Model comparison
Grok 4.20 (Non-Reasoning) vs Tulu 3 (Tülu 3) 70B
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 32.6 on the Noometry Index.
Last verified . 13 shared benchmarks.
Allen Institute for AI (Ai2)Summary
- They share 13 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 8 categories and Tulu 3 (Tülu 3) 70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.20 (Non-Reasoning) leads 48.0 to 13.3.
- The biggest single-benchmark swing is OTIS Mock AIME 2024-2025: 92.2% for Grok 4.20 (Non-Reasoning) 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 4.20 (Non-Reasoning) | Tulu 3 (Tülu 3) 70B | |
|---|---|---|
| Provider | xAI | Allen Institute for AI (Ai2) |
| Noometry Index | 48.5 | 32.6 |
| Released | 2026-02-17 | 2024-11-21 |
| Weights | Proprietary | Open |
| Context window | 1M | — |
| Max output | 30K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 46 | 14 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 41.8 (#104), Tulu 3 (Tülu 3) 70B: 35.4 (#211)
| Benchmark | Grok 4.20 (Non-Reasoning) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Coding | 1458 | 1236 |
| LMArena WebDev | 1374 | — |
| WeirdML | 52.3% | — |
| ALE-Bench | 1,150 | — |
Agentic & Tool Use Not comparable
Grok 4.20 (Non-Reasoning): 34.3 (#43), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| Terminal-Bench | 57.3% | — |
| τ²-bench Banking | 18% | — |
| LMArena Search | 1189 | — |
| Vending-Bench 2 | 4,663 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.2 (#30), Tulu 3 (Tülu 3) 70B: 22.9 (#172)
| Benchmark | Grok 4.20 (Non-Reasoning) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1220 |
| ARC-AGI-2 | 65.1% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 85.4% | — |
| ARC-AGI-1 | 89.5% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 63.8% | — |
| DTBench | 90.1% | — |
| LMCA | 38.7% | — |
| Epoch Capabilities Index | 152.01 | — |
| ForecastBench | 61.4 | — |
Math Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 48.0 (#54), Tulu 3 (Tülu 3) 70B: 13.3 (#297)
| Benchmark | Grok 4.20 (Non-Reasoning) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 92.2% | 4.4% |
| LMArena Math | 1455 | 1242 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 14% | — |
| MATH Level 5 | — | 42.7% |
Knowledge Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.8 (#54), Tulu 3 (Tülu 3) 70B: 25.1 (#257)
| Benchmark | Grok 4.20 (Non-Reasoning) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| GPQA Diamond | 89.3% | 46.3% |
| SimpleQA Verified | 30.2% | — |
| LMArena Expert | 1440 | — |
Multimodal Not comparable
Grok 4.20 (Non-Reasoning): 33.2 (#88), Tulu 3 (Tülu 3) 70B: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
Multilingual Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 54.7 (#38), Tulu 3 (Tülu 3) 70B: 40.1 (#217)
| Benchmark | Grok 4.20 (Non-Reasoning) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Non-English | 1440 | 1236 |
| LMArena Chinese | 1481 | 1249 |
| LMArena Russian | 1457 | 1246 |
| LMArena French | 1477 | — |
| LMArena German | 1463 | — |
| LMArena Japanese | 1450 | — |
| LMArena Korean | 1417 | — |
| LMArena Spanish | 1442 | — |
Instruction Following Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 75.0 (#79), Tulu 3 (Tülu 3) 70B: 65.0 (#222)
| Benchmark | Grok 4.20 (Non-Reasoning) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Instruction Following | 1420 | 1233 |
Long Context Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 45.4 (#33), Tulu 3 (Tülu 3) 70B: 37.1 (#217)
| Benchmark | Grok 4.20 (Non-Reasoning) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Longer Query | 1436 | 1224 |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 65.9 (#42), Tulu 3 (Tülu 3) 70B: 45.8 (#218)
| Benchmark | Grok 4.20 (Non-Reasoning) | Tulu 3 (Tülu 3) 70B |
|---|---|---|
| LMArena Text | 1451 | 1256 |
| LMArena Creative Writing | 1439 | 1231 |
| LMArena Multi-Turn | 1456 | 1252 |
| EQ-Bench Creative Writing | 1574 | — |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Tulu 3 (Tülu 3) 70B?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 32.6 on the Noometry Index.
Is Grok 4.20 (Non-Reasoning) or Tulu 3 (Tülu 3) 70B better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 41.8 versus 35.4 in the Noometry coding category.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Tulu 3 (Tülu 3) 70B share?
13 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Tulu 3 (Tülu 3) 70B has 14.