Model comparison
MiniMax-M2.7 vs Tulu 3 (Tülu 3) 70B
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 33.0 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-M2.7 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 writing & preference, where MiniMax-M2.7 leads 58.9 to 45.6.
Side by side
| MiniMax-M2.7 | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | MiniMax | Allen Institute for AI (Ai2) |
| Noometry Index | 37.7 | 33.0 |
| Released | 2026-03-18 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 30 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.7 leads
MiniMax-M2.7: 41.8 (#120), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | MiniMax-M2.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1454 | 1235 |
| LMArena WebDev | 1398 | — |
| SciCode | 47% | — |
| WeirdML | 37% | — |
| ALE-Bench | 599.25 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.7: 25.1 (#111), Tulu 3 (Tülu 3) 70B: —
| Benchmark | MiniMax-M2.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Terminal-Bench | 45.1% | — |
| ExploitBench | 13.3% | — |
| GBAEval | 0% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
MiniMax-M2.7: 19.7 (#253), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | MiniMax-M2.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1422 | 1220 |
| NYT Connections (extended) | 24.7% | — |
| CritPt | 0.6% | — |
| Thematic Generalization | 39.3% | — |
| Epoch Capabilities Index | 145.85 | — |
Math MiniMax-M2.7 leads
MiniMax-M2.7: 25.9 (#263), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | MiniMax-M2.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1420 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| ProofBench | 3% | — |
| MATH Level 5 | — | 42.7% |
Knowledge MiniMax-M2.7 leads
MiniMax-M2.7: 37.7 (#152), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | MiniMax-M2.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| Vectara Hallucination Rate | 12.9% | — |
| LMArena Expert | 1444 | — |
Multilingual MiniMax-M2.7 leads
MiniMax-M2.7: 50.3 (#123), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | MiniMax-M2.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1382 | 1236 |
| LMArena Chinese | 1441 | 1249 |
| LMArena Russian | 1383 | 1246 |
| LMArena French | 1421 | — |
| LMArena German | 1398 | — |
| LMArena Japanese | 1262 | — |
| LMArena Korean | 1313 | — |
| LMArena Spanish | 1403 | — |
Instruction Following MiniMax-M2.7 leads
MiniMax-M2.7: 74.1 (#103), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | MiniMax-M2.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1405 | 1233 |
Long Context MiniMax-M2.7 leads
MiniMax-M2.7: 43.3 (#99), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | MiniMax-M2.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1419 | 1224 |
Writing & Preference MiniMax-M2.7 leads
MiniMax-M2.7: 58.9 (#112), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | MiniMax-M2.7 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1405 | 1256 |
| LMArena Creative Writing | 1354 | 1231 |
| LMArena Multi-Turn | 1412 | 1252 |
Frequently asked questions
Is MiniMax-M2.7 better than Tulu 3 (Tülu 3) 70B?
MiniMax-M2.7 is the stronger model overall, scoring 37.7 to 33.0 on the Noometry Index.
Is MiniMax-M2.7 or Tulu 3 (Tülu 3) 70B better for coding?
MiniMax-M2.7 scores higher on coding benchmarks: 41.8 versus 36.0 in the Noometry coding category.
How many benchmarks do MiniMax-M2.7 and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. MiniMax-M2.7 has 30 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.