Model comparison
Grok-3 mini vs Tulu 3 (Tülu 3) 70B
Grok-3 mini is the stronger model overall, scoring 41.0 to 32.6 on the Noometry Index.
Last verified . 14 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 14 benchmarks with published results for both. Grok-3 mini 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 math, where Grok-3 mini leads 40.3 to 13.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 77.8% for Grok-3 mini and 4.4% for Tulu 3 (Tülu 3) 70B.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | xAI | Allen Institute for AI (Ai2) |
| Noometry Index | 41.0 | 32.6 |
| Released | 2025-04-09 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Grok-3 mini: 40.4 (#126), Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | Grok-3 mini | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1380 | 1236 |
| Aider Polyglot | 49.3% | — |
| WeirdML | 42.6% | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Grok-3 mini: 13.8 (#323), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | Grok-3 mini | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1374 | 1220 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| Epoch Capabilities Index | 140.35 | — |
Math Grok-3 mini leads
Grok-3 mini: 40.3 (#78), Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | Grok-3 mini | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 77.8% | 4.4% |
| LMArena Math | 1386 | 1242 |
| MATH Level 5 | 90.9% | 42.7% |
| Omni-MATH | 31.8% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Grok-3 mini leads
Grok-3 mini: 46.3 (#75), Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | Grok-3 mini | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 76.3% | 46.3% |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
| LMArena Expert | 1395 | — |
Multilingual Grok-3 mini leads
Grok-3 mini: 48.3 (#141), Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | Grok-3 mini | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1352 | 1236 |
| LMArena Chinese | 1387 | 1249 |
| LMArena Russian | 1352 | 1246 |
| LMArena French | 1357 | — |
| LMArena German | 1350 | — |
| LMArena Japanese | 1343 | — |
| LMArena Korean | 1336 | — |
| LMArena Spanish | 1379 | — |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.7 (#8), Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | Grok-3 mini | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1356 | 1233 |
| IFEval | 95.1% | — |
Long Context Grok-3 mini leads
Grok-3 mini: 41.0 (#142), Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | Grok-3 mini | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1372 | 1224 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Grok-3 mini leads
Grok-3 mini: 52.7 (#163), Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | Grok-3 mini | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1370 | 1256 |
| LMArena Creative Writing | 1342 | 1231 |
| LMArena Multi-Turn | 1355 | 1252 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than Tulu 3 (Tülu 3) 70B?
Grok-3 mini is the stronger model overall, scoring 41.0 to 32.6 on the Noometry Index.
Is Grok-3 mini or Tulu 3 (Tülu 3) 70B better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.4 versus 35.4 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Tulu 3 (Tülu 3) 70B share?
14 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.