Model comparison
Granite 3.1 2b Instruct vs Mistral Large 3
Mistral Large 3 is the stronger model overall, scoring 39.1 to 33.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
Mistral AISummary
- They share 12 benchmarks with published results for both. Granite 3.1 2b 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 60.0 to 34.1.
Side by side
| Granite 3.1 2b Instruct | Mistral Large 3 | |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 33.2 | 39.1 |
| Released | — | 2025-12-02 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 8K |
| Input $ / M tokens | — | $0.25 |
| Output $ / M tokens | — | $0.75 |
| Results tracked | 12 | 24 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Granite 3.1 2b Instruct: 33.4 (#257), Mistral Large 3: 34.4 (#237)
| Benchmark | Granite 3.1 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Coding | 1149 | 1448 |
| LMArena WebDev | — | 1230 |
Reasoning Granite 3.1 2b Instruct leads
Granite 3.1 2b Instruct: 22.0 (#209), Mistral Large 3: 15.2 (#319)
| Benchmark | Granite 3.1 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Hard Prompts | 1138 | 1429 |
| Kagi LLM Benchmark | — | 50.9% |
| NYT Connections (extended) | — | 7.5% |
| Thematic Generalization | — | 23% |
Math Mistral Large 3 leads
Granite 3.1 2b Instruct: 33.1 (#206), Mistral Large 3: 38.7 (#129)
| Benchmark | Granite 3.1 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Math | 1159 | 1414 |
Knowledge Mistral Large 3 leads
Granite 3.1 2b Instruct: 30.8 (#224), Mistral Large 3: 36.0 (#177)
| Benchmark | Granite 3.1 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Expert | 1131 | 1421 |
| Vectara Hallucination Rate | — | 14.5% |
Multimodal Not comparable
Granite 3.1 2b Instruct: —, Mistral Large 3: 38.2 (#66)
| Benchmark | Granite 3.1 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Vision | — | 1221 |
Multilingual Mistral Large 3 leads
Granite 3.1 2b Instruct: 29.1 (#269), Mistral Large 3: 52.5 (#84)
| Benchmark | Granite 3.1 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Non-English | 1068 | 1413 |
| LMArena Chinese | 1139 | 1447 |
| LMArena Russian | 1063 | 1411 |
| LMArena French | — | 1455 |
| LMArena German | — | 1437 |
| LMArena Japanese | — | 1394 |
| LMArena Korean | — | 1384 |
| LMArena Spanish | — | 1440 |
Instruction Following Mistral Large 3 leads
Granite 3.1 2b Instruct: 57.7 (#264), Mistral Large 3: 74.0 (#108)
| Benchmark | Granite 3.1 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Instruction Following | 1116 | 1403 |
Long Context Mistral Large 3 leads
Granite 3.1 2b Instruct: 35.0 (#244), Mistral Large 3: 43.1 (#105)
| Benchmark | Granite 3.1 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Longer Query | 1155 | 1413 |
Writing & Preference Mistral Large 3 leads
Granite 3.1 2b Instruct: 34.1 (#274), Mistral Large 3: 60.0 (#101)
| Benchmark | Granite 3.1 2b Instruct | Mistral Large 3 |
|---|---|---|
| LMArena Text | 1127 | 1428 |
| LMArena Creative Writing | 1116 | 1386 |
| LMArena Multi-Turn | 1099 | 1429 |
| EQ-Bench Creative Writing | — | 1412 |
Frequently asked questions
Is Granite 3.1 2b Instruct better than Mistral Large 3?
Mistral Large 3 is the stronger model overall, scoring 39.1 to 33.2 on the Noometry Index.
Is Granite 3.1 2b Instruct or Mistral Large 3 better for coding?
They score almost the same on coding (33.4 vs 34.4); test both on your own repository before choosing.
How many benchmarks do Granite 3.1 2b Instruct and Mistral Large 3 share?
12 benchmarks have published results for both models. Granite 3.1 2b Instruct has 12 scored results on Noometry and Mistral Large 3 has 24.