Model comparison

Granite 4.2 3b vs Mistral Small

Granite 4.2 3b is the stronger model overall, scoring 39.4 to 33.4 on the Noometry Index.

Last verified October 10, 2026. 11 shared benchmarks.

Granite 4.2 3b IBM

39.4

Rank #169 Confirmed

Mistral Small

Mistral AI

33.4

Rank #243 Confirmed

Summary

They share 11 benchmarks with published results for both. Granite 4.2 3b scores higher in 4 categories and Mistral Small in 3 categories; 6 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Granite 4.2 3b leads 26.0 to 19.8.

Side by side

Granite 4.2 3b and Mistral Small specifications
	Granite 4.2 3b	Mistral Small
Provider	IBM	Mistral AI
Noometry Index	39.4	33.4
Released	—	2024-02-26
Weights	Open	Open
Context window	—	262K
Max output	—	256K
Input $ / M tokens	—	$0.15
Output $ / M tokens	—	$0.60
Results tracked	11	39

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

Category by category

Coding Granite 4.2 3b leads

Granite 4.2 3b: 40.0 (#151), Mistral Small: 34.0 (#247)

Coding benchmarks
Benchmark	Granite 4.2 3b	Mistral Small
LMArena Coding	1361	1362
SciCode	—	26.5%
BigCodeBench Instruct	—	36.1%
LiveBench Coding	—	36.2%
BigCodeBench Complete	—	46.6%
ALE-Bench	—	497.62

Agentic & Tool Use Not comparable

Granite 4.2 3b: —, Mistral Small: 28.1 (#93)

Agentic & Tool Use benchmarks
Benchmark	Granite 4.2 3b	Mistral Small
Berkeley Function Calling Leaderboard	—	37.1%

Reasoning Granite 4.2 3b leads

Granite 4.2 3b: 26.0 (#138), Mistral Small: 19.8 (#250)

Reasoning benchmarks
Benchmark	Granite 4.2 3b	Mistral Small
LMArena Hard Prompts	1306	1335
Kagi LLM Benchmark	—	37.8%
CritPt	—	0%
LiveBench Reasoning	—	44.8%
DTBench	—	70.9%
LiveBench Data Analysis	—	53.7%
LMCA	—	20.6%
LiveBench	—	44%

Math Not comparable

Granite 4.2 3b: —, Mistral Small: 16.4 (#293)

Math benchmarks
Benchmark	Granite 4.2 3b	Mistral Small
OTIS Mock AIME 2024-2025	—	5.8%
LiveBench Math	—	39.9%
LMArena Math	—	1341
MATH Level 5	—	46.8%

Knowledge Granite 4.2 3b leads

Granite 4.2 3b: 36.3 (#171), Mistral Small: 31.0 (#222)

Knowledge benchmarks
Benchmark	Granite 4.2 3b	Mistral Small
LMArena Expert	1315	1291
GPQA Diamond	—	47.5%
Vectara Hallucination Rate	—	5.1%
MMLU	—	68.7%

Multimodal Not comparable

Granite 4.2 3b: —, Mistral Small: 33.5 (#96)

Multimodal benchmarks
Benchmark	Granite 4.2 3b	Mistral Small
LMArena Vision	—	1142

Multilingual Mistral Small leads

Granite 4.2 3b: 42.1 (#198), Mistral Small: 45.5 (#169)

Multilingual benchmarks
Benchmark	Granite 4.2 3b	Mistral Small
LMArena Non-English	1268	1315
LMArena Chinese	1269	1340
LMArena Russian	1249	1324
LMArena French	—	1337
LMArena German	—	1340
LMArena Japanese	—	1275
LMArena Korean	—	1259
LMArena Spanish	—	1346

Instruction Following Too close to call

Granite 4.2 3b: 67.1 (#200), Mistral Small: 66.4 (#209)

Instruction Following benchmarks
Benchmark	Granite 4.2 3b	Mistral Small
LMArena Instruction Following	1273	1310
LiveBench Instruction Following	—	63.7%

Long Context Mistral Small leads

Granite 4.2 3b: 39.2 (#185), Mistral Small: 40.4 (#156)

Long Context benchmarks
Benchmark	Granite 4.2 3b	Mistral Small
LMArena Longer Query	1291	1327

Writing & Preference Mistral Small leads

Granite 4.2 3b: 47.2 (#212), Mistral Small: 52.5 (#171)

Writing & Preference benchmarks
Benchmark	Granite 4.2 3b	Mistral Small
LMArena Text	1293	1338
LMArena Creative Writing	1205	1305
LMArena Multi-Turn	1290	1344
LiveBench Language	—	30.5%

Frequently asked questions

Is Granite 4.2 3b better than Mistral Small?