Noometry

Model comparison

Claude Fable 5 vs Gemma 3 27B

Claude Fable 5 is the stronger model overall, scoring 66.8 to 30.8 on the Noometry Index. Gemma 3 27B costs 200× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Last verified . 28 shared benchmarks.

Claude Fable 5 Anthropic

66.8

Rank #5 Confirmed

Gemma 3 27B Google

30.8

Rank #284 Confirmed

Summary

  • They share 28 benchmarks with published results for both. Claude Fable 5 scores higher in 10 categories and Gemma 3 27B in 0 categories; 10 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Fable 5 leads 88.5 to 25.9.
  • The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 100% for Claude Fable 5 and 22.5% for Gemma 3 27B.
  • Gemma 3 27B is cheaper at $0.08 / $0.16 per million input/output tokens, against $10 / $50 for Claude Fable 5.
  • Claude Fable 5 accepts more context: 1M tokens versus 131K.
  • Gemma 3 27B has downloadable open weights; the other is API-only.

Side by side

Claude Fable 5Gemma 3 27B
ProviderAnthropicGoogle
Noometry Index66.830.8
Released2026-06-072025-03-11
WeightsProprietaryOpen
Context window1M131K
Max output128K8K
Input $ / M tokens$10$0.08
Output $ / M tokens$50$0.16
Results tracked6243

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), Gemma 3 27B: 22.5 (#334)

BenchmarkClaude Fable 5Gemma 3 27B
SciCode61%21.2%
LMArena Coding15191322
DeepSWE69.9%—
FrontierCode53.5%—
Aider Polyglot—4.9%
LMArena WebDev1625—
FrontierSWE47%—
GSO78.4%—
WeirdML91.9%—
LiveBench Coding—39.9%
MirrorCode63.9%—
ALE-Bench2,041—

Agentic & Tool Use Claude Fable 5 leads

Claude Fable 5: 54.0 (#2), Gemma 3 27B: 25.1 (#110)

BenchmarkClaude Fable 5Gemma 3 27B
APEX-Agents63.6%—
Berkeley Function Calling Leaderboard—29.5%
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), Gemma 3 27B: 16.7 (#301)

BenchmarkClaude Fable 5Gemma 3 27B
Kagi LLM Benchmark91.4%40.4%
CritPt28.6%0%
Chess Puzzles41%0%
LMArena Hard Prompts15081340
DTBench98.4%52.5%
LMCA61.1%12.3%
Epoch Capabilities Index162.06130.04
ARC-AGI-289.2%—
SimpleBench81.9%—
NYT Connections (extended)92.7%—
ARC-AGI-198.5%—
EnigmaEval39.3%—
EBR-Bench39.5%—
LiveBench Reasoning—43.8%
Mystery Game Puzzles52%—
LiveBench Data Analysis—51.5%
Surface Evolver Bench95%—
Bench to the Future 30.13—
LiveBench—50%

Math Claude Fable 5 leads

Claude Fable 5: 88.5 (#5), Gemma 3 27B: 25.9 (#265)

BenchmarkClaude Fable 5Gemma 3 27B
OTIS Mock AIME 2024-2025100%22.5%
LMArena Math15191312
FrontierMath (Tiers 1-3)87%—
FrontierMath Tier 490.2%—
ProofBench95%—
LiveBench Math—55.4%
MATH Level 5—74%
FrontierMath Erdős0%—

Knowledge Claude Fable 5 leads

Claude Fable 5: 62.2 (#25), Gemma 3 27B: 25.5 (#261)

BenchmarkClaude Fable 5Gemma 3 27B
GPQA Diamond85.9%47.7%
LMArena Expert15341304
SimpleQA Verified70.7%—
Confabulations—40.3%
Vectara Hallucination Rate—7.4%

Multimodal Claude Fable 5 leads

Claude Fable 5: 45.3 (#17), Gemma 3 27B: 32.6 (#100)

BenchmarkClaude Fable 5Gemma 3 27B
LMArena Vision13241164
GeoBench—52%
Blueprint-Bench 238.6%—
Furniture Assembly35.8%—
LMArena Document1496—

Multilingual Claude Fable 5 leads

Claude Fable 5: 57.3 (#9), Gemma 3 27B: 46.9 (#155)

BenchmarkClaude Fable 5Gemma 3 27B
LMArena Non-English14811334
LMArena Chinese15431346
LMArena French15051368
LMArena German14861362
LMArena Japanese15061287
LMArena Korean14881308
LMArena Russian15041349
LMArena Spanish14981349

Instruction Following Claude Fable 5 leads

Claude Fable 5: 78.6 (#8), Gemma 3 27B: 70.6 (#160)

BenchmarkClaude Fable 5Gemma 3 27B
LMArena Instruction Following15021321
LiveBench Instruction Following—74.9%

Long Context Claude Fable 5 leads

Claude Fable 5: 46.3 (#23), Gemma 3 27B: 27.6 (#293)

BenchmarkClaude Fable 5Gemma 3 27B
LMArena Longer Query15091333
Fiction.LiveBench—33.3%

Writing & Preference Claude Fable 5 leads

Claude Fable 5: 75.9 (#5), Gemma 3 27B: 52.5 (#168)

BenchmarkClaude Fable 5Gemma 3 27B
LMArena Text14911358
LMArena Creative Writing14941346
EQ-Bench Creative Writing19431266
LMArena Multi-Turn15041345
Short-Story Creative Writing—79.9%
EQ-Bench 41340—
LiveBench Language—34.6%

Frequently asked questions

Is Claude Fable 5 better than Gemma 3 27B?

Claude Fable 5 is the stronger model overall, scoring 66.8 to 30.8 on the Noometry Index. Gemma 3 27B costs 200× 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 Gemma 3 27B?

Gemma 3 27B is cheaper. It lists at $0.08 per million input tokens and $0.16 per million output tokens; Claude Fable 5 lists at $10 and $50.

Is Claude Fable 5 or Gemma 3 27B better for coding?

Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 22.5 in the Noometry coding category.

Which has the bigger context window?

Claude Fable 5 does, with 1M tokens against 131K.

How many benchmarks do Claude Fable 5 and Gemma 3 27B share?

28 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and Gemma 3 27B has 43.

Related comparisons

Go deeper