Model comparison
Ministral 8B vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 28.2 on the Noometry Index.
Last verified . 13 shared benchmarks.
Mistral AI
Allen Institute for AI (Ai2)Summary
- They share 13 benchmarks with published results for both. Ministral 8B scores higher in 1 category and Tulu 3 (Tülu 3) 70B in 7 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Tulu 3 (Tülu 3) 70B leads 25.0 to 12.6.
- The biggest single-benchmark swing is MATH Level 5: 14.9% for Ministral 8B and 42.7% for Tulu 3 (Tülu 3) 70B.
Side by side
| Ministral 8B | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Mistral AI | Allen Institute for AI (Ai2) |
| Noometry Index | 28.2 | 33.0 |
| Released | 2024-10-01 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 262K | — |
| Max output | 262K | — |
| Input $ / M tokens | $0.15 | — |
| Output $ / M tokens | $0.15 | — |
| Results tracked | 17 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Ministral 8B: 35.0 (#230), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Ministral 8B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1202 | 1235 |
Agentic & Tool Use Not comparable
Ministral 8B: 16.4 (#148), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Ministral 8B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 11.1% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Ministral 8B: 18.4 (#281), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Ministral 8B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1220 |
| DTBench | 45.7% | — |
Math Ministral 8B leads
Ministral 8B: 25.7 (#267), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Ministral 8B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1188 | 1242 |
| MATH Level 5 | 14.9% | 42.7% |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
Knowledge Tulu 3 (Tülu 3) 70B leads
Ministral 8B: 12.6 (#297), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Ministral 8B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 27.1% | 46.3% |
| Vectara Hallucination Rate | 7.4% | — |
| LMArena Expert | 1170 | — |
Multilingual Tulu 3 (Tülu 3) 70B leads
Ministral 8B: 35.1 (#247), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Ministral 8B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1165 | 1236 |
| LMArena Chinese | 1193 | 1249 |
| LMArena Russian | 1195 | 1246 |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Ministral 8B: 60.5 (#250), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Ministral 8B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1161 | 1233 |
Long Context Too close to call
Ministral 8B: 36.7 (#227), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Ministral 8B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1212 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Ministral 8B: 39.6 (#246), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Ministral 8B | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1191 | 1256 |
| LMArena Creative Writing | 1175 | 1231 |
| LMArena Multi-Turn | 1166 | 1252 |
Frequently asked questions
Is Ministral 8B better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 28.2 on the Noometry Index.
Is Ministral 8B or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 35.0 in the Noometry coding category.
How many benchmarks do Ministral 8B and Tulu 3 (Tülu 3) 70B share?
13 benchmarks have published results for both models. Ministral 8B has 17 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.