Noometry

Model comparison

Granite 3.1 8b Instruct vs Mistral Large 3

Mistral Large 3 is the stronger model overall, scoring 38.6 to 31.8 on the Noometry Index.

Last verified . 12 shared benchmarks.

Granite 3.1 8b Instruct IBM

31.8

Rank #256 Confirmed

Mistral Large 3 Mistral AI

38.6

Rank #172 Confirmed

Summary

  • They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 1 category and Mistral Large 3 in 7 categories; 7 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where Mistral Large 3 leads 60.2 to 35.7.

Side by side

Granite 3.1 8b InstructMistral Large 3
ProviderIBMMistral AI
Noometry Index31.838.6
Released—2025-12-02
WeightsOpenOpen
Context window—262K
Max output—8K
Input $ / M tokens—$0.25
Output $ / M tokens—$0.75
Results tracked1324

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

Category by category

Coding Too close to call

Granite 3.1 8b Instruct: 33.9 (#232), Mistral Large 3: 34.1 (#230)

BenchmarkGranite 3.1 8b InstructMistral Large 3
LMArena Coding11861447
LMArena WebDev—1230

Agentic & Tool Use Not comparable

Granite 3.1 8b Instruct: 23.9 (#113), Mistral Large 3: —

BenchmarkGranite 3.1 8b InstructMistral Large 3
Berkeley Function Calling Leaderboard27.1%—

Reasoning Granite 3.1 8b Instruct leads

Granite 3.1 8b Instruct: 21.2 (#204), Mistral Large 3: 14.6 (#314)

BenchmarkGranite 3.1 8b InstructMistral Large 3
LMArena Hard Prompts11461429
Kagi LLM Benchmark—50.9%
NYT Connections (extended)—7.5%
Thematic Generalization—23%

Math Mistral Large 3 leads

Granite 3.1 8b Instruct: 30.4 (#210), Mistral Large 3: 36.0 (#131)

BenchmarkGranite 3.1 8b InstructMistral Large 3
LMArena Math11521415

Knowledge Mistral Large 3 leads

Granite 3.1 8b Instruct: 30.6 (#218), Mistral Large 3: 35.5 (#173)

BenchmarkGranite 3.1 8b InstructMistral Large 3
LMArena Expert11421421
Vectara Hallucination Rate—14.5%

Multimodal Not comparable

Granite 3.1 8b Instruct: —, Mistral Large 3: 37.6 (#65)

BenchmarkGranite 3.1 8b InstructMistral Large 3
LMArena Vision—1222

Multilingual Mistral Large 3 leads

Granite 3.1 8b Instruct: 31.1 (#255), Mistral Large 3: 52.6 (#79)

BenchmarkGranite 3.1 8b InstructMistral Large 3
LMArena Non-English10991412
LMArena Chinese11451448
LMArena Russian10921412
LMArena French—1456
LMArena German—1438
LMArena Japanese—1399
LMArena Korean—1384
LMArena Spanish—1437

Instruction Following Mistral Large 3 leads

Granite 3.1 8b Instruct: 58.9 (#254), Mistral Large 3: 74.1 (#104)

BenchmarkGranite 3.1 8b InstructMistral Large 3
LMArena Instruction Following11311402

Long Context Mistral Large 3 leads

Granite 3.1 8b Instruct: 35.2 (#236), Mistral Large 3: 43.1 (#102)

BenchmarkGranite 3.1 8b InstructMistral Large 3
LMArena Longer Query11621413

Writing & Preference Mistral Large 3 leads

Granite 3.1 8b Instruct: 35.7 (#261), Mistral Large 3: 60.2 (#100)

BenchmarkGranite 3.1 8b InstructMistral Large 3
LMArena Text11501427
LMArena Creative Writing11291385
LMArena Multi-Turn11081429
EQ-Bench Creative Writing—1412

Frequently asked questions

Is Granite 3.1 8b Instruct better than Mistral Large 3?

Mistral Large 3 is the stronger model overall, scoring 38.6 to 31.8 on the Noometry Index.

Is Granite 3.1 8b Instruct or Mistral Large 3 better for coding?

They score almost the same on coding (33.9 vs 34.1); test both on your own repository before choosing.

How many benchmarks do Granite 3.1 8b Instruct and Mistral Large 3 share?

12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Mistral Large 3 has 24.

Related comparisons

Go deeper