AI Flash Report

DeepSeek V4 Flash vs MiniCPM-V 4.6 1.3B: Benchmarks, Pricing & Capabilities Compared

TL;DR — DeepSeek V4 Flash wins for reasoning + long-context · MiniCPM-V 4.6 1.3B wins for general use.

Released
2026-04-24
Context window
1M tokens
Input price
$0.14 / Mtok
Output price
$0.28 / Mtok
Released
2026-05-11
Context window
262K tokens
Input price
$0.00 / Mtok
Output price
$0.00 / Mtok

Benchmark comparison

Benchmark DeepSeek V4 Flash MiniCPM-V 4.6 1.3B
AA Intelligence Index 46.5 12.7
GPQA Diamond 89.4% 30.5%
HLE 32.1% 4.9%
IF-Bench 79.2% 26.7%
LiveCodeBench Reasoning 63.0% 6.3%
SciCode 44.9% 2.1%
TAU2-bench 95.0% 87.7%
TerminalBench-Hard 35.6% 0.0%

Pricing comparison

Metric DeepSeek V4 Flash MiniCPM-V 4.6 1.3B
Input ($/Mtok) $0.14 $0.00
Output ($/Mtok) $0.28 $0.00
Cached input ($/Mtok)
Cost per 1M-token roundtrip (1M in + 1M out) $0.42 $0.00

Context window & modalities

Attribute DeepSeek V4 Flash MiniCPM-V 4.6 1.3B
Context window 1M tokens 262K tokens
Input modalities text text, image, video
Output modalities text text
Knowledge cutoff

Verdict by use case

Coding
Insufficient data
Basis: SWE-bench

No shared coding benchmark.

Reasoning
→ DeepSeek V4 Flash
Basis: GPQA Diamond

DeepSeek V4 Flash 89.4% vs MiniCPM-V 4.6 1.3B 30.5% on GPQA Diamond.

Math
Insufficient data
Basis: MATH / AIME

No shared math benchmark.

Long context
→ DeepSeek V4 Flash
Basis: Context window

DeepSeek V4 Flash 1M tokens vs MiniCPM-V 4.6 1.3B 262K tokens.

Cost
→ MiniCPM-V 4.6 1.3B
Basis: Input $/Mtok

DeepSeek V4 Flash $0.14/Mtok vs MiniCPM-V 4.6 1.3B $0/Mtok input.

Changelog & releases

DeepSeek V4 Flash
Released 2026-04-24
MiniCPM-V 4.6 1.3B
Released 2026-05-11

Related comparisons