Model comparison
Granite 4.0 Micro vs MiniMax-M3
MiniMax-M3 is the stronger model overall, scoring 43.8 to 29.0 on the Noometry Index. Granite 4.0 Micro costs 13× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Last verified . 3 shared benchmarks.
MiniMaxSummary
- They share 3 benchmarks with published results for both. Granite 4.0 Micro scores higher in 0 categories and MiniMax-M3 in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M3 leads 58.4 to 9.9.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 2.8% for Granite 4.0 Micro and 71.1% for MiniMax-M3.
- Granite 4.0 Micro is cheaper at $0.017 / $0.11 per million input/output tokens, against $0.30 / $1.20 for MiniMax-M3.
- MiniMax-M3 accepts more context: 1M tokens versus 131K.
Side by side
| Granite 4.0 Micro | MiniMax-M3 | |
|---|---|---|
| Provider | IBM | MiniMax |
| Noometry Index | 29.0 | 43.8 |
| Released | 2025-10-02 | 2026-06-01 |
| Weights | Open | Open |
| Context window | 131K | 1M |
| Max output | 118K | 512K |
| Input $ / M tokens | $0.017 | $0.30 |
| Output $ / M tokens | $0.11 | $1.20 |
| Results tracked | 8 | 41 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Granite 4.0 Micro: —, MiniMax-M3: 41.8 (#118)
| Benchmark | Granite 4.0 Micro | MiniMax-M3 |
|---|---|---|
| FrontierCode | — | 14.7% |
| LMArena WebDev | — | 1482 |
| SciCode | — | 47.1% |
| LMArena Coding | — | 1469 |
| ALE-Bench | — | 640.02 |
Agentic & Tool Use Not comparable
Granite 4.0 Micro: —, MiniMax-M3: 22.6 (#130)
| Benchmark | Granite 4.0 Micro | MiniMax-M3 |
|---|---|---|
| APEX-Agents | — | 37.7% |
| OSWorld 2.0 | — | 4.6% |
| GBAEval | — | 0.9% |
| Vending-Bench 2 | — | 2,158 |
Reasoning MiniMax-M3 leads
Granite 4.0 Micro: 19.2 (#265), MiniMax-M3: 30.1 (#87)
| Benchmark | Granite 4.0 Micro | MiniMax-M3 |
|---|---|---|
| Chess Puzzles | 0% | 14% |
| SimpleBench | — | 45.8% |
| NYT Connections (extended) | — | 65.1% |
| CritPt | — | 3.7% |
| LMArena Hard Prompts | — | 1447 |
| Mystery Game Puzzles | — | 8% |
| DTBench | — | 78.9% |
| LMCA | — | 33.7% |
| Surface Evolver Bench | — | 55% |
| Epoch Capabilities Index | — | 146.95 |
| ForecastBench | — | 61.4 |
Math MiniMax-M3 leads
Granite 4.0 Micro: 12.0 (#307), MiniMax-M3: 40.0 (#95)
| Benchmark | Granite 4.0 Micro | MiniMax-M3 |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 2.8% | 71.1% |
| ProofBench | — | 18% |
| Omni-MATH | 20.9% | — |
| LMArena Math | — | 1429 |
Knowledge MiniMax-M3 leads
Granite 4.0 Micro: 9.9 (#304), MiniMax-M3: 58.4 (#35)
| Benchmark | Granite 4.0 Micro | MiniMax-M3 |
|---|---|---|
| GPQA Diamond | 28.3% | 90.9% |
| MMLU-Pro | 39.5% | — |
| GPQA (HELM) | 30.7% | — |
| LMArena Expert | — | 1461 |
Multimodal Not comparable
Granite 4.0 Micro: —, MiniMax-M3: 40.2 (#51)
| Benchmark | Granite 4.0 Micro | MiniMax-M3 |
|---|---|---|
| LMArena Vision | — | 1253 |
| LMArena Document | — | 1435 |
Multilingual Not comparable
Granite 4.0 Micro: —, MiniMax-M3: 53.0 (#75)
| Benchmark | Granite 4.0 Micro | MiniMax-M3 |
|---|---|---|
| LMArena Non-English | — | 1420 |
| LMArena Chinese | — | 1463 |
| LMArena French | — | 1447 |
| LMArena German | — | 1426 |
| LMArena Japanese | — | 1381 |
| LMArena Korean | — | 1372 |
| LMArena Russian | — | 1428 |
| LMArena Spanish | — | 1432 |
Instruction Following MiniMax-M3 leads
Granite 4.0 Micro: 69.9 (#169), MiniMax-M3: 75.5 (#62)
| Benchmark | Granite 4.0 Micro | MiniMax-M3 |
|---|---|---|
| IFEval | 84.9% | — |
| LMArena Instruction Following | — | 1433 |
Long Context Not comparable
Granite 4.0 Micro: —, MiniMax-M3: 44.2 (#72)
| Benchmark | Granite 4.0 Micro | MiniMax-M3 |
|---|---|---|
| LMArena Longer Query | — | 1445 |
Writing & Preference MiniMax-M3 leads
Granite 4.0 Micro: 46.7 (#216), MiniMax-M3: 62.1 (#83)
| Benchmark | Granite 4.0 Micro | MiniMax-M3 |
|---|---|---|
| LMArena Text | — | 1433 |
| LMArena Creative Writing | — | 1404 |
| WildBench | 67% | — |
| EQ-Bench 4 | — | 1150 |
| LMArena Multi-Turn | — | 1442 |
Frequently asked questions
Is Granite 4.0 Micro better than MiniMax-M3?
MiniMax-M3 is the stronger model overall, scoring 43.8 to 29.0 on the Noometry Index. Granite 4.0 Micro costs 13× less per token, which makes it the better buy when MiniMax-M3's lead doesn't matter for your workload.
Which is cheaper, Granite 4.0 Micro or MiniMax-M3?
Granite 4.0 Micro is cheaper. It lists at $0.017 per million input tokens and $0.11 per million output tokens; MiniMax-M3 lists at $0.30 and $1.20.
Which has the bigger context window?
MiniMax-M3 does, with 1M tokens against 131K.
How many benchmarks do Granite 4.0 Micro and MiniMax-M3 share?
3 benchmarks have published results for both models. Granite 4.0 Micro has 8 scored results on Noometry and MiniMax-M3 has 41.