Noometry

Model comparison

Claude Fable 5 vs Llama 4 Maverick

Claude Fable 5 is the stronger model overall, scoring 66.8 to 30.9 on the Noometry Index. Llama 4 Maverick costs 66× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Last verified . 34 shared benchmarks.

Claude Fable 5 Anthropic

66.8

Rank #5 Confirmed

Llama 4 Maverick Meta

30.9

Rank #282 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Claude Fable 5 scores higher in 10 categories and Llama 4 Maverick in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Fable 5 leads 76.8 to 10.1.
  • The biggest single-benchmark swing is ARC-AGI-1: 98.5% for Claude Fable 5 and 4.4% for Llama 4 Maverick.
  • Llama 4 Maverick is cheaper at $0.19 / $0.65 per million input/output tokens, against $10 / $50 for Claude Fable 5.
  • Claude Fable 5 accepts more context: 1M tokens versus 128K.
  • Llama 4 Maverick has downloadable open weights; the other is API-only.

Side by side

Claude Fable 5Llama 4 Maverick
ProviderAnthropicMeta
Noometry Index66.830.9
Released2026-06-072025-04-05
WeightsProprietaryOpen
Context window1M128K
Max output128K4K
Input $ / M tokens$10$0.19
Output $ / M tokens$50$0.65
Results tracked6254

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

Category by category

Coding Claude Fable 5 leads

Claude Fable 5: 70.6 (#4), Llama 4 Maverick: 26.6 (#324)

BenchmarkClaude Fable 5Llama 4 Maverick
SciCode61%33.1%
WeirdML91.9%24.5%
LMArena Coding15191302
ALE-Bench2,041172.97
DeepSWE69.9%—
FrontierCode53.5%—
SWE-bench Verified (bash only)—21%
Aider Polyglot—15.6%
LMArena WebDev1625—
FrontierSWE47%—
GSO78.4%—
BigCodeBench Instruct—49.7%
MirrorCode63.9%—
BigCodeBench Complete—61.4%

Agentic & Tool Use Claude Fable 5 leads

Claude Fable 5: 54.0 (#2), Llama 4 Maverick: 28.2 (#91)

BenchmarkClaude Fable 5Llama 4 Maverick
APEX-Agents63.6%—
Berkeley Function Calling Leaderboard—37.3%
Remote Labor Index16.1%—
τ²-bench Banking39.7%—
PostTrainBench41.8%—
GBAEval74.5%—
GDP.pdf30%—
LMArena Search1230—
Vending-Bench 25,680—

Reasoning Claude Fable 5 leads

Claude Fable 5: 76.8 (#6), Llama 4 Maverick: 10.1 (#342)

BenchmarkClaude Fable 5Llama 4 Maverick
ARC-AGI-289.2%0%
SimpleBench81.9%27.7%
Kagi LLM Benchmark91.4%55.9%
NYT Connections (extended)92.7%8%
ARC-AGI-198.5%4.4%
CritPt28.6%0%
EnigmaEval39.3%0.6%
LMArena Hard Prompts15081281
DTBench98.4%61.9%
LMCA61.1%15.9%
Epoch Capabilities Index162.06132.2
Chess Puzzles41%—
EBR-Bench39.5%—
Mystery Game Puzzles52%—
Surface Evolver Bench95%—
Bench to the Future 30.13—
ForecastBench—57.5

Math Claude Fable 5 leads

Claude Fable 5: 88.5 (#5), Llama 4 Maverick: 26.0 (#262)

BenchmarkClaude Fable 5Llama 4 Maverick
OTIS Mock AIME 2024-2025100%20.6%
LMArena Math15191299
FrontierMath (Tiers 1-3)87%—
FrontierMath Tier 490.2%—
ProofBench95%—
Omni-MATH—42.2%
MATH Level 5—73%
FrontierMath (Feb 2025 set)—0.7%
FrontierMath Erdős0%—

Knowledge Claude Fable 5 leads

Claude Fable 5: 62.2 (#25), Llama 4 Maverick: 33.4 (#204)

BenchmarkClaude Fable 5Llama 4 Maverick
GPQA Diamond85.9%67%
LMArena Expert15341259
Humanity's Last Exam—5.7%
SimpleQA Verified70.7%—
MMLU-Pro—81%
Confabulations—22.6%
Vectara Hallucination Rate—8.2%
GPQA (HELM)—65%

Multimodal Claude Fable 5 leads

Claude Fable 5: 45.3 (#17), Llama 4 Maverick: 31.6 (#105)

BenchmarkClaude Fable 5Llama 4 Maverick
LMArena Vision13241142
GeoBench—52%
Blueprint-Bench 238.6%—
Furniture Assembly35.8%—
LMArena Document1496—
SpatialViz-Bench—31.8%

Multilingual Claude Fable 5 leads

Claude Fable 5: 57.3 (#9), Llama 4 Maverick: 42.2 (#195)

BenchmarkClaude Fable 5Llama 4 Maverick
LMArena Non-English14811269
LMArena Chinese15431277
LMArena French15051259
LMArena German14861291
LMArena Japanese15061207
LMArena Korean14881203
LMArena Russian15041286
LMArena Spanish14981293

Instruction Following Claude Fable 5 leads

Claude Fable 5: 78.6 (#8), Llama 4 Maverick: 71.7 (#146)

BenchmarkClaude Fable 5Llama 4 Maverick
LMArena Instruction Following15021267
IFEval—90.8%

Long Context Claude Fable 5 leads

Claude Fable 5: 46.3 (#23), Llama 4 Maverick: 31.4 (#279)

BenchmarkClaude Fable 5Llama 4 Maverick
LMArena Longer Query15091280
Fiction.LiveBench—46.2%

Writing & Preference Claude Fable 5 leads

Claude Fable 5: 75.9 (#5), Llama 4 Maverick: 38.8 (#252)

BenchmarkClaude Fable 5Llama 4 Maverick
LMArena Text14911287
LMArena Creative Writing14941267
EQ-Bench Creative Writing1943860
LMArena Multi-Turn15041289
Short-Story Creative Writing—62%
WildBench—80%
EQ-Bench 41340—

Frequently asked questions

Is Claude Fable 5 better than Llama 4 Maverick?

Claude Fable 5 is the stronger model overall, scoring 66.8 to 30.9 on the Noometry Index. Llama 4 Maverick costs 66× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Which is cheaper, Claude Fable 5 or Llama 4 Maverick?

Llama 4 Maverick is cheaper. It lists at $0.19 per million input tokens and $0.65 per million output tokens; Claude Fable 5 lists at $10 and $50.

Is Claude Fable 5 or Llama 4 Maverick better for coding?

Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 26.6 in the Noometry coding category.

Which has the bigger context window?

Claude Fable 5 does, with 1M tokens against 128K.

How many benchmarks do Claude Fable 5 and Llama 4 Maverick share?

34 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and Llama 4 Maverick has 54.

Related comparisons

Go deeper