Model comparison

Granite 4.2 8B vs Mistral Small 3.2

Granite 4.2 8B is the stronger model overall, scoring 40.5 to 31.2 on the Noometry Index.

Last verified October 11, 2026. 0 shared benchmarks.

Granite 4.2 8B IBM

40.5

Rank #148 Confirmed

Mistral Small 3.2

Mistral AI

31.2

Rank #280 Confirmed

Summary

The widest gap is in knowledge, where Granite 4.2 8B leads 38.4 to 26.7.
Granite 4.2 8B is cheaper at $0.06 / $0.25 per million input/output tokens, against $0.0938 / $0.25 for Mistral Small 3.2.
Mistral Small 3.2 accepts more context: 256K tokens versus 131K.

Side by side

Granite 4.2 8B and Mistral Small 3.2 specifications
	Granite 4.2 8B	Mistral Small 3.2
Provider	IBM	Mistral AI
Noometry Index	40.5	31.2
Released	—	2025-06-20
Weights	Open	Open
Context window	131K	256K
Max output	118K	16K
Input $ / M tokens	$0.06	$0.0938
Output $ / M tokens	$0.25	$0.25
Results tracked	11	6

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

Granite 4.2 8B: 40.5 (#137), Mistral Small 3.2: —

Coding benchmarks
Benchmark	Granite 4.2 8B	Mistral Small 3.2
LMArena Coding	1380	—

Reasoning Granite 4.2 8B leads

Granite 4.2 8B: 26.6 (#131), Mistral Small 3.2: 18.1 (#287)

Reasoning benchmarks
Benchmark	Granite 4.2 8B	Mistral Small 3.2
Kagi LLM Benchmark	—	40.4%
Chess Puzzles	—	1%
LMArena Hard Prompts	1329	—
Epoch Capabilities Index	—	131.74

Math Not comparable

Granite 4.2 8B: —, Mistral Small 3.2: 26.3 (#260)

Math benchmarks
Benchmark	Granite 4.2 8B	Mistral Small 3.2
OTIS Mock AIME 2024-2025	—	30.3%

Knowledge Granite 4.2 8B leads

Granite 4.2 8B: 38.4 (#145), Mistral Small 3.2: 26.7 (#256)

Knowledge benchmarks
Benchmark	Granite 4.2 8B	Mistral Small 3.2
GPQA Diamond	—	49.1%
LMArena Expert	1384	—

Multilingual Not comparable

Granite 4.2 8B: 44.5 (#178), Mistral Small 3.2: —

Multilingual benchmarks
Benchmark	Granite 4.2 8B	Mistral Small 3.2
LMArena Non-English	1302	—
LMArena Chinese	1366	—
LMArena Russian	1285	—

Instruction Following Not comparable

Granite 4.2 8B: 68.7 (#184), Mistral Small 3.2: —

Instruction Following benchmarks
Benchmark	Granite 4.2 8B	Mistral Small 3.2
LMArena Instruction Following	1301	—

Long Context Not comparable

Granite 4.2 8B: 40.3 (#159), Mistral Small 3.2: —

Long Context benchmarks
Benchmark	Granite 4.2 8B	Mistral Small 3.2
LMArena Longer Query	1324	—

Writing & Preference Granite 4.2 8B leads

Granite 4.2 8B: 49.6 (#189), Mistral Small 3.2: 45.0 (#224)

Writing & Preference benchmarks
Benchmark	Granite 4.2 8B	Mistral Small 3.2
LMArena Text	1320	—
LMArena Creative Writing	1236	—
EQ-Bench Creative Writing	—	1255
LMArena Multi-Turn	1301	—

Frequently asked questions

Is Granite 4.2 8B better than Mistral Small 3.2?

Granite 4.2 8B is the stronger model overall, scoring 40.5 to 31.2 on the Noometry Index.

Which is cheaper, Granite 4.2 8B or Mistral Small 3.2?

Granite 4.2 8B is cheaper. It lists at $0.06 per million input tokens and $0.25 per million output tokens; Mistral Small 3.2 lists at $0.0938 and $0.25.

Which has the bigger context window?

Mistral Small 3.2 does, with 256K tokens against 131K.

How many benchmarks do Granite 4.2 8B and Mistral Small 3.2 share?

0 benchmarks have published results for both models. Granite 4.2 8B has 11 scored results on Noometry and Mistral Small 3.2 has 6.