Skip to main content

MiniMax H3

MiniMaxMiniMax
Release Date
2026-07
Parameters
Context Length
205K
Modalities
text

Capability Radar

60
general
60
coding
60
reasoning
51
scienceest.
70
agents
0
multimodal

Science uses a reasoning proxy when dedicated science benchmarks are unavailable.

Rankings

Domain#RankScoreSource
Agentic Capability99
51.0
LS
Image-to-Video2
96.0
AA
Text-to-Video2
97.0
AA

Benchmark Scores (LLM Stats)

Agents

BrowseComp62.0%SR
Terminal-Bench47.9%SR
Toolathlon43.5%SR

Biology

GPQA81.0%SR
SciCode39.0%SR

Code

VIBE Web91.5%SR
VIBE Android89.7%SR
VIBE88.6%SR
VIBE iOS88.0%SR
VIBE Simulation87.1%SR
VIBE Backend86.7%SR
LiveCodeBench78.0%SR
SWE-bench Multilingual72.5%SR
SWT-Bench69.3%SR
SWE-Bench Verified67.0%SR
Multi-SWE-Bench49.4%SR
OctoCodingBench26.1%SR
SWE-Review8.9%SR
SWE-Perf3.1%SR

Communication

Tau2 Telecom87.0%SR

Finance

MMLU-Pro88.0%SR

General

IFBench70.0%SR

Long Context

AA-LCR62.0%SR

Math

AIME 202581.0%SR
Humanity's Last Exam22.0%SR

AA Evaluation Indices

No AA evaluation data available

LLM Stats Category Scores

Language
90
Legal
90
Finance
90
Healthcare
90
Communication
90
Instruction Following
70
Frontend Development
70
Tool Calling
70
Long Context
60
Math
60
Physics
60
Reasoning
60
Search
60
General
60
Biology
60
Chemistry
60
Code
60
Agents
50
Vision
20

Pricing

Input Price$0.3 / 1M tokens
Output Price$1.2 / 1M tokens
Blended Price (3:1)$0.525 / 1M tokens

Speed

No speed data available

Provider Price Ranking

Provider Price Ranking

1 providers

ProviderInputOutput
1MiniMaxPRIMARY
$0.3
$1.2

Compare pricing across different API providers for this model.

External Sources