SShogo Bench

Claude Fable 5 vs DeepSeek V4.1 Flash 1017

Claude Fable 5 leads DeepSeek V4.1 Flash 1017 by 6.5 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5 wins 11 and DeepSeek V4.1 Flash 1017 wins 1 of 12 shared benchmarks. DeepSeek V4.1 Flash 1017 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5DeepSeek V4.1 Flash 1017
Agentic coding7463
Long-horizon autonomy6966
Knowledge-work agents5249
Computer use5545
Security & context learning5954

Shared benchmarks

BenchmarkClaude Fable 5DeepSeek V4.1 Flash 1017
APEX-Agentsindex63.6%69.8%
ARC-AGI98.5%94.5%
ARC-AGI-289.2%78.1%
Chess Puzzles47.0%46.0%
CritPt28.6%24.0%
FrontierMath Tier 490.2%46.3%
FrontierMath Tiers 1-387.0%71.2%
GPQA Diamond93.9%93.2%
OTIS Mock AIME100.0%99.4%
SciCode61.0%55.9%
SimpleQA Verified70.7%42.5%
WeirdML v315.6%9.1%

Specs and price

Claude Fable 5DeepSeek V4.1 Flash 1017
Agent Index64.1 (#12)57.6 (#17)
Agent $/M$4.62$0.050
Input / output $/M$10.00 / $50.00$0.15 / $0.60
Context1M1M
ReleasedJun 9, 2026Oct 17, 2026
WeightsClosedOpen
API hosts451

Don’t pick one. Route.

Shogo can run Claude Fable 5 and DeepSeek V4.1 Flash 1017 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo