Noometry

Model comparison

Claude Sonnet 4.6 vs Llama 3.2 90B

Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 27.1 on the Noometry Index.

Last verified . 4 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.1

Rank #42 Confirmed

Llama 3.2 90B Meta

27.1

Rank #326 Confirmed

Summary

  • They share 4 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 5 categories and Llama 3.2 90B in 0 categories; 5 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Sonnet 4.6 leads 51.9 to 10.4.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 85.8% for Claude Sonnet 4.6 and 2.6% for Llama 3.2 90B.
  • Llama 3.2 90B has downloadable open weights; the other is API-only.

Side by side

Claude Sonnet 4.6Llama 3.2 90B
ProviderAnthropicMeta
Noometry Index50.127.1
Released2026-02-172024-09-24
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$3—
Output $ / M tokens$15—
Results tracked579

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

Category by category

Coding Not comparable

Claude Sonnet 4.6: 46.0 (#62), Llama 3.2 90B: —

BenchmarkClaude Sonnet 4.6Llama 3.2 90B
SWE-bench Verified75.2%—
DeepSWE29.9%—
FrontierCode24.3%—
LMArena WebDev1521—
SciCode46.8%—
WeirdML66.1%—
LMArena Coding1504—
ALE-Bench1,327—

Agentic & Tool Use Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 39.1 (#26), Llama 3.2 90B: 29.7 (#73)

BenchmarkClaude Sonnet 4.6Llama 3.2 90B
Terminal-Bench53.4%—
APEX-Agents43%—
OSWorld 2.09.3%—
DeepResearch Bench54.9%—
OSWorld72.1%—
BALROG—27.3%
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—
LMArena Search1221—
Vending-Bench 27,204—

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#40), Llama 3.2 90B: 20.9 (#207)

BenchmarkClaude Sonnet 4.6Llama 3.2 90B
Epoch Capabilities Index152.25125.5
ARC-AGI-260.4%—
NYT Connections (extended)80.9%—
ARC-AGI-186.5%—
CritPt3.1%—
Chess Puzzles13%—
EnigmaEval—0.4%
Thematic Generalization76.3%—
LMArena Hard Prompts1485—
Mystery Game Puzzles16%—
DTBench89.9%—
LMCA46.5%—
ForecastBench62—

Math Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.9 (#41), Llama 3.2 90B: 10.4 (#302)

BenchmarkClaude Sonnet 4.6Llama 3.2 90B
OTIS Mock AIME 2024-202585.8%2.6%
ProofBench45%—
LMArena Math1463—
MATH Level 5—39.4%
FrontierMath (Feb 2025 set)32.4%—
FrontierMath Tier 4 (v1)8.3%—

Knowledge Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.6 (#60), Llama 3.2 90B: 21.7 (#269)

BenchmarkClaude Sonnet 4.6Llama 3.2 90B
GPQA Diamond87.4%41%
SimpleQA Verified35.5%—
Vectara Hallucination Rate10.6%—
LMArena Expert1500—
MMLU—80.3%

Multimodal Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 38.0 (#61), Llama 3.2 90B: 24.9 (#119)

BenchmarkClaude Sonnet 4.6Llama 3.2 90B
LMArena Vision12831000
GeoBench—52%
Blueprint-Bench 26.7%—
LMArena Document1482—

Multilingual Not comparable

Claude Sonnet 4.6: 54.6 (#39), Llama 3.2 90B: —

BenchmarkClaude Sonnet 4.6Llama 3.2 90B
LMArena Non-English1440—
LMArena Chinese1491—
LMArena French1465—
LMArena German1428—
LMArena Japanese1419—
LMArena Korean1411—
LMArena Russian1440—
LMArena Spanish1465—

Instruction Following Not comparable

Claude Sonnet 4.6: 77.6 (#23), Llama 3.2 90B: —

BenchmarkClaude Sonnet 4.6Llama 3.2 90B
LMArena Instruction Following1476—

Long Context Not comparable

Claude Sonnet 4.6: 45.3 (#40), Llama 3.2 90B: —

BenchmarkClaude Sonnet 4.6Llama 3.2 90B
LMArena Longer Query1479—

Writing & Preference Not comparable

Claude Sonnet 4.6: 70.4 (#22), Llama 3.2 90B: —

BenchmarkClaude Sonnet 4.6Llama 3.2 90B
LMArena Text1458—
LMArena Creative Writing1435—
EQ-Bench Creative Writing1810—
EQ-Bench 41207—
LMArena Multi-Turn1464—

Frequently asked questions

Is Claude Sonnet 4.6 better than Llama 3.2 90B?

Claude Sonnet 4.6 is the stronger model overall, scoring 50.1 to 27.1 on the Noometry Index.

How many benchmarks do Claude Sonnet 4.6 and Llama 3.2 90B share?

4 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Llama 3.2 90B has 9.

Related comparisons

Go deeper