Model comparison
Mistral vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.9 on the Noometry Index.
Last verified . 11 shared benchmarks.
Mistral AI
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Mistral scores higher in 1 category and Tulu 3 (Tülu 3) 70B in 7 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Tulu 3 (Tülu 3) 70B leads 64.8 to 52.6.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| Mistral | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Mistral AI | Allen Institute for AI (Ai2) |
| Noometry Index | 29.9 | 33.0 |
| Released | — | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 22 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Mistral: 33.8 (#250), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Mistral | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1162 | 1235 |
Reasoning Tulu 3 (Tülu 3) 70B leads
Mistral: 22.2 (#200), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Mistral | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1149 | 1220 |
Math Mistral leads
Mistral: 22.3 (#278), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Mistral | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1180 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| Omni-MATH | 7.2% | — |
| MATH Level 5 | — | 42.7% |
Knowledge Tulu 3 (Tülu 3) 70B leads
Mistral: 16.6 (#288), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Mistral | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| MMLU-Pro | 27.7% | — |
| GPQA (HELM) | 30.3% | — |
| LMArena Expert | 1125 | — |
Multilingual Tulu 3 (Tülu 3) 70B leads
Mistral: 32.8 (#254), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Mistral | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1129 | 1236 |
| LMArena Chinese | 1109 | 1249 |
| LMArena Russian | 1168 | 1246 |
| LMArena French | 1180 | — |
| LMArena German | 1155 | — |
| LMArena Japanese | 1013 | — |
| LMArena Korean | 1032 | — |
| LMArena Spanish | 1143 | — |
Instruction Following Tulu 3 (Tülu 3) 70B leads
Mistral: 52.6 (#288), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Mistral | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1152 | 1233 |
| IFEval | 56.8% | — |
Long Context Tulu 3 (Tülu 3) 70B leads
Mistral: 35.0 (#245), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Mistral | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1153 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Mistral: 37.0 (#260), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Mistral | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1165 | 1256 |
| LMArena Creative Writing | 1158 | 1231 |
| LMArena Multi-Turn | 1147 | 1252 |
| WildBench | 66% | — |
Frequently asked questions
Is Mistral better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 29.9 on the Noometry Index.
Is Mistral or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 33.8 in the Noometry coding category.
How many benchmarks do Mistral and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. Mistral has 22 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.