AI Flash Report

Granite 4.1 8B vs MiniCPM-V 4.6 1.3B: Benchmarks, Pricing & Capabilities Compared

TL;DR — Granite 4.1 8B wins for reasoning · MiniCPM-V 4.6 1.3B wins for long-context.

Released
2026-04-29
Context window
131K tokens
Input price
$0.05 / Mtok
Output price
$0.10 / Mtok
Released
2026-05-11
Context window
262K tokens
Input price
$0.00 / Mtok
Output price
$0.00 / Mtok

Benchmark comparison

Benchmark Granite 4.1 8B MiniCPM-V 4.6 1.3B
AA Intelligence Index 12.4 12.7
GPQA Diamond 43.3% 30.5%
HLE 3.8% 4.9%
IF-Bench 38.6% 26.7%
LiveCodeBench Reasoning 12.0% 6.3%
SciCode 21.8% 2.1%
TAU2-bench 27.8% 87.7%
TerminalBench-Hard 0.0% 0.0%

Pricing comparison

Metric Granite 4.1 8B MiniCPM-V 4.6 1.3B
Input ($/Mtok) $0.05 $0.00
Output ($/Mtok) $0.10 $0.00
Cached input ($/Mtok)
Cost per 1M-token roundtrip (1M in + 1M out) $0.15 $0.00

Context window & modalities

Attribute Granite 4.1 8B MiniCPM-V 4.6 1.3B
Context window 131K 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
→ Granite 4.1 8B
Basis: GPQA Diamond

Granite 4.1 8B 43.3% vs MiniCPM-V 4.6 1.3B 30.5% on GPQA Diamond.

Math
Insufficient data
Basis: MATH / AIME

No shared math benchmark.

Long context
→ MiniCPM-V 4.6 1.3B
Basis: Context window

Granite 4.1 8B 131K tokens vs MiniCPM-V 4.6 1.3B 262K tokens.

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

Granite 4.1 8B $0.05/Mtok vs MiniCPM-V 4.6 1.3B $0/Mtok input.

Changelog & releases

Granite 4.1 8B
Released 2026-04-29
MiniCPM-V 4.6 1.3B
Released 2026-05-11

Related comparisons