Model comparison
Grok 4 Fast vs Tulu 3 (Tülu 3) 70B
Grok 4 Fast is the stronger model overall, scoring 39.4 to 33.0 on the Noometry Index.
Last verified . 11 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 11 benchmarks with published results for both. Grok 4 Fast scores higher in 6 categories and Tulu 3 (Tülu 3) 70B in 2 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in long context, where Grok 4 Fast leads 63.2 to 37.1.
- Tulu 3 (Tülu 3) 70B has downloadable open weights; the other is API-only.
Side by side
| Grok 4 Fast | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | xAI | Allen Institute for AI (Ai2) |
| Noometry Index | 39.4 | 33.0 |
| Released | 2025-09-19 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 30 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Tulu 3 (Tülu 3) 70B leads
Grok 4 Fast: 32.5 (#271), Tulu 3 (Tülu 3) 70B: 36.0 (#214)
| Benchmark | Grok 4 Fast | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1429 | 1235 |
| LMArena WebDev | 1159 | — |
| WeirdML | 42.9% | — |
Agentic & Tool Use Not comparable
Grok 4 Fast: 29.5 (#86), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Grok 4 Fast | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| τ²-bench Banking | 15.7% | — |
| Cybench | 30% | — |
| LMArena Search | 1171 | — |
Reasoning Tulu 3 (Tülu 3) 70B leads
Grok 4 Fast: 22.2 (#201), Tulu 3 (Tülu 3) 70B: 23.9 (#169)
| Benchmark | Grok 4 Fast | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1412 | 1220 |
| ARC-AGI-2 | 5.3% | — |
| Kagi LLM Benchmark | 66.1% | — |
| ARC-AGI-1 | 48.5% | — |
| DTBench | 82.7% | — |
| Epoch Capabilities Index | 144.2 | — |
| ForecastBench | 60.5 | — |
Math Grok 4 Fast leads
Grok 4 Fast: 38.9 (#123), Tulu 3 (Tülu 3) 70B: 14.2 (#303)
| Benchmark | Grok 4 Fast | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Math | 1419 | 1242 |
| OTIS Mock AIME 2024-2025 | — | 4.4% |
| MATH Level 5 | — | 42.7% |
Knowledge Grok 4 Fast leads
Grok 4 Fast: 32.0 (#214), Tulu 3 (Tülu 3) 70B: 25.0 (#264)
| Benchmark | Grok 4 Fast | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | — | 46.3% |
| Vectara Hallucination Rate | 19.7% | — |
| LMArena Expert | 1411 | — |
Multilingual Grok 4 Fast leads
Grok 4 Fast: 51.3 (#111), Tulu 3 (Tülu 3) 70B: 39.9 (#222)
| Benchmark | Grok 4 Fast | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1396 | 1236 |
| LMArena Chinese | 1457 | 1249 |
| LMArena Russian | 1389 | 1246 |
| LMArena French | 1431 | — |
| LMArena German | 1383 | — |
| LMArena Japanese | 1352 | — |
| LMArena Korean | 1357 | — |
| LMArena Spanish | 1415 | — |
Instruction Following Grok 4 Fast leads
Grok 4 Fast: 73.2 (#121), Tulu 3 (Tülu 3) 70B: 64.8 (#227)
| Benchmark | Grok 4 Fast | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1387 | 1233 |
Long Context Grok 4 Fast leads
Grok 4 Fast: 63.2 (#3), Tulu 3 (Tülu 3) 70B: 37.1 (#222)
| Benchmark | Grok 4 Fast | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1415 | 1224 |
| Fiction.LiveBench | 94.4% | — |
Writing & Preference Grok 4 Fast leads
Grok 4 Fast: 60.0 (#102), Tulu 3 (Tülu 3) 70B: 45.6 (#223)
| Benchmark | Grok 4 Fast | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1407 | 1256 |
| LMArena Creative Writing | 1387 | 1231 |
| LMArena Multi-Turn | 1414 | 1252 |
Frequently asked questions
Is Grok 4 Fast better than Tulu 3 (Tülu 3) 70B?
Grok 4 Fast is the stronger model overall, scoring 39.4 to 33.0 on the Noometry Index.
Is Grok 4 Fast or Tulu 3 (Tülu 3) 70B better for coding?
Tulu 3 (Tülu 3) 70B scores higher on coding benchmarks: 36.0 versus 32.5 in the Noometry coding category.
How many benchmarks do Grok 4 Fast and Tulu 3 (Tülu 3) 70B share?
11 benchmarks have published results for both models. Grok 4 Fast has 30 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.