The Model Index
Up to four models

GPT-5.3-Codex vs Kimi K2.5

On the index (GPT-4 = 100), GPT-5.3-Codex scores 165 and Kimi K2.5 145. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to GPT-5.3-Codex
Presets
GPT-5.3-Codex
165149–182
WeightsClosed
ReleasedFeb 2026
Price in / out$1.75 / $14
Context400K
Core tests taken2 of 9
Kimi K2.5
145130–161
WeightsOpen
ReleasedJan 2026
Price in / out$0.50 / $2.5
Context262K
Core tests taken5 of 9

GPT-5.3-Codex leads Kimi K2.5 by 20 points, ahead on 1 of 1 shared core tests, at 4.8× the price.

Test by testthird-party results

GPT-5.3-CodexKimi K2.5
0%25%50%75%100%CODINGSWE-bench VerifiedSWE-bench VerifiedTerminal-Bench 2.0 (Terminus 2 runs)Terminal-Bench 2.0 (Terminus 2 runs)LiveCodeBenchLiveCodeBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1WeirdMLWeirdML
Every result as a table
TestGPT-5.3-CodexKimi K2.5
Coding
SWE-bench Verified74.8%73.8%
Terminal-Bench 2.0 (Terminus 2 runs)64.7%43.2%
LiveCodeBench87.3%83.9%
SWE-bench78.0%70.0%
Vibe Code Bench v1.161.8%17.5%
WeirdML79.3%45.6%
Task length · METR45 sec

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG