SShogo Bench

GPT-6 Sol vs Kimi K3

GPT-6 Sol leads Kimi K3 by 8.7 points on the Shogo Agent Index, but their ranges overlap, so treat it as close. GPT-6 Sol wins 17 and Kimi K3 wins 3 of 20 shared benchmarks. GPT-6 Sol is cheaper for agent workloads.

Add more models to this comparison →

Pillars

PillarGPT-6 SolKimi K3
Agentic coding7263
Long-horizon autonomy7665
Knowledge-work agents4842
Computer use5443
Security & context learning5953

Shared benchmarks

BenchmarkGPT-6 SolKimi K3
APEX-Agentsindex54.3%47.8%
Vending-Bench 2index$14,428$5,165
ARC-AGI95.5%94.5%
ARC-AGI-289.6%60.4%
Chess Puzzles56.0%37.0%
CritPt30.9%23.4%
DTBench97.3%91.2%
FrontierCode49.3%44.2%
FrontierMath Tier 490.0%39.0%
FrontierMath Tiers 1-389.8%72.2%
GPQA Diamond94.3%93.1%
LMCA59.1%52.7%
MirrorCode48.9%54.4%
OTIS Mock AIME100.0%97.2%
ProofBench83.0%87.0%
SciCode57.6%59.5%
SimpleBench73.1%60.7%
SimpleQA Verified60.7%50.6%
WebDev Arena16891674
WeirdML v319.7%7.5%

Specs and price

GPT-6 SolKimi K3
Agent Index63.6 (#13)54.9 (#26)
Agent $/M$0.92$1.39
Input / output $/M$2.00 / $10.00$3.00 / $15.00
Context1.1M1M
ReleasedSep 22, 2026Jul 16, 2026
WeightsClosedOpen
API hosts529

Don’t pick one. Route.

Shogo can run GPT-6 Sol 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