Kimi K2.5vsGPT-5.3-Codex

Kimi K2.5
GPT-5.3-Codex
Specifications
Parameters
1T
Context window
256k
API pricing
Input price
$0.60$1.75
Output price
$3.00$14.00
Cached input price
$0.10$0.175
Cheapest input
$0.45DeepInfra$1.75Azure
Cheapest output
$2.25DeepInfra$14.00Azure
Benchmarks
BullshitBench v2
52%24%
SWE-Bench Verified
76.8%85%
Next.js Evals
19%81%
Benchmarks
LiveCodeBench
85%
GPQA Diamond
87.6%
Overview
CompanyMoonshot AIOpenAI
Release dateJan 27 2026Feb 5 2026
AccessOpen WeightProprietary

Other comparisons

Kimi K2.5vsClaude Opus 5GPT-5.3-CodexvsClaude Opus 5Kimi K2.5vsGemini 3.7 FlashGPT-5.3-CodexvsGemini 3.7 FlashKimi K2.5vsMuse GlimmerGPT-5.3-CodexvsMuse GlimmerKimi K2.5vsGrok 4.6GPT-5.3-CodexvsGrok 4.6Kimi K2.5vsDeepSeek-V4-Pro-0813GPT-5.3-CodexvsDeepSeek-V4-Pro-0813Kimi K2.5vsMistral Medium 3.5GPT-5.3-CodexvsMistral Medium 3.5

Frequently asked questions

GPT-5.3-Codex leads Kimi K2.5 on 2 of the 3 benchmarks they both report (BullshitBench v2, SWE-Bench Verified, Next.js Evals). Kimi K2.5 is cheaper on both input and output: $0.60 vs $1.75 per million input tokens, and $3.00 vs $14.00 per million output tokens. Kimi K2.5 shipped 9 days before GPT-5.3-Codex, so benchmark comparisons should account for the intervening progress.

Kimi K2.5 is open weight, while GPT-5.3-Codex is proprietary.

On BullshitBench v2, Kimi K2.5 leads at 52% vs GPT-5.3-Codex at 24%. On SWE-Bench Verified, GPT-5.3-Codex leads at 85% vs Kimi K2.5 at 76.8%. On Next.js Evals, GPT-5.3-Codex leads at 81% vs Kimi K2.5 at 19%.

Kimi K2.5 was released by Moonshot AI on Jan 27 2026.

GPT-5.3-Codex was released by OpenAI on Feb 5 2026.

GPT-5.3-Codex leads on SWE-Bench Verified — Kimi K2.5 76.8% vs GPT-5.3-Codex 85%.

Kimi K2.5 is cheaper on both input and output: $0.60 vs $1.75 per million input tokens, and $3.00 vs $14.00 per million output tokens. Rates are pay-as-you-go API prices verified on August 18, 2026.

Kimi K2.5 is an open weight model released by Moonshot AI. GPT-5.3-Codex is a proprietary model released by OpenAI.