Model comparison

Granite 4.1 8b vs Mistral Large

Granite 4.1 8b is the stronger model overall, scoring 37.4 to 31.9 on the Noometry Index.

Last verified October 10, 2026. 12 shared benchmarks.

Granite 4.1 8b IBM

37.4

Rank #205 Confirmed

Mistral Large

Mistral AI

31.9

Rank #263 Confirmed

Summary

They share 12 benchmarks with published results for both. Granite 4.1 8b scores higher in 6 categories and Mistral Large in 2 categories; 7 gaps are clear of the uncertainty.
The widest gap is in math, where Granite 4.1 8b leads 36.4 to 18.2.

Side by side

Granite 4.1 8b and Mistral Large specifications
	Granite 4.1 8b	Mistral Large
Provider	IBM	Mistral AI
Noometry Index	37.4	31.9
Released	—	2024-02-26
Weights	Open	Open
Context window	—	131K
Max output	—	16K
Input $ / M tokens	—	$2
Output $ / M tokens	—	$6
Results tracked	13	51

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

Category by category

Coding Mistral Large leads

Granite 4.1 8b: 30.1 (#297), Mistral Large: 34.3 (#240)

Coding benchmarks
Benchmark	Granite 4.1 8b	Mistral Large
LMArena Coding	1312	1277
LMArena WebDev	1192	—
SciCode	—	36.2%
BigCodeBench Instruct	—	30%
LiveBench Coding	—	47.1%
BigCodeBench Complete	—	38.3%
ALE-Bench	—	264.7
HumanEval+	—	62.2%
MBPP+	—	59.5%

Agentic & Tool Use Not comparable

Granite 4.1 8b: —, Mistral Large: 28.6 (#89)

Agentic & Tool Use benchmarks
Benchmark	Granite 4.1 8b	Mistral Large
Berkeley Function Calling Leaderboard	—	38.4%

Reasoning Granite 4.1 8b leads

Granite 4.1 8b: 25.7 (#143), Mistral Large: 15.8 (#310)

Reasoning benchmarks
Benchmark	Granite 4.1 8b	Mistral Large
LMArena Hard Prompts	1293	1257
SimpleBench	—	22.5%
CritPt	—	0%
LiveBench Reasoning	—	43.5%
DTBench	—	65.1%
LiveBench Data Analysis	—	50.1%
LMCA	—	16.7%
Epoch Capabilities Index	—	128.52
ForecastBench	—	57.1
LiveBench	—	48.4%

Math Granite 4.1 8b leads

Granite 4.1 8b: 36.4 (#166), Mistral Large: 18.2 (#291)

Math benchmarks
Benchmark	Granite 4.1 8b	Mistral Large
LMArena Math	1312	1262
OTIS Mock AIME 2024-2025	—	8.5%
Omni-MATH	—	28.1%
LiveBench Math	—	42.5%
MATH Level 5	—	50.3%
FrontierMath (Feb 2025 set)	—	0.3%

Knowledge Granite 4.1 8b leads

Granite 4.1 8b: 36.1 (#174), Mistral Large: 30.1 (#230)

Knowledge benchmarks
Benchmark	Granite 4.1 8b	Mistral Large
LMArena Expert	1309	1232
GPQA Diamond	—	51.3%
MMLU-Pro	—	59.9%
Confabulations	—	21.4%
Vectara Hallucination Rate	—	4.5%
GPQA (HELM)	—	43.5%
MMLU	—	80%

Multilingual Granite 4.1 8b leads

Granite 4.1 8b: 41.7 (#204), Mistral Large: 40.0 (#219)

Multilingual benchmarks
Benchmark	Granite 4.1 8b	Mistral Large
LMArena Non-English	1261	1237
LMArena Chinese	1337	1240
LMArena Russian	1240	1257
LMArena French	—	1325
LMArena German	—	1254
LMArena Japanese	—	1188
LMArena Korean	—	1202
LMArena Spanish	—	1268

Instruction Following Mistral Large leads

Granite 4.1 8b: 66.9 (#203), Mistral Large: 67.9 (#191)

Instruction Following benchmarks
Benchmark	Granite 4.1 8b	Mistral Large
LMArena Instruction Following	1269	1249
LiveBench Instruction Following	—	67.9%
IFEval	—	87.7%

Long Context Too close to call

Granite 4.1 8b: 38.7 (#193), Mistral Large: 38.3 (#199)

Long Context benchmarks
Benchmark	Granite 4.1 8b	Mistral Large
LMArena Longer Query	1275	1261

Writing & Preference Granite 4.1 8b leads

Granite 4.1 8b: 48.1 (#204), Mistral Large: 40.7 (#242)

Writing & Preference benchmarks
Benchmark	Granite 4.1 8b	Mistral Large
LMArena Text	1290	1266
LMArena Creative Writing	1251	1243
LMArena Multi-Turn	1268	1260
Short-Story Creative Writing	—	69%
EQ-Bench Creative Writing	—	985
WildBench	—	80.1%
LiveBench Language	—	39.4%

Frequently asked questions

Is Granite 4.1 8b better than Mistral Large?