Model comparison
Granite 3.1 8b Instruct vs Ministral 8B
Granite 3.1 8b Instruct is the stronger model overall, scoring 32.4 to 28.2 on the Noometry Index.
Last verified . 13 shared benchmarks.
Mistral AISummary
- They share 13 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 4 categories and Ministral 8B in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Granite 3.1 8b Instruct leads 31.1 to 12.6.
- The biggest single-benchmark swing is Berkeley Function Calling Leaderboard: 27.1% for Granite 3.1 8b Instruct and 11.1% for Ministral 8B.
Side by side
| Granite 3.1 8b Instruct | Ministral 8B | |
|---|---|---|
| Provider | IBM | Mistral AI |
| Noometry Index | 32.4 | 28.2 |
| Released | — | 2024-10-01 |
| Weights | Open | Open |
| Context window | — | 262K |
| Max output | — | 262K |
| Input $ / M tokens | — | $0.15 |
| Output $ / M tokens | — | $0.15 |
| Results tracked | 13 | 17 |
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: 34.5 (#233), Ministral 8B: 35.0 (#230)
| Benchmark | Granite 3.1 8b Instruct | Ministral 8B |
|---|---|---|
| LMArena Coding | 1186 | 1202 |
Agentic & Tool Use Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 24.1 (#120), Ministral 8B: 16.4 (#148)
| Benchmark | Granite 3.1 8b Instruct | Ministral 8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | 11.1% |
Reasoning Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 22.1 (#207), Ministral 8B: 18.4 (#281)
| Benchmark | Granite 3.1 8b Instruct | Ministral 8B |
|---|---|---|
| LMArena Hard Prompts | 1145 | 1191 |
| DTBench | — | 45.7% |
Math Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 33.0 (#209), Ministral 8B: 25.7 (#267)
| Benchmark | Granite 3.1 8b Instruct | Ministral 8B |
|---|---|---|
| LMArena Math | 1152 | 1188 |
| MATH Level 5 | — | 14.9% |
Knowledge Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 31.1 (#220), Ministral 8B: 12.6 (#297)
| Benchmark | Granite 3.1 8b Instruct | Ministral 8B |
|---|---|---|
| LMArena Expert | 1142 | 1170 |
| GPQA Diamond | — | 27.1% |
| Vectara Hallucination Rate | — | 7.4% |
Multilingual Ministral 8B leads
Granite 3.1 8b Instruct: 30.9 (#260), Ministral 8B: 35.1 (#247)
| Benchmark | Granite 3.1 8b Instruct | Ministral 8B |
|---|---|---|
| LMArena Non-English | 1099 | 1165 |
| LMArena Chinese | 1145 | 1193 |
| LMArena Russian | 1092 | 1195 |
Instruction Following Ministral 8B leads
Granite 3.1 8b Instruct: 58.6 (#259), Ministral 8B: 60.5 (#250)
| Benchmark | Granite 3.1 8b Instruct | Ministral 8B |
|---|---|---|
| LMArena Instruction Following | 1131 | 1161 |
Long Context Ministral 8B leads
Granite 3.1 8b Instruct: 35.2 (#241), Ministral 8B: 36.7 (#227)
| Benchmark | Granite 3.1 8b Instruct | Ministral 8B |
|---|---|---|
| LMArena Longer Query | 1162 | 1212 |
Writing & Preference Ministral 8B leads
Granite 3.1 8b Instruct: 35.5 (#266), Ministral 8B: 39.6 (#246)
| Benchmark | Granite 3.1 8b Instruct | Ministral 8B |
|---|---|---|
| LMArena Text | 1150 | 1191 |
| LMArena Creative Writing | 1129 | 1175 |
| LMArena Multi-Turn | 1108 | 1166 |
Frequently asked questions
Is Granite 3.1 8b Instruct better than Ministral 8B?
Granite 3.1 8b Instruct is the stronger model overall, scoring 32.4 to 28.2 on the Noometry Index.
Is Granite 3.1 8b Instruct or Ministral 8B better for coding?
They score almost the same on coding (34.5 vs 35.0); test both on your own repository before choosing.
How many benchmarks do Granite 3.1 8b Instruct and Ministral 8B share?
13 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and Ministral 8B has 17.