Model comparison
Granite 4.1 8b vs MiniMax-M2
Granite 4.1 8b and MiniMax-M2 score almost the same on the Noometry Index (37.4 vs 37.4), so choose on price, context window or the category you care about most.
Last verified . 13 shared benchmarks.
MiniMaxSummary
- They share 13 benchmarks with published results for both. Granite 4.1 8b scores higher in 1 category and MiniMax-M2 in 7 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2 leads 39.3 to 30.1.
Side by side
| Granite 4.1 8b | MiniMax-M2 | |
|---|---|---|
| Provider | IBM | MiniMax |
| Noometry Index | 37.4 | 37.4 |
| Released | — | 2025-10-27 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 13 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
Granite 4.1 8b: 30.1 (#297), MiniMax-M2: 39.3 (#159)
| Benchmark | Granite 4.1 8b | MiniMax-M2 |
|---|---|---|
| LMArena WebDev | 1192 | 1297 |
| LMArena Coding | 1312 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
Agentic & Tool Use Not comparable
Granite 4.1 8b: —, MiniMax-M2: 25.1 (#109)
| Benchmark | Granite 4.1 8b | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning Granite 4.1 8b leads
Granite 4.1 8b: 25.7 (#143), MiniMax-M2: 19.4 (#258)
| Benchmark | Granite 4.1 8b | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1293 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
Math Too close to call
Granite 4.1 8b: 36.4 (#166), MiniMax-M2: 37.3 (#160)
| Benchmark | Granite 4.1 8b | MiniMax-M2 |
|---|---|---|
| LMArena Math | 1312 | 1352 |
Knowledge Too close to call
Granite 4.1 8b: 36.1 (#174), MiniMax-M2: 37.0 (#163)
| Benchmark | Granite 4.1 8b | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1309 | 1337 |
Multilingual MiniMax-M2 leads
Granite 4.1 8b: 41.7 (#204), MiniMax-M2: 45.3 (#171)
| Benchmark | Granite 4.1 8b | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1261 | 1313 |
| LMArena Chinese | 1337 | 1366 |
| LMArena Russian | 1240 | 1331 |
| LMArena French | — | 1335 |
| LMArena German | — | 1355 |
| LMArena Spanish | — | 1326 |
Instruction Following MiniMax-M2 leads
Granite 4.1 8b: 66.9 (#203), MiniMax-M2: 70.2 (#166)
| Benchmark | Granite 4.1 8b | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1269 | 1328 |
Long Context MiniMax-M2 leads
Granite 4.1 8b: 38.7 (#193), MiniMax-M2: 40.5 (#153)
| Benchmark | Granite 4.1 8b | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1275 | 1331 |
Writing & Preference MiniMax-M2 leads
Granite 4.1 8b: 48.1 (#204), MiniMax-M2: 53.0 (#162)
| Benchmark | Granite 4.1 8b | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1290 | 1340 |
| LMArena Creative Writing | 1251 | 1286 |
| LMArena Multi-Turn | 1268 | 1361 |
Frequently asked questions
Is Granite 4.1 8b better than MiniMax-M2?
Granite 4.1 8b and MiniMax-M2 score almost the same on the Noometry Index (37.4 vs 37.4), so choose on price, context window or the category you care about most.
Is Granite 4.1 8b or MiniMax-M2 better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.3 versus 30.1 in the Noometry coding category.
How many benchmarks do Granite 4.1 8b and MiniMax-M2 share?
13 benchmarks have published results for both models. Granite 4.1 8b has 13 scored results on Noometry and MiniMax-M2 has 21.