Model comparison
Grok 4.20 (Non-Reasoning) vs Grok 4 Fast
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 39.4 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 8 categories and Grok 4 Fast in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 22.2.
- The biggest single-benchmark swing is ARC-AGI-2: 65.1% for Grok 4.20 (Non-Reasoning) and 5.3% for Grok 4 Fast.
Side by side
| Grok 4.20 (Non-Reasoning) | Grok 4 Fast | |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 48.6 | 39.4 |
| Released | 2026-02-17 | 2025-09-19 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Max output | 30K | — |
| Input $ / M tokens | $1.25 | — |
| Output $ / M tokens | $2.50 | — |
| Results tracked | 46 | 30 |
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): 42.1 (#112), Grok 4 Fast: 32.5 (#271)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4 Fast |
|---|---|---|
| LMArena WebDev | 1375 | 1159 |
| WeirdML | 52.3% | 42.9% |
| LMArena Coding | 1459 | 1429 |
| ALE-Bench | 1,150 | — |
Agentic & Tool Use Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 34.4 (#46), Grok 4 Fast: 29.5 (#86)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4 Fast |
|---|---|---|
| τ²-bench Banking | 18% | 15.7% |
| LMArena Search | 1189 | 1171 |
| Terminal-Bench | 57.3% | — |
| Cybench | — | 30% |
| Vending-Bench 2 | 4,663 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.3 (#32), Grok 4 Fast: 22.2 (#201)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4 Fast |
|---|---|---|
| ARC-AGI-2 | 65.1% | 5.3% |
| Kagi LLM Benchmark | 75% | 66.1% |
| ARC-AGI-1 | 89.5% | 48.5% |
| LMArena Hard Prompts | 1451 | 1412 |
| DTBench | 90.1% | 82.7% |
| Epoch Capabilities Index | 151.98 | 144.2 |
| ForecastBench | 61.4 | 60.5 |
| NYT Connections (extended) | 85.4% | — |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 63.8% | — |
| LMCA | 38.7% | — |
Math Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 48.2 (#65), Grok 4 Fast: 38.9 (#123)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4 Fast |
|---|---|---|
| LMArena Math | 1455 | 1419 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
| ProofBench | 14% | — |
Knowledge Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.8 (#60), Grok 4 Fast: 32.0 (#214)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4 Fast |
|---|---|---|
| LMArena Expert | 1439 | 1411 |
| GPQA Diamond | 89.3% | — |
| SimpleQA Verified | 30.2% | — |
| Vectara Hallucination Rate | — | 19.7% |
Multimodal Not comparable
Grok 4.20 (Non-Reasoning): 33.3 (#98), Grok 4 Fast: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4 Fast |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
Multilingual Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 54.5 (#40), Grok 4 Fast: 51.3 (#111)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4 Fast |
|---|---|---|
| LMArena Non-English | 1441 | 1396 |
| LMArena Chinese | 1481 | 1457 |
| LMArena French | 1476 | 1431 |
| LMArena German | 1465 | 1383 |
| LMArena Japanese | 1449 | 1352 |
| LMArena Korean | 1417 | 1357 |
| LMArena Russian | 1458 | 1389 |
| LMArena Spanish | 1443 | 1415 |
Instruction Following Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 74.8 (#83), Grok 4 Fast: 73.2 (#121)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4 Fast |
|---|---|---|
| LMArena Instruction Following | 1420 | 1387 |
Long Context Grok 4 Fast leads
Grok 4.20 (Non-Reasoning): 45.5 (#34), Grok 4 Fast: 63.2 (#3)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4 Fast |
|---|---|---|
| LMArena Longer Query | 1437 | 1415 |
| Fiction.LiveBench | — | 94.4% |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 65.7 (#44), Grok 4 Fast: 60.0 (#102)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4 Fast |
|---|---|---|
| LMArena Text | 1451 | 1407 |
| LMArena Creative Writing | 1438 | 1387 |
| LMArena Multi-Turn | 1456 | 1414 |
| EQ-Bench Creative Writing | 1574 | — |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Grok 4 Fast?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 39.4 on the Noometry Index.
Is Grok 4.20 (Non-Reasoning) or Grok 4 Fast better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 versus 32.5 in the Noometry coding category.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Grok 4 Fast share?
27 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Grok 4 Fast has 30.