AI Flash Report

MiniMax-M3 vs Step 3.7 Flash: Benchmarks, Pricing & Capabilities Compared

TL;DR — MiniMax-M3 wins for reasoning + long-context · Step 3.7 Flash wins for cost.

MiniMax-M3 MiniMax
Released
2026-06-01
Context window
1M tokens
Input price
$0.30 / Mtok
Output price
$1.20 / Mtok
Step 3.7 Flash StepFun
Released
2026-05-29
Context window
256K tokens
Input price
$0.20 / Mtok
Output price
$1.15 / Mtok

Benchmark comparison

Benchmark MiniMax-M3 Step 3.7 Flash
AA Intelligence Index 54.7 42.6
GPQA Diamond 92.9% 80.9%
HLE 37.1% 19.9%
IF-Bench 82.9% 67.3%
LiveCodeBench Reasoning 74.0% 63.7%
SciCode 45.4% 40.0%
TAU2-bench 88.9% 98.5%
TerminalBench-Hard 42.4% 35.6%

Pricing comparison

Metric MiniMax-M3 Step 3.7 Flash
Input ($/Mtok) $0.30 $0.20
Output ($/Mtok) $1.20 $1.15
Cached input ($/Mtok)
Cost per 1M-token roundtrip (1M in + 1M out) $1.50 $1.35

Context window & modalities

Attribute MiniMax-M3 Step 3.7 Flash
Context window 1M tokens 256K tokens
Input modalities text, image, video text, image
Output modalities text text
Knowledge cutoff

Verdict by use case

Coding
Insufficient data
Basis: SWE-bench

No shared coding benchmark.

Reasoning
→ MiniMax-M3
Basis: GPQA Diamond

MiniMax-M3 92.9% vs Step 3.7 Flash 80.9% on GPQA Diamond.

Math
Insufficient data
Basis: MATH / AIME

No shared math benchmark.

Long context
→ MiniMax-M3
Basis: Context window

MiniMax-M3 1M tokens vs Step 3.7 Flash 256K tokens.

Cost
→ Step 3.7 Flash
Basis: Input $/Mtok

MiniMax-M3 $0.3/Mtok vs Step 3.7 Flash $0.2/Mtok input.

Changelog & releases

MiniMax-M3
Released 2026-06-01
Step 3.7 Flash
Released 2026-05-29

Related comparisons