Model comparison
Granite 3.1 8b Instruct vs MiniMax-M2.1
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 32.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
MiniMaxSummary
- They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 1 category and MiniMax-M2.1 in 8 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.1 leads 58.3 to 35.5.
Side by side
| Granite 3.1 8b Instruct | MiniMax-M2.1 | |
|---|---|---|
| Provider | IBM | MiniMax |
| Noometry Index | 32.4 | 38.9 |
| Released | — | 2025-12-23 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 13 | 22 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.1 leads
Granite 3.1 8b Instruct: 34.5 (#233), MiniMax-M2.1: 40.4 (#143)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Coding | 1186 | 1421 |
| LMArena WebDev | — | 1384 |
| ALE-Bench | — | 623.83 |
Agentic & Tool Use MiniMax-M2.1 leads
Granite 3.1 8b Instruct: 24.1 (#120), MiniMax-M2.1: 27.9 (#98)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.1 |
|---|---|---|
| Terminal-Bench | — | 36.6% |
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 22.1 (#207), MiniMax-M2.1: 16.6 (#302)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Hard Prompts | 1145 | 1411 |
| NYT Connections (extended) | — | 11.2% |
Math MiniMax-M2.1 leads
Granite 3.1 8b Instruct: 33.0 (#209), MiniMax-M2.1: 38.3 (#138)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Math | 1152 | 1397 |
Knowledge MiniMax-M2.1 leads
Granite 3.1 8b Instruct: 31.1 (#220), MiniMax-M2.1: 38.3 (#147)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Expert | 1142 | 1431 |
| Vectara Hallucination Rate | — | 11.8% |
Multilingual MiniMax-M2.1 leads
Granite 3.1 8b Instruct: 30.9 (#260), MiniMax-M2.1: 50.0 (#128)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Non-English | 1099 | 1378 |
| LMArena Chinese | 1145 | 1430 |
| LMArena Russian | 1092 | 1387 |
| LMArena French | — | 1404 |
| LMArena German | — | 1381 |
| LMArena Japanese | — | 1287 |
| LMArena Korean | — | 1298 |
| LMArena Spanish | — | 1397 |
Instruction Following MiniMax-M2.1 leads
Granite 3.1 8b Instruct: 58.6 (#259), MiniMax-M2.1: 73.8 (#112)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Instruction Following | 1131 | 1400 |
Long Context MiniMax-M2.1 leads
Granite 3.1 8b Instruct: 35.2 (#241), MiniMax-M2.1: 43.2 (#101)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Longer Query | 1162 | 1416 |
Writing & Preference MiniMax-M2.1 leads
Granite 3.1 8b Instruct: 35.5 (#266), MiniMax-M2.1: 58.3 (#120)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.1 |
|---|---|---|
| LMArena Text | 1150 | 1392 |
| LMArena Creative Writing | 1129 | 1361 |
| LMArena Multi-Turn | 1108 | 1396 |
Frequently asked questions
Is Granite 3.1 8b Instruct better than MiniMax-M2.1?
MiniMax-M2.1 is the stronger model overall, scoring 38.9 to 32.4 on the Noometry Index.
Is Granite 3.1 8b Instruct or MiniMax-M2.1 better for coding?
MiniMax-M2.1 scores higher on coding benchmarks: 40.4 versus 34.5 in the Noometry coding category.
How many benchmarks do Granite 3.1 8b Instruct and MiniMax-M2.1 share?
12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and MiniMax-M2.1 has 22.