Model comparison
Granite 3.1 8b Instruct vs MiniMax-M2.7
MiniMax-M2.7 is the stronger model overall, scoring 37.7 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 2 categories and MiniMax-M2.7 in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiniMax-M2.7 leads 58.9 to 35.5.
Side by side
| Granite 3.1 8b Instruct | MiniMax-M2.7 | |
|---|---|---|
| Provider | IBM | MiniMax |
| Noometry Index | 32.4 | 37.7 |
| Released | — | 2026-03-18 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 13 | 30 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.7 leads
Granite 3.1 8b Instruct: 34.5 (#233), MiniMax-M2.7: 41.8 (#120)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.7 |
|---|---|---|
| LMArena Coding | 1186 | 1454 |
| LMArena WebDev | — | 1398 |
| SciCode | — | 47% |
| WeirdML | — | 37% |
| ALE-Bench | — | 599.25 |
Agentic & Tool Use Too close to call
Granite 3.1 8b Instruct: 24.1 (#120), MiniMax-M2.7: 25.1 (#111)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.7 |
|---|---|---|
| Terminal-Bench | — | 45.1% |
| Berkeley Function Calling Leaderboard | 27.1% | — |
| ExploitBench | — | 13.3% |
| GBAEval | — | 0% |
Reasoning Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 22.1 (#207), MiniMax-M2.7: 19.7 (#253)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.7 |
|---|---|---|
| LMArena Hard Prompts | 1145 | 1422 |
| NYT Connections (extended) | — | 24.7% |
| CritPt | — | 0.6% |
| Thematic Generalization | — | 39.3% |
| Epoch Capabilities Index | — | 145.85 |
Math Granite 3.1 8b Instruct leads
Granite 3.1 8b Instruct: 33.0 (#209), MiniMax-M2.7: 25.9 (#263)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.7 |
|---|---|---|
| LMArena Math | 1152 | 1420 |
| ProofBench | — | 3% |
Knowledge MiniMax-M2.7 leads
Granite 3.1 8b Instruct: 31.1 (#220), MiniMax-M2.7: 37.7 (#152)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.7 |
|---|---|---|
| LMArena Expert | 1142 | 1444 |
| Vectara Hallucination Rate | — | 12.9% |
Multilingual MiniMax-M2.7 leads
Granite 3.1 8b Instruct: 30.9 (#260), MiniMax-M2.7: 50.3 (#123)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.7 |
|---|---|---|
| LMArena Non-English | 1099 | 1382 |
| LMArena Chinese | 1145 | 1441 |
| LMArena Russian | 1092 | 1383 |
| LMArena French | — | 1421 |
| LMArena German | — | 1398 |
| LMArena Japanese | — | 1262 |
| LMArena Korean | — | 1313 |
| LMArena Spanish | — | 1403 |
Instruction Following MiniMax-M2.7 leads
Granite 3.1 8b Instruct: 58.6 (#259), MiniMax-M2.7: 74.1 (#103)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.7 |
|---|---|---|
| LMArena Instruction Following | 1131 | 1405 |
Long Context MiniMax-M2.7 leads
Granite 3.1 8b Instruct: 35.2 (#241), MiniMax-M2.7: 43.3 (#99)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.7 |
|---|---|---|
| LMArena Longer Query | 1162 | 1419 |
Writing & Preference MiniMax-M2.7 leads
Granite 3.1 8b Instruct: 35.5 (#266), MiniMax-M2.7: 58.9 (#112)
| Benchmark | Granite 3.1 8b Instruct | MiniMax-M2.7 |
|---|---|---|
| LMArena Text | 1150 | 1405 |
| LMArena Creative Writing | 1129 | 1354 |
| LMArena Multi-Turn | 1108 | 1412 |
Frequently asked questions
Is Granite 3.1 8b Instruct better than MiniMax-M2.7?
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 32.4 on the Noometry Index.
Is Granite 3.1 8b Instruct or MiniMax-M2.7 better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 34.5 in the Noometry coding category.
How many benchmarks do Granite 3.1 8b Instruct and MiniMax-M2.7 share?
12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and MiniMax-M2.7 has 30.