Model comparison
Llama 3.1 Tulu 3 8b vs MiMo-V2-Pro
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 35.7 on the Noometry Index.
Last verified . 11 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Llama 3.1 Tulu 3 8b scores higher in 1 category and MiMo-V2-Pro in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where MiMo-V2-Pro leads 62.8 to 39.7.
- Llama 3.1 Tulu 3 8b has downloadable open weights; the other is API-only.
Side by side
| Llama 3.1 Tulu 3 8b | MiMo-V2-Pro | |
|---|---|---|
| Provider | Allen Institute for AI (Ai2) | Xiaomi |
| Noometry Index | 35.7 | 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 | 11 | 23 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiMo-V2-Pro leads
Llama 3.1 Tulu 3 8b: 34.4 (#235), MiMo-V2-Pro: 43.8 (#83)
| Benchmark | Llama 3.1 Tulu 3 8b | MiMo-V2-Pro |
|---|---|---|
| LMArena Coding | 1183 | 1476 |
| LMArena WebDev | — | 1433 |
| ALE-Bench | — | 785.17 |
Reasoning Too close to call
Llama 3.1 Tulu 3 8b: 22.8 (#188), MiMo-V2-Pro: 22.1 (#206)
| Benchmark | Llama 3.1 Tulu 3 8b | MiMo-V2-Pro |
|---|---|---|
| LMArena Hard Prompts | 1174 | 1457 |
| NYT Connections (extended) | — | 25.8% |
| Thematic Generalization | — | 45.9% |
Math MiMo-V2-Pro leads
Llama 3.1 Tulu 3 8b: 33.9 (#198), MiMo-V2-Pro: 39.5 (#102)
| Benchmark | Llama 3.1 Tulu 3 8b | MiMo-V2-Pro |
|---|---|---|
| LMArena Math | 1195 | 1447 |
Knowledge Not comparable
Llama 3.1 Tulu 3 8b: —, MiMo-V2-Pro: 41.4 (#111)
| Benchmark | Llama 3.1 Tulu 3 8b | MiMo-V2-Pro |
|---|---|---|
| LMArena Expert | — | 1478 |
Multilingual MiMo-V2-Pro leads
Llama 3.1 Tulu 3 8b: 35.4 (#246), MiMo-V2-Pro: 52.7 (#81)
| Benchmark | Llama 3.1 Tulu 3 8b | MiMo-V2-Pro |
|---|---|---|
| LMArena Non-English | 1169 | 1416 |
| LMArena Chinese | 1176 | 1456 |
| LMArena Russian | 1193 | 1427 |
| LMArena French | — | 1469 |
| LMArena German | — | 1417 |
| LMArena Japanese | — | 1366 |
| LMArena Korean | — | 1400 |
| LMArena Spanish | — | 1457 |
Instruction Following MiMo-V2-Pro leads
Llama 3.1 Tulu 3 8b: 61.3 (#246), MiMo-V2-Pro: 76.0 (#49)
| Benchmark | Llama 3.1 Tulu 3 8b | MiMo-V2-Pro |
|---|---|---|
| LMArena Instruction Following | 1174 | 1445 |
Long Context MiMo-V2-Pro leads
Llama 3.1 Tulu 3 8b: 35.8 (#239), MiMo-V2-Pro: 41.5 (#138)
| Benchmark | Llama 3.1 Tulu 3 8b | MiMo-V2-Pro |
|---|---|---|
| LMArena Longer Query | 1181 | 1455 |
| CL-bench | — | 15.7% |
| CL-bench Life | — | 6.9% |
Writing & Preference MiMo-V2-Pro leads
Llama 3.1 Tulu 3 8b: 39.7 (#245), MiMo-V2-Pro: 62.8 (#70)
| Benchmark | Llama 3.1 Tulu 3 8b | MiMo-V2-Pro |
|---|---|---|
| LMArena Text | 1193 | 1436 |
| LMArena Creative Writing | 1182 | 1415 |
| LMArena Multi-Turn | 1154 | 1456 |
Frequently asked questions
Is Llama 3.1 Tulu 3 8b better than MiMo-V2-Pro?
MiMo-V2-Pro is the stronger model overall, scoring 43.0 to 35.7 on the Noometry Index.
Is Llama 3.1 Tulu 3 8b or MiMo-V2-Pro better for coding?
MiMo-V2-Pro scores higher on coding benchmarks: 43.8 versus 34.4 in the Noometry coding category.
How many benchmarks do Llama 3.1 Tulu 3 8b and MiMo-V2-Pro share?
11 benchmarks have published results for both models. Llama 3.1 Tulu 3 8b has 11 scored results on Noometry and MiMo-V2-Pro has 23.