Model comparison
MiniMax-M2 vs Tulu 3 (Tülu 3) 70B
MiniMax-M2 is the stronger model overall, scoring 36.9 to 32.6 on the Noometry Index.
Last verified . 11 shared benchmarks.
MiniMax
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. MiniMax-M2 scores higher in 7 categories and Tulu 3 (Tülu 3) 70B in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where MiniMax-M2 leads 34.6 to 13.3.
Side by side
| MiniMax-M2 | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | MiniMax | Allen Institute for AI (Ai2) |
| Noometry Index | 36.9 | 32.6 |
| Released | 2025-10-27 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 21 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2 leads
MiniMax-M2: 39.1 (#151), Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | MiniMax-M2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1370 | 1236 |
| SWE-bench Verified (bash only) | 61% | — |
| LMArena WebDev | 1297 | — |
Agentic & Tool Use Not comparable
MiniMax-M2: 24.9 (#102), Tulu 3 (Tülu 3) 70B: —
| Benchmark | MiniMax-M2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Terminal-Bench | 30% | — |
| Vending-Bench 2 | 160.6 | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
MiniMax-M2: 18.6 (#256), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | MiniMax-M2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1357 | 1220 |
| Kagi LLM Benchmark | 57.8% | — |
| NYT Connections (extended) | 14.8% | — |
Math MiniMax-M2 leads
MiniMax-M2: 34.6 (#158), Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | MiniMax-M2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1350 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
Knowledge MiniMax-M2 leads
MiniMax-M2: 36.3 (#160), Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | MiniMax-M2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| LMArena Expert | 1336 | — |
Multilingual MiniMax-M2 leads
MiniMax-M2: 45.6 (#165), Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | MiniMax-M2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1314 | 1236 |
| LMArena Chinese | 1367 | 1249 |
| LMArena Russian | 1332 | 1246 |
| LMArena French | 1336 | — |
| LMArena German | 1366 | — |
| LMArena Spanish | 1326 | — |
Instruction Following MiniMax-M2 leads
MiniMax-M2: 70.4 (#160), Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | MiniMax-M2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1329 | 1233 |
Long Context MiniMax-M2 leads
MiniMax-M2: 40.5 (#148), Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | MiniMax-M2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1332 | 1224 |
Writing & Preference MiniMax-M2 leads
MiniMax-M2: 53.3 (#157), Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | MiniMax-M2 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1340 | 1256 |
| LMArena Creative Writing | 1288 | 1231 |
| LMArena Multi-Turn | 1362 | 1252 |
Frequently asked questions
Is MiniMax-M2 better than Tulu 3 (Tülu 3) 70B?
MiniMax-M2 is the stronger model overall, scoring 36.9 to 32.6 on the Noometry Index.
Is MiniMax-M2 or Tulu 3 (Tülu 3) 70B better for coding?
MiniMax-M2 scores higher on coding benchmarks: 39.1 versus 35.4 in the Noometry coding category.
How many benchmarks do MiniMax-M2 and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. MiniMax-M2 has 21 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.