SShogo Bench

Claude Fable 5.2 vs Kimi K3

Claude Fable 5.2 leads Kimi K3 by 21.5 points on the Shogo Agent Index. Claude Fable 5.2 wins 19 and Kimi K3 wins 0 of 19 shared benchmarks. Kimi K3 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Fable 5.2Kimi K3
Agentic coding8663
Long-horizon autonomy7865
Knowledge-work agents6742
Computer use7743
Security & context learning6553

Shared benchmarks

BenchmarkClaude Fable 5.2Kimi K3
APEX-Agentsindex80.1%47.8%
Vending-Bench 2index$9,628$5,165
FrontierSWEindex69.9%25.9%
PostTrainBenchindex44.6%31.5%
ARC-AGI98.5%94.5%
ARC-AGI-293.8%60.4%
Chess Puzzles79.0%37.0%
CritPt35.7%23.4%
DTBench99.2%91.2%
FrontierMath Tier 4100.0%39.0%
FrontierMath Tiers 1-395.1%72.2%
GPQA Diamond96.0%93.1%
LMCA70.6%52.7%
OTIS Mock AIME99.7%97.2%
ProofBench100.0%87.0%
SciCode67.7%59.5%
SimpleBench94.9%60.7%
SimpleQA Verified94.0%50.6%
WeirdML v343.1%7.5%

Specs and price

Claude Fable 5.2Kimi K3
Agent Index76.4 (#1)54.9 (#26)
Agent $/M$3.21$1.39
Input / output $/M$8.00 / $40.00$3.00 / $15.00
Context1M1M
ReleasedNov 9, 2026Jul 16, 2026
WeightsClosedOpen
API hosts429

Don’t pick one. Route.

Shogo can run Claude Fable 5.2 and Kimi K3 side by side and send each step of an agent to the one that’s cheaper for it.

Try both in Shogo