Model comparison
Grok 4.20 (Non-Reasoning) vs Grok 4.7
Grok 4.7 is the stronger model overall, scoring 53.1 to 48.6 on the Noometry Index. Grok 4.20 (Non-Reasoning) costs 1.9× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Last verified . 30 shared benchmarks.
Summary
- They share 30 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 4 categories and Grok 4.7 in 6 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Grok 4.7 leads 58.0 to 42.1.
- The biggest single-benchmark swing is Blueprint-Bench 2: 0% for Grok 4.20 (Non-Reasoning) and 32.5% for Grok 4.7.
- Grok 4.20 (Non-Reasoning) is cheaper at $1.25 / $2.50 per million input/output tokens, against $2 / $6 for Grok 4.7.
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 500K.
Side by side
| Grok 4.20 (Non-Reasoning) | Grok 4.7 | |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 48.6 | 53.1 |
| Released | 2026-02-17 | 2026-09-21 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 500K |
| Max output | 30K | 500K |
| Input $ / M tokens | $1.25 | $2 |
| Output $ / M tokens | $2.50 | $6 |
| Results tracked | 46 | 39 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.7 leads
Grok 4.20 (Non-Reasoning): 42.1 (#112), Grok 4.7: 58.0 (#18)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4.7 |
|---|---|---|
| LMArena WebDev | 1375 | 1639 |
| LMArena Coding | 1459 | 1427 |
| FrontierCode | — | 47.6% |
| CursorBench | — | 46.3% |
| FrontierSWE | — | 29.5% |
| SciCode | — | 57.8% |
| WeirdML | 52.3% | — |
| ALE-Bench | 1,150 | — |
Agentic & Tool Use Grok 4.7 leads
Grok 4.20 (Non-Reasoning): 34.4 (#46), Grok 4.7: 36.7 (#37)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4.7 |
|---|---|---|
| Vending-Bench 2 | 4,663 | 10,537 |
| Terminal-Bench | 57.3% | — |
| APEX-Agents | — | 54.6% |
| τ²-bench Banking | 18% | — |
| GDP.pdf | — | 22.8% |
| LMArena Search | 1189 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.3 (#32), Grok 4.7: 49.1 (#40)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4.7 |
|---|---|---|
| NYT Connections (extended) | 85.4% | 76.8% |
| Chess Puzzles | 24% | 38% |
| LMArena Hard Prompts | 1451 | 1413 |
| DTBench | 90.1% | 96% |
| LMCA | 38.7% | 49.4% |
| Epoch Capabilities Index | 151.98 | 153.53 |
| ARC-AGI-2 | 65.1% | — |
| Kagi LLM Benchmark | 75% | — |
| ARC-AGI-1 | 89.5% | — |
| CritPt | — | 18% |
| Thematic Generalization | 63.8% | — |
| Mystery Game Puzzles | — | 29% |
| ForecastBench | 61.4 | — |
Math Grok 4.7 leads
Grok 4.20 (Non-Reasoning): 48.2 (#65), Grok 4.7: 57.8 (#39)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4.7 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 44.9% | 53% |
| FrontierMath Tier 4 | 17.1% | 17.1% |
| OTIS Mock AIME 2024-2025 | 92.2% | 98.1% |
| ProofBench | 14% | 34% |
| LMArena Math | 1455 | 1407 |
Knowledge Grok 4.7 leads
Grok 4.20 (Non-Reasoning): 52.8 (#60), Grok 4.7: 62.8 (#22)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4.7 |
|---|---|---|
| GPQA Diamond | 89.3% | 92.7% |
| SimpleQA Verified | 30.2% | 56% |
| LMArena Expert | 1439 | 1422 |
Multimodal Grok 4.7 leads
Grok 4.20 (Non-Reasoning): 33.3 (#98), Grok 4.7: 35.5 (#87)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4.7 |
|---|---|---|
| LMArena Vision | 1263 | 1228 |
| Blueprint-Bench 2 | 0% | 32.5% |
| Furniture Assembly | — | 20.8% |
| LMArena Document | 1416 | — |
Multilingual Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 54.5 (#40), Grok 4.7: 50.8 (#116)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4.7 |
|---|---|---|
| LMArena Non-English | 1441 | 1389 |
| LMArena Chinese | 1481 | 1455 |
| LMArena French | 1476 | 1455 |
| LMArena Russian | 1458 | 1397 |
| LMArena Spanish | 1443 | 1400 |
| LMArena German | 1465 | — |
| LMArena Japanese | 1449 | — |
| LMArena Korean | 1417 | — |
Instruction Following Too close to call
Grok 4.20 (Non-Reasoning): 74.8 (#83), Grok 4.7: 74.1 (#105)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4.7 |
|---|---|---|
| LMArena Instruction Following | 1420 | 1404 |
Long Context Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 45.5 (#34), Grok 4.7: 43.1 (#104)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4.7 |
|---|---|---|
| LMArena Longer Query | 1437 | 1413 |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
Writing & Preference Grok 4.7 leads
Grok 4.20 (Non-Reasoning): 65.7 (#44), Grok 4.7: 70.0 (#24)
| Benchmark | Grok 4.20 (Non-Reasoning) | Grok 4.7 |
|---|---|---|
| LMArena Text | 1451 | 1399 |
| LMArena Creative Writing | 1438 | 1391 |
| EQ-Bench Creative Writing | 1574 | 2007 |
| LMArena Multi-Turn | 1456 | 1393 |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Grok 4.7?
Grok 4.7 is the stronger model overall, scoring 53.1 to 48.6 on the Noometry Index. Grok 4.20 (Non-Reasoning) costs 1.9× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Which is cheaper, Grok 4.20 (Non-Reasoning) or Grok 4.7?
Grok 4.20 (Non-Reasoning) is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Grok 4.7 lists at $2 and $6.
Is Grok 4.20 (Non-Reasoning) or Grok 4.7 better for coding?
Grok 4.7 scores higher on coding benchmarks: 58.0 versus 42.1 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 (Non-Reasoning) does, with 1M tokens against 500K.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Grok 4.7 share?
30 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Grok 4.7 has 39.