SShogo Bench

Claude Fable 5.2 vs Gemini 4 Argon

Claude Fable 5.2 leads Gemini 4 Argon by 6.9 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Fable 5.2 wins 16 and Gemini 4 Argon wins 4 of 21 shared benchmarks. Gemini 4 Argon is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.2Gemini 4 Argon
Agentic coding8677
Long-horizon autonomy7878
Knowledge-work agents6759
Computer use7761
Security & context learning6561

Shared benchmarks

BenchmarkClaude Fable 5.2Gemini 4 Argon
APEX-Agentsindex80.1%82.4%
Vending-Bench 2index$9,628$13,718
FrontierSWEindex69.9%55.0%
Remote Labor Indexindex41.3%17.1%
CursorBenchindex60.0%52.9%
PostTrainBenchindex44.6%40.4%
ARC-AGI98.5%98.5%
ARC-AGI-293.8%91.3%
Chess Puzzles79.0%59.0%
CritPt35.7%27.1%
DTBench99.2%97.6%
FrontierMath Tier 4100.0%78.0%
FrontierMath Tiers 1-395.1%86.0%
GPQA Diamond96.0%96.4%
LMCA70.6%63.7%
OTIS Mock AIME99.7%100.0%
ProofBench100.0%99.0%
SciCode67.7%61.8%
SimpleBench94.9%91.7%
SimpleQA Verified94.0%76.0%
WeirdML v343.1%20.3%

Specs and price

Claude Fable 5.2Gemini 4 Argon
Agent Index76.4 (#1)69.5 (#6)
Agent $/M$3.21$0.84
Input / output $/M$8.00 / $40.00$2.00 / $10.00
Context1M1M
ReleasedNov 9, 2026Oct 13, 2026
WeightsClosedClosed
API hosts45

Don’t pick one. Route.

Shogo can run Claude Fable 5.2 and Gemini 4 Argon side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo