ModelsAgree

Head-to-head

Codestral Embed vs Voyage Code 3

Voyage Code 3 leads: the AI models rank it above its rival on 1 of the 1 leaderboard they share. Based on how ChatGPT, Claude, Gemini & Grok rank both across the leaderboard they share — re-polled on demand, reasoning shown verbatim.

Codestral Embed0 wins
Voyage Code 31 win
LeaderboardCodestral EmbedVoyage Code 3
Best code embedding APIs for repository search#2 / 11#1 / 11

Why the models rank Codestral Embed — on best code embedding apis for repository search

Best overall for chunked repository search: excellent real-world issue-to-file retrieval, flexible dimensions and int8 output, and strong value at $0.15/M tokens; narrowly beats Voyage assuming normal code-aware chunking.

Why the models rank Voyage Code 3 — on best code embedding apis for repository search

Purpose-built for code retrieval and consistently at or near the top of code-search benchmarks; long context, Matryoshka-style adjustable dimensions and int8/binary quantization let you trade recall for index cost, which matters at whole-repo scale; mature reranker pairing (rerank-2) and clean API. Near-tie with Codestral Embed at the top.

More head-to-heads

Rankings move. Know when this flips.

The 3 biggest AI-ranking flips, one short email a week.

Ranks from the merged 4-model leaderboards · re-polled on demand · methodology