Noometry

Model comparison

Claude Fable 5 vs Llama 3.2 90B

Claude Fable 5 is the stronger model overall, scoring 66.8 to 27.5 on the Noometry Index.

Last verified . 5 shared benchmarks.

Claude Fable 5 Anthropic

66.8

Rank #5 Confirmed

Llama 3.2 90B Meta

27.5

Rank #331 Confirmed

Summary

  • They share 5 benchmarks with published results for both. Claude Fable 5 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 Fable 5 leads 88.5 to 11.1.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for Claude Fable 5 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 Fable 5Llama 3.2 90B
ProviderAnthropicMeta
Noometry Index66.827.5
Released2026-06-072024-09-24
WeightsProprietaryOpen
Context window1M—
Max output128K—
Input $ / M tokens$10—
Output $ / M tokens$50—
Results tracked629

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

Category by category

Coding Not comparable

Claude Fable 5: 70.6 (#4), Llama 3.2 90B: —

BenchmarkClaude Fable 5Llama 3.2 90B
DeepSWE69.9%—
FrontierCode53.5%—
LMArena WebDev1625—
FrontierSWE47%—
SciCode61%—
GSO78.4%—
WeirdML91.9%—
LMArena Coding1519—
MirrorCode63.9%—
ALE-Bench2,041—

Agentic & Tool Use Claude Fable 5 leads

Claude Fable 5: 54.0 (#2), Llama 3.2 90B: 30.0 (#80)

BenchmarkClaude Fable 5Llama 3.2 90B
APEX-Agents63.6%—
Remote Labor Index16.1%—
τ²-bench Banking39.7%—
PostTrainBench41.8%—
BALROG—27.3%
GBAEval74.5%—
GDP.pdf30%—
LMArena Search1230—
Vending-Bench 25,680—

Reasoning Claude Fable 5 leads

Claude Fable 5: 76.8 (#6), Llama 3.2 90B: 21.7 (#217)

BenchmarkClaude Fable 5Llama 3.2 90B
EnigmaEval39.3%0.4%
Epoch Capabilities Index162.06125.5
ARC-AGI-289.2%—
SimpleBench81.9%—
Kagi LLM Benchmark91.4%—
NYT Connections (extended)92.7%—
ARC-AGI-198.5%—
CritPt28.6%—
Chess Puzzles41%—
EBR-Bench39.5%—
LMArena Hard Prompts1508—
Mystery Game Puzzles52%—
DTBench98.4%—
LMCA61.1%—
Surface Evolver Bench95%—
Bench to the Future 30.13—

Math Claude Fable 5 leads

Claude Fable 5: 88.5 (#5), Llama 3.2 90B: 11.1 (#308)

BenchmarkClaude Fable 5Llama 3.2 90B
OTIS Mock AIME 2024-2025100%2.6%
FrontierMath (Tiers 1-3)87%—
FrontierMath Tier 490.2%—
ProofBench95%—
LMArena Math1519—
MATH Level 5—39.4%
FrontierMath Erdős0%—

Knowledge Claude Fable 5 leads

Claude Fable 5: 62.2 (#25), Llama 3.2 90B: 21.7 (#274)

BenchmarkClaude Fable 5Llama 3.2 90B
GPQA Diamond85.9%41%
SimpleQA Verified70.7%—
LMArena Expert1534—
MMLU—80.3%

Multimodal Claude Fable 5 leads

Claude Fable 5: 45.3 (#17), Llama 3.2 90B: 25.4 (#124)

BenchmarkClaude Fable 5Llama 3.2 90B
LMArena Vision13241000
GeoBench—52%
Blueprint-Bench 238.6%—
Furniture Assembly35.8%—
LMArena Document1496—

Multilingual Not comparable

Claude Fable 5: 57.3 (#9), Llama 3.2 90B: —

BenchmarkClaude Fable 5Llama 3.2 90B
LMArena Non-English1481—
LMArena Chinese1543—
LMArena French1505—
LMArena German1486—
LMArena Japanese1506—
LMArena Korean1488—
LMArena Russian1504—
LMArena Spanish1498—

Instruction Following Not comparable

Claude Fable 5: 78.6 (#8), Llama 3.2 90B: —

BenchmarkClaude Fable 5Llama 3.2 90B
LMArena Instruction Following1502—

Long Context Not comparable

Claude Fable 5: 46.3 (#23), Llama 3.2 90B: —

BenchmarkClaude Fable 5Llama 3.2 90B
LMArena Longer Query1509—

Writing & Preference Not comparable

Claude Fable 5: 75.9 (#5), Llama 3.2 90B: —

BenchmarkClaude Fable 5Llama 3.2 90B
LMArena Text1491—
LMArena Creative Writing1494—
EQ-Bench Creative Writing1943—
EQ-Bench 41340—
LMArena Multi-Turn1504—

Frequently asked questions

Is Claude Fable 5 better than Llama 3.2 90B?

Claude Fable 5 is the stronger model overall, scoring 66.8 to 27.5 on the Noometry Index.

How many benchmarks do Claude Fable 5 and Llama 3.2 90B share?

5 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and Llama 3.2 90B has 9.

Related comparisons

Go deeper