SShogo Bench

Claude Opus 4.8 vs Kimi K3

Claude Opus 4.8 leads Kimi K3 by 1.4 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. Claude Opus 4.8 wins 13 and Kimi K3 wins 8 of 21 shared benchmarks. Kimi K3 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarClaude Opus 4.8Kimi K3
Agentic coding6363
Long-horizon autonomy6665
Knowledge-work agents4342
Computer use4743
Security & context learning5553

Shared benchmarks

BenchmarkClaude Opus 4.8Kimi K3
APEX-Agentsindex48.9%47.8%
DeepSWEindex59.0%68.5%
Vending-Bench 2index$5,787$5,165
PostTrainBenchindex31.0%31.5%
ARC-AGI92.5%94.5%
ARC-AGI-272.1%60.4%
Chess Puzzles52.0%37.0%
CritPt20.9%23.4%
DTBench94.9%91.2%
FrontierCode46.5%44.2%
FrontierMath Tier 456.1%39.0%
FrontierMath Tiers 1-380.0%72.2%
GPQA Diamond91.0%93.1%
LMCA57.5%52.7%
MirrorCode65.6%54.4%
OTIS Mock AIME98.3%97.2%
ProofBench69.0%87.0%
SciCode53.5%59.5%
SimpleBench64.8%60.7%
SimpleQA Verified53.0%50.6%
WebDev Arena15591674

Specs and price

Claude Opus 4.8Kimi K3
Agent Index56.3 (#20)54.9 (#26)
Agent $/M$2.31$1.39
Input / output $/M$5.00 / $25.00$3.00 / $15.00
Context1M1M
ReleasedMay 28, 2026Jul 16, 2026
WeightsClosedOpen
API hosts629

Don’t pick one. Route.

Shogo can run Claude Opus 4.8 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