SShogo Bench

Claude Opus 5 vs Kimi K3

Claude Opus 5 leads Kimi K3 by 10.5 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 5 wins 22 and Kimi K3 wins 1 of 23 shared benchmarks. Kimi K3 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 5Kimi K3
Agentic coding7463
Long-horizon autonomy7465
Knowledge-work agents5242
Computer use5643
Security & context learning5953

Shared benchmarks

BenchmarkClaude Opus 5Kimi K3
APEX-Agentsindex65.8%47.8%
DeepSWEindex73.6%68.5%
Vending-Bench 2index$11,182$5,165
FrontierSWEindex52.0%25.9%
PostTrainBenchindex35.7%31.5%
ARC-AGI97.5%94.5%
ARC-AGI-290.4%60.4%
Chess Puzzles43.0%37.0%
CritPt29.1%23.4%
DTBench97.9%91.2%
FrontierCode53.4%44.2%
FrontierMath Tier 473.2%39.0%
FrontierMath Tiers 1-385.6%72.2%
GPQA Diamond93.9%93.1%
LMCA64.5%52.7%
MirrorCode87.8%54.4%
OTIS Mock AIME98.9%97.2%
ProofBench99.0%87.0%
SciCode56.4%59.5%
SimpleBench80.6%60.7%
SimpleQA Verified59.9%50.6%
WebDev Arena16871674
WeirdML v319.0%7.5%

Specs and price

Claude Opus 5Kimi K3
Agent Index65.4 (#11)54.9 (#26)
Agent $/M$2.31$1.39
Input / output $/M$5.00 / $25.00$3.00 / $15.00
Context1M1M
ReleasedJul 24, 2026Jul 16, 2026
WeightsClosedOpen
API hosts629

Don’t pick one. Route.

Shogo can run Claude Opus 5 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