Model comparison
Granite 4.0 H Small vs MiniMax-M2.5
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 36.5 on the Noometry Index.
Last verified . 14 shared benchmarks.
MiniMaxSummary
- They share 14 benchmarks with published results for both. Granite 4.0 H Small scores higher in 3 categories and MiniMax-M2.5 in 5 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where MiniMax-M2.5 leads 48.1 to 36.4.
Side by side
| Granite 4.0 H Small | MiniMax-M2.5 | |
|---|---|---|
| Provider | IBM | MiniMax |
| Noometry Index | 36.5 | 38.3 |
| Released | — | 2026-02-12 |
| Weights | Open | Open |
| Context window | — | 205K |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.30 |
| Output $ / M tokens | — | $1.20 |
| Results tracked | 19 | 33 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
Granite 4.0 H Small: 36.4 (#209), MiniMax-M2.5: 48.1 (#58)
| Benchmark | Granite 4.0 H Small | MiniMax-M2.5 |
|---|---|---|
| LMArena Coding | 1249 | 1381 |
| SWE-bench Verified (bash only) | — | 75.8% |
| LMArena WebDev | — | 1387 |
| SWE-bench Multilingual | — | 68.3% |
| ALE-Bench | — | 618.17 |
Agentic & Tool Use Not comparable
Granite 4.0 H Small: —, MiniMax-M2.5: 30.4 (#77)
| Benchmark | Granite 4.0 H Small | MiniMax-M2.5 |
|---|---|---|
| Terminal-Bench | — | 42.7% |
| Vending-Bench 2 | — | -23.16 |
Reasoning Granite 4.0 H Small leads
Granite 4.0 H Small: 24.4 (#163), MiniMax-M2.5: 17.5 (#292)
| Benchmark | Granite 4.0 H Small | MiniMax-M2.5 |
|---|---|---|
| LMArena Hard Prompts | 1240 | 1372 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 55.2% |
| NYT Connections (extended) | — | 16.8% |
| ARC-AGI-1 | — | 63.7% |
| Epoch Capabilities Index | — | 146.68 |
Math Granite 4.0 H Small leads
Granite 4.0 H Small: 31.4 (#223), MiniMax-M2.5: 26.9 (#253)
| Benchmark | Granite 4.0 H Small | MiniMax-M2.5 |
|---|---|---|
| LMArena Math | 1247 | 1378 |
| ProofBench | — | 4% |
| Omni-MATH | 29.6% | — |
Knowledge MiniMax-M2.5 leads
Granite 4.0 H Small: 32.0 (#215), MiniMax-M2.5: 39.2 (#135)
| Benchmark | Granite 4.0 H Small | MiniMax-M2.5 |
|---|---|---|
| Vectara Hallucination Rate | 5.2% | 9.1% |
| LMArena Expert | 1251 | 1379 |
| MMLU-Pro | 56.9% | — |
| GPQA (HELM) | 38.3% | — |
Multilingual MiniMax-M2.5 leads
Granite 4.0 H Small: 38.6 (#228), MiniMax-M2.5: 47.1 (#152)
| Benchmark | Granite 4.0 H Small | MiniMax-M2.5 |
|---|---|---|
| LMArena Non-English | 1216 | 1338 |
| LMArena Chinese | 1249 | 1393 |
| LMArena Russian | 1201 | 1358 |
| LMArena Spanish | 1258 | 1354 |
| LMArena French | — | 1362 |
| LMArena German | — | 1362 |
| LMArena Japanese | — | 1171 |
| LMArena Korean | — | 1232 |
Instruction Following MiniMax-M2.5 leads
Granite 4.0 H Small: 68.7 (#183), MiniMax-M2.5: 71.5 (#148)
| Benchmark | Granite 4.0 H Small | MiniMax-M2.5 |
|---|---|---|
| LMArena Instruction Following | 1222 | 1353 |
| IFEval | 89% | — |
Long Context Too close to call
Granite 4.0 H Small: 37.7 (#213), MiniMax-M2.5: 37.5 (#216)
| Benchmark | Granite 4.0 H Small | MiniMax-M2.5 |
|---|---|---|
| LMArena Longer Query | 1242 | 1366 |
| CL-bench | — | 11.4% |
| CL-bench Life | — | 6.3% |
Writing & Preference MiniMax-M2.5 leads
Granite 4.0 H Small: 43.8 (#227), MiniMax-M2.5: 53.9 (#153)
| Benchmark | Granite 4.0 H Small | MiniMax-M2.5 |
|---|---|---|
| LMArena Text | 1241 | 1359 |
| LMArena Creative Writing | 1211 | 1331 |
| LMArena Multi-Turn | 1242 | 1364 |
| EQ-Bench Creative Writing | — | 1361 |
| WildBench | 73.9% | — |
Frequently asked questions
Is Granite 4.0 H Small better than MiniMax-M2.5?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 36.5 on the Noometry Index.
Is Granite 4.0 H Small or MiniMax-M2.5 better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 36.4 in the Noometry coding category.
How many benchmarks do Granite 4.0 H Small and MiniMax-M2.5 share?
14 benchmarks have published results for both models. Granite 4.0 H Small has 19 scored results on Noometry and MiniMax-M2.5 has 33.