Model comparison
Mistral Large vs Tulu 3 (Tülu 3) 70B
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 31.9 on the Noometry Index.
Last verified . 14 shared benchmarks.
Mistral AI
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. Mistral Large scores higher in 5 categories and Tulu 3 (Tülu 3) 70B in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Tulu 3 (Tülu 3) 70B leads 23.9 to 15.8.
- The biggest single-benchmark swing is MATH Level 5: 50.3% for Mistral Large and 42.7% for Tulu 3 (Tülu 3) 70B.
Side by side
| Mistral Large | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | Mistral AI | Allen Institute for AI (Ai2) |
| Noometry Index | 31.9 | 33.0 |
| Released | 2024-02-26 | 2024-11-21 |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 16K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 51 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Mistral Large: 34.3 (#240), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Mistral Large | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1277 | 1235 |
| SciCode | 36.2% | — |
| BigCodeBench Instruct | 30% | — |
| LiveBench Coding | 47.1% | — |
| BigCodeBench Complete | 38.3% | — |
| ALE-Bench | 264.7 | — |
| HumanEval+ | 62.2% | — |
| MBPP+ | 59.5% | — |
Agentic & Tool Use Not comparable
Mistral Large: 28.6 (#89), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Mistral Large | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 38.4% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Mistral Large: 15.8 (#310), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Mistral Large | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1257 | 1220 |
| SimpleBench | 22.5% | — |
| CritPt | 0% | — |
| LiveBench Reasoning | 43.5% | — |
| DTBench | 65.1% | — |
| LiveBench Data Analysis | 50.1% | — |
| LMCA | 16.7% | — |
| Epoch Capabilities Index | 128.52 | — |
| ForecastBench | 57.1 | — |
| LiveBench | 48.4% | — |
Math Mistral Large leads
Mistral Large: 18.2 (#291), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Mistral Large | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 8.5% | 4.4% |
| LMArena Math | 1262 | 1242 |
| MATH Level 5 | 50.3% | 42.7% |
| Omni-MATH | 28.1% | — |
| LiveBench Math | 42.5% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Mistral Large leads
Mistral Large: 30.1 (#230), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Mistral Large | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 51.3% | 46.3% |
| MMLU-Pro | 59.9% | — |
| Confabulations | 21.4% | — |
| Vectara Hallucination Rate | 4.5% | — |
| GPQA (HELM) | 43.5% | — |
| LMArena Expert | 1232 | — |
| MMLU | 80% | — |
Multilingual Too close to call
Mistral Large: 40.0 (#219), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Mistral Large | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1237 | 1236 |
| LMArena Chinese | 1240 | 1249 |
| LMArena Russian | 1257 | 1246 |
| LMArena French | 1325 | — |
| LMArena German | 1254 | — |
| LMArena Japanese | 1188 | — |
| LMArena Korean | 1202 | — |
| LMArena Spanish | 1268 | — |
Instruction Following Mistral Large leads
Mistral Large: 67.9 (#191), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Mistral Large | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1249 | 1233 |
| LiveBench Instruction Following | 67.9% | — |
| IFEval | 87.7% | — |
Long Context Mistral Large leads
Mistral Large: 38.3 (#199), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Mistral Large | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1261 | 1224 |
Writing & Preference Tulu 3 (Tülu 3) 70B leads
Mistral Large: 40.7 (#242), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Mistral Large | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1266 | 1256 |
| LMArena Creative Writing | 1243 | 1231 |
| LMArena Multi-Turn | 1260 | 1252 |
| Short-Story Creative Writing | 69% | — |
| EQ-Bench Creative Writing | 985 | — |
| WildBench | 80.1% | — |
| LiveBench Language | 39.4% | — |
Frequently asked questions
Is Mistral Large better than Tulu 3 (Tülu 3) 70B?
Tulu 3 (Tülu 3) 70B is the stronger model overall, scoring 33.0 to 31.9 on the Noometry Index.
Is Mistral Large or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 34.3 in the Noometry coding category.
How many benchmarks do Mistral Large and Tulu 3 (Tülu 3) 70B share?
14 benchmarks have published results for both models. Mistral Large has 51 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.