DataLearner logo

Hy3vsMiniMax M3

Across 4 shared benchmarks, Hy3 leads overall: Hy3 wins 3, MiniMax M3 wins 1, with 0 ties and an average score difference of +2.55.

腾讯AI实验室
Hy3

腾讯AI实验室 · 2026-07-06 · Reasoning model

MiniMaxAI
MiniMax M3

MiniMaxAI · 2026-06-01 · Multimodal model

Hy33 wins(75%)(25%)1 winMiniMax M3

Benchmark scores

Grouped by capability, sorted by largest gap within each. 4 shared benchmarks.

AI Agent - Tool Usage

Hy3 2/2
BenchmarkHy3MiniMax M3Diff
Terminal-Bench 2.171.7030 / 44Thinking High (With Tools)6635 / 44Thinking (With Tools)+5.70
MCP-Atlas79.109 / 38Thinking High (With Tools)74.2022 / 38Thinking (With Tools)+4.90

AI Agent - Information Search

Hy3 1/1
BenchmarkHy3MiniMax M3Diff
BrowseComp84.2010 / 54Thinking High (With Tools + Internet)83.5012 / 54Thinking (With Tools + Internet)+0.70

Coding and Software Engineer

MiniMax M3 1/1
BenchmarkHy3MiniMax M3Diff
SWE-Bench Pro - Public57.9018 / 57Thinking High (With Tools)5913 / 57Thinking (With Tools)-1.10

Specs

FieldHy3MiniMax M3
Publisher腾讯AI实验室MiniMaxAI
Release date2026-07-062026-06-01
Model typeReasoning modelMultimodal model
ArchitectureMoEMoE
Parameters295B428B
Context length256K1M
Max outputNot available512K

API pricing

Prices use DataLearner records when available; missing fields are not inferred.

ItemHy3MiniMax M3
Text input¥1.2 / 1M tokens¥2.1 / 1M tokens
Text output¥4 / 1M tokens¥8.4 / 1M tokens
Cache read¥0.4 / 1M tokens¥0.42 / 1M tokens

Summary

  • Hy3leads in:AI Agent - Tool Usage (2/2), AI Agent - Information Search (1/1)
  • MiniMax M3leads in:Coding and Software Engineer (1/1)

On average across the 4 shared benchmarks, Hy3 scores 2.55 higher.

Largest single-benchmark gap: Terminal-Bench 2.1 — Hy3 71.70 vs MiniMax M3 66 (+5.70).

Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.