SShogo Bench

Claude Opus 4.6 vs Kimi K3

Kimi K3 leads Claude Opus 4.6 by 1.7 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 4.6 wins 4 and Kimi K3 wins 12 of 17 shared benchmarks. Kimi K3 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.6Kimi K3
Agentic coding5763
Long-horizon autonomy6765
Knowledge-work agents4142
Computer use3943
Security & context learning5753

Shared benchmarks

BenchmarkClaude Opus 4.6Kimi K3
APEX-Agentsindex46.3%47.8%
Vending-Bench 2index$8,018$5,165
ARC-AGI94.0%94.5%
ARC-AGI-269.2%60.4%
Chess Puzzles21.0%37.0%
DTBench91.2%91.2%
FrontierCode26.6%44.2%
FrontierMath Tier 426.8%39.0%
FrontierMath Tiers 1-366.0%72.2%
GPQA Diamond90.5%93.1%
LMCA55.8%52.7%
MirrorCode33.3%54.4%
OTIS Mock AIME94.4%97.2%
ProofBench50.0%87.0%
SimpleBench67.6%60.7%
SimpleQA Verified47.0%50.6%
WebDev Arena15561674

Specs and price

Claude Opus 4.6Kimi K3
Agent Index53.2 (#31)54.9 (#26)
Agent $/M$2.31$1.39
Input / output $/M$5.00 / $25.00$3.00 / $15.00
Context1M1M
ReleasedFeb 5, 2026Jul 16, 2026
WeightsClosedOpen
API hosts529

Don’t pick one. Route.

Shogo can run Claude Opus 4.6 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