SShogo Bench

GPT-5.4 vs Kimi K3

Kimi K3 leads GPT-5.4 by 3.3 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-5.4 wins 10 and Kimi K3 wins 9 of 19 shared benchmarks. GPT-5.4 is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-5.4Kimi K3
Agentic coding5763
Long-horizon autonomy6165
Knowledge-work agents4042
Computer use4243
Security & context learning5453

Shared benchmarks

BenchmarkGPT-5.4Kimi K3
APEX-Agentsindex52.4%47.8%
DeepSWEindex51.8%68.5%
Vending-Bench 2index$6,144$5,165
PostTrainBenchindex17.8%31.5%
ARC-AGI93.7%94.5%
ARC-AGI-274.0%60.4%
Chess Puzzles48.0%37.0%
CritPt23.4%23.4%
DTBench94.4%91.2%
FrontierMath Tier 449.0%39.0%
FrontierMath Tiers 1-378.6%72.2%
GPQA Diamond93.3%93.1%
LMCA52.0%52.7%
MirrorCode23.3%54.4%
OTIS Mock AIME97.8%97.2%
ProofBench56.0%87.0%
SciCode56.6%59.5%
SimpleQA Verified45.1%50.6%
WebDev Arena14631674

Specs and price

GPT-5.4Kimi K3
Agent Index51.6 (#33)54.9 (#26)
Agent $/M$1.27$1.39
Input / output $/M$2.50 / $15.00$3.00 / $15.00
Context1.1M1M
ReleasedMar 5, 2026Jul 16, 2026
WeightsClosedOpen
API hosts429

Don’t pick one. Route.

Shogo can run GPT-5.4 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