SShogo Bench

Claude Fable 5.2 vs Gemini 3.8 Flash

Claude Fable 5.2 leads Gemini 3.8 Flash by 20.2 points on the Shogo Agent Index. Claude Fable 5.2 wins 19 and Gemini 3.8 Flash wins 0 of 20 shared benchmarks. Gemini 3.8 Flash is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.2Gemini 3.8 Flash
Agentic coding8663
Long-horizon autonomy7864
Knowledge-work agents6747
Computer use7744
Security & context learning6553

Shared benchmarks

BenchmarkClaude Fable 5.2Gemini 3.8 Flash
APEX-Agentsindex80.1%64.3%
Vending-Bench 2index$9,628$5,094
FrontierSWEindex69.9%19.6%
Remote Labor Indexindex41.3%5.8%
CursorBenchindex60.0%39.6%
ARC-AGI98.5%98.5%
ARC-AGI-293.8%89.2%
Chess Puzzles79.0%58.0%
CritPt35.7%18.3%
DTBench99.2%95.7%
FrontierMath Tier 4100.0%22.0%
FrontierMath Tiers 1-395.1%68.4%
GPQA Diamond96.0%95.4%
LMCA70.6%52.9%
OTIS Mock AIME99.7%98.9%
ProofBench100.0%48.0%
SciCode67.7%56.6%
SimpleBench94.9%82.4%
SimpleQA Verified94.0%69.7%
WeirdML v343.1%7.4%

Specs and price

Claude Fable 5.2Gemini 3.8 Flash
Agent Index76.4 (#1)56.2 (#21)
Agent $/M$3.21$0.35
Input / output $/M$8.00 / $40.00$0.75 / $3.75
Context1M1M
ReleasedNov 9, 2026Sep 2, 2026
WeightsClosedClosed
API hosts46

Don’t pick one. Route.

Shogo can run Claude Fable 5.2 and Gemini 3.8 Flash side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo