Noometry

Model comparison

Claude Fable 5 vs Gemini 2.5 Pro

Claude Fable 5 is the stronger model overall, scoring 66.8 to 45.0 on the Noometry Index. Gemini 2.5 Pro costs 5.8× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Last verified . 43 shared benchmarks.

Claude Fable 5 Anthropic

66.8

Rank #5 Confirmed

Gemini 2.5 Pro Google

45.0

Rank #75 Confirmed

Summary

  • They share 43 benchmarks with published results for both. Claude Fable 5 scores higher in 9 categories and Gemini 2.5 Pro in 1 category; 9 gaps are clear of the uncertainty.
  • The widest gap is in math, where Claude Fable 5 leads 88.5 to 32.5.
  • The biggest single-benchmark swing is FrontierMath Tier 4: 90.2% for Claude Fable 5 and 0% for Gemini 2.5 Pro.
  • Gemini 2.5 Pro is cheaper at $1.25 / $10 per million input/output tokens, against $10 / $50 for Claude Fable 5.
  • Gemini 2.5 Pro accepts more context: 1.05M tokens versus 1M.

Side by side

Claude Fable 5Gemini 2.5 Pro
ProviderAnthropicGoogle
Noometry Index66.845.0
Released2026-06-072025-03-25
WeightsProprietaryProprietary
Context window1M1.05M
Max output128K66K
Input $ / M tokens$10$1.25
Output $ / M tokens$50$10
Results tracked6278

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), Gemini 2.5 Pro: 42.4 (#101)

BenchmarkClaude Fable 5Gemini 2.5 Pro
LMArena WebDev16251227
SciCode61%42.8%
GSO78.4%3.9%
WeirdML91.9%54%
LMArena Coding15191452
ALE-Bench2,041785.52
SWE-bench Verified—57.6%
DeepSWE69.9%—
FrontierCode53.5%—
SWE-bench Verified (bash only)—53.6%
Aider Polyglot—83.1%
FrontierSWE47%—
LiveBench Coding—85.9%
MirrorCode63.9%—
CadEval—64%
AlgoTune—1.51

Agentic & Tool Use Claude Fable 5 leads

Claude Fable 5: 54.0 (#2), Gemini 2.5 Pro: 29.2 (#88)

BenchmarkClaude Fable 5Gemini 2.5 Pro
Remote Labor Index16.1%0.8%
τ²-bench Banking39.7%13.7%
LMArena Search12301142
Vending-Bench 25,680573.64
Terminal-Bench—32.6%
APEX-Agents63.6%—
GDPval—23.3%
TheAgentCompany—30.3%
DeepResearch Bench—42.8%
PostTrainBench41.8%—
BALROG—43.3%
GBAEval74.5%—
GDP.pdf30%—
METR Time Horizons—55.4%

Reasoning Claude Fable 5 leads

Claude Fable 5: 76.8 (#6), Gemini 2.5 Pro: 28.8 (#99)

BenchmarkClaude Fable 5Gemini 2.5 Pro
ARC-AGI-289.2%4.9%
SimpleBench81.9%62.4%
Kagi LLM Benchmark91.4%70.3%
ARC-AGI-198.5%41%
CritPt28.6%2%
Chess Puzzles41%20%
EnigmaEval39.3%5.6%
LMArena Hard Prompts15081455
DTBench98.4%82.4%
LMCA61.1%34.8%
Epoch Capabilities Index162.06145.32
NYT Connections (extended)92.7%—
EBR-Bench39.5%—
LiveBench Reasoning—89.8%
Mystery Game Puzzles52%—
LiveBench Data Analysis—79.9%
Surface Evolver Bench95%—
Bench to the Future 30.13—
ForecastBench—61.3
LiveBench—82.3%

Math Claude Fable 5 leads

Claude Fable 5: 88.5 (#5), Gemini 2.5 Pro: 32.5 (#213)

BenchmarkClaude Fable 5Gemini 2.5 Pro
FrontierMath (Tiers 1-3)87%24.6%
FrontierMath Tier 490.2%0%
OTIS Mock AIME 2024-2025100%84.7%
LMArena Math15191450
ProofBench95%—
Omni-MATH—41.6%
LiveBench Math—90.2%
MATH Level 5—95.9%
FrontierMath (Feb 2025 set)—14.1%
FrontierMath Erdős0%—
FrontierMath Tier 4 (v1)—4.2%

Knowledge Claude Fable 5 leads

Claude Fable 5: 62.2 (#25), Gemini 2.5 Pro: 56.0 (#46)

BenchmarkClaude Fable 5Gemini 2.5 Pro
GPQA Diamond85.9%85.3%
LMArena Expert15341452
Humanity's Last Exam—21.6%
SimpleQA Verified70.7%—
MMLU-Pro—86.3%
Confabulations—10.6%
Vectara Hallucination Rate—7%
GPQA (HELM)—74.9%

Multimodal Too close to call

Claude Fable 5: 45.3 (#17), Gemini 2.5 Pro: 45.2 (#18)

BenchmarkClaude Fable 5Gemini 2.5 Pro
LMArena Vision13241263
LMArena Document14961421
GeoBench—86%
VPCT—48%
Blueprint-Bench 238.6%—
Furniture Assembly35.8%—
SpatialViz-Bench—44.7%

Multilingual Claude Fable 5 leads

Claude Fable 5: 57.3 (#9), Gemini 2.5 Pro: 55.3 (#31)

BenchmarkClaude Fable 5Gemini 2.5 Pro
LMArena Non-English14811451
LMArena Chinese15431507
LMArena French15051472
LMArena German14861487
LMArena Japanese15061461
LMArena Korean14881434
LMArena Russian15041461
LMArena Spanish14981473

Instruction Following Claude Fable 5 leads

Claude Fable 5: 78.6 (#8), Gemini 2.5 Pro: 75.0 (#75)

BenchmarkClaude Fable 5Gemini 2.5 Pro
LMArena Instruction Following15021437
LiveBench Instruction Following—80.6%
IFEval—84%

Long Context Gemini 2.5 Pro leads

Claude Fable 5: 46.3 (#23), Gemini 2.5 Pro: 59.8 (#5)

BenchmarkClaude Fable 5Gemini 2.5 Pro
LMArena Longer Query15091449
Fiction.LiveBench—91.7%

Writing & Preference Claude Fable 5 leads

Claude Fable 5: 75.9 (#5), Gemini 2.5 Pro: 63.7 (#62)

BenchmarkClaude Fable 5Gemini 2.5 Pro
LMArena Text14911458
LMArena Creative Writing14941454
EQ-Bench Creative Writing19431421
LMArena Multi-Turn15041453
Short-Story Creative Writing—83.8%
WildBench—85.7%
EQ-Bench 41340—
LiveBench Language—67.8%

Frequently asked questions

Is Claude Fable 5 better than Gemini 2.5 Pro?

Claude Fable 5 is the stronger model overall, scoring 66.8 to 45.0 on the Noometry Index. Gemini 2.5 Pro costs 5.8× 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 Gemini 2.5 Pro?

Gemini 2.5 Pro is cheaper. It lists at $1.25 per million input tokens and $10 per million output tokens; Claude Fable 5 lists at $10 and $50.

Is Claude Fable 5 or Gemini 2.5 Pro better for coding?

Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 42.4 in the Noometry coding category.

Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 1M.

How many benchmarks do Claude Fable 5 and Gemini 2.5 Pro share?

43 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and Gemini 2.5 Pro has 78.

Related comparisons

Go deeper