SShogo Bench

Claude Fable 5.1 vs Grok 4.7

Claude Fable 5.1 leads Grok 4.7 by 13.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5.1 wins 19 and Grok 4.7 wins 2 of 21 shared benchmarks. Grok 4.7 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.1Grok 4.7
Agentic coding8058
Long-horizon autonomy7169
Knowledge-work agents5547
Computer use6239
Security & context learning6150

Shared benchmarks

BenchmarkClaude Fable 5.1Grok 4.7
APEX-Agentsindex68.6%70.0%
Vending-Bench 2index$5,422$10,537
FrontierSWEindex56.3%29.5%
CursorBenchindex51.8%46.3%
ARC-AGI97.5%90.2%
ARC-AGI-290.0%61.4%
Chess Puzzles48.0%41.0%
CritPt31.1%18.0%
DTBench97.6%96.0%
FrontierCode50.9%47.6%
FrontierMath Tier 487.8%17.1%
FrontierMath Tiers 1-390.2%53.0%
GeoBench84.0%61.0%
LMCA65.5%49.4%
MirrorCode93.3%54.4%
OTIS Mock AIME100.0%98.1%
ProofBench100.0%26.0%
SciCode63.1%57.8%
SimpleQA Verified70.8%56.0%
WebDev Arena17581638
WeirdML v326.0%8.5%

Specs and price

Claude Fable 5.1Grok 4.7
Agent Index68.2 (#10)54.8 (#27)
Agent $/M$4.01$0.98
Input / output $/M$10.00 / $50.00$2.00 / $6.00
Context1M500K
ReleasedSep 1, 2026Sep 21, 2026
WeightsClosedClosed
API hosts35

Don’t pick one. Route.

Shogo can run Claude Fable 5.1 and Grok 4.7 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo