Model comparison
Grok 4.1 vs Grok 4.20 Multi-Agent
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 41.5 on the Noometry Index.
Last verified . 17 shared benchmarks.
Summary
- They share 17 benchmarks with published results for both. Grok 4.1 scores higher in 0 categories and Grok 4.20 Multi-Agent in 8 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 Multi-Agent leads 43.9 to 29.5.
Side by side
| Grok 4.1 | Grok 4.20 Multi-Agent | |
|---|---|---|
| Provider | xAI | xAI |
| Noometry Index | 41.5 | 46.2 |
| Released | 2025-11-17 | 2026-03-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 30K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 19 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 Multi-Agent leads
Grok 4.1: 33.7 (#253), Grok 4.20 Multi-Agent: 43.0 (#92)
| Benchmark | Grok 4.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Coding | 1445 | 1457 |
| LMArena WebDev | 1214 | — |
Agentic & Tool Use Not comparable
Grok 4.1: 34.1 (#49), Grok 4.20 Multi-Agent: —
| Benchmark | Grok 4.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| Cybench | 39% | — |
| LMArena Search | — | 1204 |
Reasoning Grok 4.20 Multi-Agent leads
Grok 4.1: 29.5 (#91), Grok 4.20 Multi-Agent: 43.9 (#48)
| Benchmark | Grok 4.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Hard Prompts | 1435 | 1448 |
| NYT Connections (extended) | — | 89.6% |
Math Too close to call
Grok 4.1: 38.9 (#120), Grok 4.20 Multi-Agent: 39.4 (#104)
| Benchmark | Grok 4.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Math | 1422 | 1442 |
Knowledge Too close to call
Grok 4.1: 39.5 (#133), Grok 4.20 Multi-Agent: 40.4 (#119)
| Benchmark | Grok 4.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Expert | 1417 | 1445 |
Multimodal Not comparable
Grok 4.1: —, Grok 4.20 Multi-Agent: 40.5 (#48)
| Benchmark | Grok 4.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Vision | — | 1259 |
Multilingual Grok 4.20 Multi-Agent leads
Grok 4.1: 53.4 (#68), Grok 4.20 Multi-Agent: 54.4 (#43)
| Benchmark | Grok 4.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Non-English | 1425 | 1440 |
| LMArena Chinese | 1465 | 1475 |
| LMArena French | 1448 | 1466 |
| LMArena German | 1446 | 1456 |
| LMArena Japanese | 1397 | 1405 |
| LMArena Korean | 1407 | 1416 |
| LMArena Russian | 1434 | 1457 |
| LMArena Spanish | 1438 | 1447 |
Instruction Following Too close to call
Grok 4.1: 73.8 (#111), Grok 4.20 Multi-Agent: 74.8 (#84)
| Benchmark | Grok 4.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Instruction Following | 1400 | 1420 |
Long Context Too close to call
Grok 4.1: 43.2 (#100), Grok 4.20 Multi-Agent: 43.7 (#88)
| Benchmark | Grok 4.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Longer Query | 1416 | 1431 |
Writing & Preference Grok 4.20 Multi-Agent leads
Grok 4.1: 62.4 (#75), Grok 4.20 Multi-Agent: 64.0 (#59)
| Benchmark | Grok 4.1 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Text | 1437 | 1450 |
| LMArena Creative Writing | 1411 | 1436 |
| LMArena Multi-Turn | 1437 | 1452 |
Frequently asked questions
Is Grok 4.1 better than Grok 4.20 Multi-Agent?
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 41.5 on the Noometry Index.
Is Grok 4.1 or Grok 4.20 Multi-Agent better for coding?
Grok 4.20 Multi-Agent scores higher on coding benchmarks: 43.0 versus 33.7 in the Noometry coding category.
How many benchmarks do Grok 4.1 and Grok 4.20 Multi-Agent share?
17 benchmarks have published results for both models. Grok 4.1 has 19 scored results on Noometry and Grok 4.20 Multi-Agent has 20.