Model comparison
Granite 4.2 3b vs MiniMax-M2
Granite 4.2 3b is the stronger model overall, scoring 39.0 to 36.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
MiniMaxSummary
- They share 11 benchmarks with published results for both. Granite 4.2 3b scores higher in 2 categories and MiniMax-M2 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Granite 4.2 3b leads 25.0 to 18.6.
Side by side
| Granite 4.2 3b | MiniMax-M2 | |
|---|---|---|
| Provider | IBM | MiniMax |
| Noometry Index | 39.0 | 36.9 |
| 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 | 11 | 21 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Granite 4.2 3b: 39.4 (#146), MiniMax-M2: 39.1 (#151)
| Benchmark | Granite 4.2 3b | MiniMax-M2 |
|---|---|---|
| LMArena Coding | 1363 | 1370 |
| SWE-bench Verified (bash only) | — | 61% |
| LMArena WebDev | — | 1297 |
Agentic & Tool Use Not comparable
Granite 4.2 3b: —, MiniMax-M2: 24.9 (#102)
| Benchmark | Granite 4.2 3b | MiniMax-M2 |
|---|---|---|
| Terminal-Bench | — | 30% |
| Vending-Bench 2 | — | 160.6 |
Reasoning Granite 4.2 3b leads
Granite 4.2 3b: 25.0 (#136), MiniMax-M2: 18.6 (#256)
| Benchmark | Granite 4.2 3b | MiniMax-M2 |
|---|---|---|
| LMArena Hard Prompts | 1308 | 1357 |
| Kagi LLM Benchmark | — | 57.8% |
| NYT Connections (extended) | — | 14.8% |
Math Not comparable
Granite 4.2 3b: —, MiniMax-M2: 34.6 (#158)
| Benchmark | Granite 4.2 3b | MiniMax-M2 |
|---|---|---|
| LMArena Math | — | 1350 |
Knowledge Too close to call
Granite 4.2 3b: 35.6 (#169), MiniMax-M2: 36.3 (#160)
| Benchmark | Granite 4.2 3b | MiniMax-M2 |
|---|---|---|
| LMArena Expert | 1313 | 1336 |
Multilingual MiniMax-M2 leads
Granite 4.2 3b: 42.4 (#193), MiniMax-M2: 45.6 (#165)
| Benchmark | Granite 4.2 3b | MiniMax-M2 |
|---|---|---|
| LMArena Non-English | 1268 | 1314 |
| LMArena Chinese | 1268 | 1367 |
| LMArena Russian | 1249 | 1332 |
| LMArena French | — | 1336 |
| LMArena German | — | 1366 |
| LMArena Spanish | — | 1326 |
Instruction Following MiniMax-M2 leads
Granite 4.2 3b: 67.2 (#195), MiniMax-M2: 70.4 (#160)
| Benchmark | Granite 4.2 3b | MiniMax-M2 |
|---|---|---|
| LMArena Instruction Following | 1271 | 1329 |
Long Context MiniMax-M2 leads
Granite 4.2 3b: 39.3 (#179), MiniMax-M2: 40.5 (#148)
| Benchmark | Granite 4.2 3b | MiniMax-M2 |
|---|---|---|
| LMArena Longer Query | 1293 | 1332 |
Writing & Preference MiniMax-M2 leads
Granite 4.2 3b: 47.9 (#202), MiniMax-M2: 53.3 (#157)
| Benchmark | Granite 4.2 3b | MiniMax-M2 |
|---|---|---|
| LMArena Text | 1295 | 1340 |
| LMArena Creative Writing | 1215 | 1288 |
| LMArena Multi-Turn | 1293 | 1362 |
Frequently asked questions
Is Granite 4.2 3b better than MiniMax-M2?
Granite 4.2 3b is the stronger model overall, scoring 39.0 to 36.9 on the Noometry Index.
Is Granite 4.2 3b or MiniMax-M2 better for coding?
They score almost the same on coding (39.4 vs 39.1); test both on your own repository before choosing.
How many benchmarks do Granite 4.2 3b and MiniMax-M2 share?
11 benchmarks have published results for both models. Granite 4.2 3b has 11 scored results on Noometry and MiniMax-M2 has 21.