Compare, 2 models

Side by side.

GPT-5.4 and Kimi K3 on every board at least two of them share. Blue marks the best in each row.

Add a model

Specs

List prices, context and published output speed. Blue marks the best in each row.

Specs for GPT-5.4 and Kimi K3
Spec	GPT-5.4OpenAI	Kimi K3Moonshot
Lab	OpenAI	Moonshot
Type	Language	Language
Released	Mar 5, 2026	Jul 16, 2026
Input price$ per 1M tokens	$2.50	$3.00
Output price$ per 1M tokens	$15.00	$15.00
Blended price3 input tokens per output	$5.63	$6.00
Contexttokens	1.05M	1.05M
Open weights	No	Yes

Every board where at least two of these models have a published score. Each score links to its source.

Benchmark scores for GPT-5.4 and Kimi K3
Board	GPT-5.4OpenAI	Kimi K3Moonshot
Epoch Capabilities IndexOverall, higher is better	157	158
LMArena textOverall, higher is better	1475High, style control	1488Max, style control
ARC-AGI-2Reasoning and knowledge, higher is better	74.0%xhigh setting	60.4%max setting
FrontierMath Tiers 1-3Reasoning and knowledge, higher is better	78.6%xhigh setting	72.2%max setting
GPQA DiamondReasoning and knowledge, higher is better	93.3%xhigh setting	93.1%max setting

n/a means the board has not published a score for that model.