MiniMax H3 Flash Benchmarks, Pricing & Rankings
MiniMax · 2026-09-02 · Open · Current
Snapshot 2026-10-14 · updated weekly
MiniMax H3 Flash ranks #30 of 42 on the AMR leaderboard.
MiniMax H3 Flash benchmark scores
| GPQA Diamond | 72.6% | |
| MMLU-Pro | 71.2% | |
| SWE-Bench Verified | 45.8% | |
| AIME 2025 | 69.4% | |
| LiveCodeBench v6 | 61.5% | |
| Arena Elo | 1338 |
MiniMax H3 Flash price, speed & context
Input price
$0.10
per 1M tokens
Output price
$0.40
per 1M tokens
Speed
358
tok/s
Context
512K
tokens
About MiniMax H3 Flash
MiniMax H3 Flash undercuts Gemini 3.8 Flash on price and edges it on speed, making it the cheapest fast open model with a 512K context.
Models around MiniMax H3 Flash in the rankings
More MiniMax models
MiniMax H3 Flash FAQ
Where does MiniMax H3 Flash rank?
MiniMax H3 Flash ranks #30 of 42 tracked AI models on the AMR aggregate as of October 2026, with an aggregate score of 78.8. Its strongest dimension is GPQA Diamond at 72.6%.
How much does MiniMax H3 Flash cost?
MiniMax H3 Flash costs $0.10 per million input tokens and $0.40 per million output tokens on the standard API. At a typical 1:3 input/output agent workload, that blends to roughly $0.33 per million tokens.
What is the MiniMax H3 Flash context window?
MiniMax H3 Flash supports a 512K token context window and generates at a median 358 output tokens per second. That context fits roughly 341 standard documents in a single prompt.
Is MiniMax H3 Flash open source?
Yes — MiniMax H3 Flash ships open weights that you can download and self-host or serve through any compatible inference provider.
What is better than MiniMax H3 Flash?
Qwen3.8 27B ranks one place higher at #29 with an AMR score of 79.8. MiniMax H3 Flash still wins 0 of the tracked dimensions head-to-head — check the comparison table to see exactly which.