Model comparison
Granite 3.1 8b Instruct vs MiMo-V2-Pro
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 32.4 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Granite 3.1 8b Instruct scores higher in 0 categories and MiMo-V2-Pro in 8 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Pro leads 62.8 to 35.5.
- Granite 3.1 8b Instruct has downloadable open weights; the other is API-only.
Side by side
| Granite 3.1 8b Instruct | MiMo-V2-Pro | |
|---|---|---|
| Provider | IBM | Xiaomi |
| Noometry Index | 32.4 | 43.0 |
| Released | — | 2026-03-18 |
| Weights | Open | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 131K |
| Input $ / M tokens | — | $0.43 |
| Output $ / M tokens | — | $0.87 |
| Results tracked | 13 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
Granite 3.1 8b Instruct: 34.5 (#233), MiMo-V2-Pro: 43.8 (#83)
| Benchmark | Granite 3.1 8b Instruct | MiMo-V2-Pro |
|---|---|---|
| LMArena Coding | 1186 | 1476 |
| LMArena WebDev | — | 1433 |
| ALE-Bench | — | 785.17 |
Agentic & Tool Use Not comparable
Granite 3.1 8b Instruct: 24.1 (#120), MiMo-V2-Pro: —
| Benchmark | Granite 3.1 8b Instruct | MiMo-V2-Pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 27.1% | — |
Reasoning Too close to call
Granite 3.1 8b Instruct: 22.1 (#207), MiMo-V2-Pro: 22.1 (#206)
| Benchmark | Granite 3.1 8b Instruct | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1145 | 1457 |
| NYT Connections (extended) | — | 25.8% |
| Thematic Generalization | — | 45.9% |
Math MiMo-V2-Pro leads
Granite 3.1 8b Instruct: 33.0 (#209), MiMo-V2-Pro: 39.5 (#102)
| Benchmark | Granite 3.1 8b Instruct | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1152 | 1447 |
Knowledge MiMo-V2-Pro leads
Granite 3.1 8b Instruct: 31.1 (#220), MiMo-V2-Pro: 41.4 (#111)
| Benchmark | Granite 3.1 8b Instruct | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | 1142 | 1478 |
Multilingual MiMo-V2-Pro leads
Granite 3.1 8b Instruct: 30.9 (#260), MiMo-V2-Pro: 52.7 (#81)
| Benchmark | Granite 3.1 8b Instruct | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1099 | 1416 |
| LMArena Chinese | 1145 | 1456 |
| LMArena Russian | 1092 | 1427 |
| LMArena French | — | 1469 |
| LMArena German | — | 1417 |
| LMArena Japanese | — | 1366 |
| LMArena Korean | — | 1400 |
| LMArena Spanish | — | 1457 |
Instruction Following MiMo-V2-Pro leads
Granite 3.1 8b Instruct: 58.6 (#259), MiMo-V2-Pro: 76.0 (#49)
| Benchmark | Granite 3.1 8b Instruct | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1131 | 1445 |
Long Context MiMo-V2-Pro leads
Granite 3.1 8b Instruct: 35.2 (#241), MiMo-V2-Pro: 41.5 (#138)
| Benchmark | Granite 3.1 8b Instruct | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1162 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference MiMo-V2-Pro leads
Granite 3.1 8b Instruct: 35.5 (#266), MiMo-V2-Pro: 62.8 (#70)
| Benchmark | Granite 3.1 8b Instruct | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1150 | 1436 |
| LMArena Creative Writing | 1129 | 1415 |
| LMArena Multi-Turn | 1108 | 1456 |
Frequently asked questions
Is Granite 3.1 8b Instruct better than MiMo-V2-Pro?
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 32.4 on the Noometry Index.
Is Granite 3.1 8b Instruct or MiMo-V2-Pro better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 34.5 in the Noometry coding category.
How many benchmarks do Granite 3.1 8b Instruct and MiMo-V2-Pro share?
12 benchmarks have published results for both models. Granite 3.1 8b Instruct has 13 scored results on Noometry and MiMo-V2-Pro has 23.