noometry and Llama 2-70B has 35.

Related comparisons

Go deeper