Model comparison
MiniMax-M2.5 vs Tulu 3 (Tülu 3) 70B
MiniMax-M2.5 is the stronger model overall, scoring 38.3 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-M2.5 scores higher in 7 categories and Tulu 3 (Tülu 3) 70B in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where MiniMax-M2.5 leads 39.2 to 25.0.
Side by side
| MiniMax-M2.5 | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | MiniMax | Allen Institute for AI (Ai2) |
| Noometry Index | 38.3 | 33.0 |
| Released | 2026-02-12 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 205K | — |
| Max output | 131K | — |
| Input $ / M tokens | $0.30 | — |
| Output $ / M tokens | $1.20 | — |
| Results tracked | 33 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding MiniMax-M2.5 leads
MiniMax-M2.5: 48.1 (#58), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | MiniMax-M2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1381 | 1235 |
| SWE-bench Verified (bash only) | 75.8% | — |
| LMArena WebDev | 1387 | — |
| SWE-bench Multilingual | 68.3% | — |
| ALE-Bench | 618.17 | — |
Agentic & Tool Use Not comparable
MiniMax-M2.5: 30.4 (#77), Tulu 3 (Tülu 3) 70B: —
| Benchmark | MiniMax-M2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Terminal-Bench | 42.7% | — |
| Vending-Bench 2 | -23.16 | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
MiniMax-M2.5: 17.5 (#292), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | MiniMax-M2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1372 | 1220 |
| 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 MiniMax-M2.5 leads
MiniMax-M2.5: 26.9 (#253), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | MiniMax-M2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1378 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| ProofBench | 4% | — |
| MATH Level 5 | — | 42.7% |
Knowledge MiniMax-M2.5 leads
MiniMax-M2.5: 39.2 (#135), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | MiniMax-M2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| Vectara Hallucination Rate | 9.1% | — |
| LMArena Expert | 1379 | — |
Multilingual MiniMax-M2.5 leads
MiniMax-M2.5: 47.1 (#152), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | MiniMax-M2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1338 | 1236 |
| LMArena Chinese | 1393 | 1249 |
| LMArena Russian | 1358 | 1246 |
| LMArena French | 1362 | — |
| LMArena German | 1362 | — |
| LMArena Japanese | 1171 | — |
| LMArena Korean | 1232 | — |
| LMArena Spanish | 1354 | — |
Instruction Following MiniMax-M2.5 leads
MiniMax-M2.5: 71.5 (#148), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | MiniMax-M2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1353 | 1233 |
Long Context Too close to call
MiniMax-M2.5: 37.5 (#216), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | MiniMax-M2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1366 | 1224 |
| CL-bench | 11.4% | — |
| CL-bench Life | 6.3% | — |
Writing & Preference MiniMax-M2.5 leads
MiniMax-M2.5: 53.9 (#153), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | MiniMax-M2.5 | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1359 | 1256 |
| LMArena Creative Writing | 1331 | 1231 |
| LMArena Multi-Turn | 1364 | 1252 |
| EQ-Bench Creative Writing | 1361 | — |
Frequently asked questions
Is MiniMax-M2.5 better than Tulu 3 (Tülu 3) 70B?
MiniMax-M2.5 is the stronger model overall, scoring 38.3 to 33.0 on the Noometry Index.
Is MiniMax-M2.5 or Tulu 3 (Tülu 3) 70B better for coding?
MiniMax-M2.5 scores higher on coding benchmarks: 48.1 versus 36.0 in the Noometry coding category.
How many benchmarks do MiniMax-M2.5 and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. MiniMax-M2.5 has 33 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.