Compare/Mistral Small 3.2 vs Granite 4.0 H Small

Mistral Small 3.2vsGranite 4.0 H Small

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Mistral

Mistral Small 3.2

Input
$0.087/M
Output
$0.25/M
Speed
121 tok/s
TTFT
0.43s
IBM

Granite 4.0 H Small

Input
$0.06/M
Output
$0.25/M
Speed
265 tok/s
TTFT
8.78s

Winner by Category

Cheaper
Granite 4.0 H Small
Faster (tok/s)
Granite 4.0 H Small
Lower Latency
Mistral Small 3.2
Benchmarks (12-0)
Mistral Small 3.2

Pricing Comparison

MetricMistral Small 3.2Granite 4.0 H Small
Input ($/M tokens)$0.087$0.06
Output ($/M tokens)$0.25$0.25
Cost for 1M input + 100K output tokens:
Mistral Small 3.2$0.11
Granite 4.0 H Small$0.08

Speed Comparison

Output Speed (tokens/s) — higher is better
Mistral Small 3.2
121 tok/s
Granite 4.0 H Small
265 tok/s
Time to First Token (seconds) — lower is better
Mistral Small 3.2
0.43s
Granite 4.0 H Small
8.78s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
15.110.8
Coding Index
13.38.5
Math Index
27.013.7
GPQA Diamond
50.5%41.6%
MMLU-Pro
68.1%62.4%
LiveCodeBench
27.5%25.1%
AIME 2025
27.0%13.7%
MATH-500
88.3%
Humanity's Last Exam
4.3%3.7%
SciCode
26.4%20.9%
IFBench
33.5%31.5%
TerminalBench
6.8%2.3%
Mistral Small 3.212 wins
0 winsGranite 4.0 H Small

Frequently Asked Questions

Which is cheaper, Mistral Small 3.2 or Granite 4.0 H Small?

Granite 4.0 H Small is cheaper overall. Its blended price (3:1 input/output ratio) is $0.11/M tokens vs $0.13/M for Mistral Small 3.2.

Which model performs better on benchmarks?

Mistral Small 3.2 wins 12 out of 12 benchmarks compared to 0 for Granite 4.0 H Small. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Granite 4.0 H Small generates tokens faster at 265 tok/s vs 121 tok/s. Mistral Small 3.2 also has lower time-to-first-token (0.43s vs 8.78s).

When should I use Mistral Small 3.2 vs Granite 4.0 H Small?

Choose based on your priorities: Granite 4.0 H Small for lower cost, Mistral Small 3.2 for stronger benchmark performance, and Granite 4.0 H Small for faster generation. For latency-sensitive apps, check the TTFT comparison above.