Model comparison
Claude 3 Sonnet vs Grok 4.20 Multi-Agent
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 29.0 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Claude 3 Sonnet scores higher in 0 categories and Grok 4.20 Multi-Agent in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in math, where Grok 4.20 Multi-Agent leads 39.4 to 10.7.
Side by side
| Claude 3 Sonnet | Grok 4.20 Multi-Agent | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 29.0 | 46.2 |
| Released | 2024-02-29 | 2026-03-09 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1M |
| Max output | — | 30K |
| Input $ / M tokens | — | $1.25 |
| Output $ / M tokens | — | $2.50 |
| Results tracked | 30 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 Multi-Agent leads
Claude 3 Sonnet: 29.6 (#302), Grok 4.20 Multi-Agent: 43.0 (#92)
| Benchmark | Claude 3 Sonnet | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Coding | 1223 | 1457 |
| WeirdML | 10.2% | — |
| BigCodeBench Instruct | 42.7% | — |
| BigCodeBench Complete | 53.8% | — |
| HumanEval+ | 64% | — |
| MBPP+ | 69.3% | — |
Agentic & Tool Use Not comparable
Claude 3 Sonnet: —, Grok 4.20 Multi-Agent: —
| Benchmark | Claude 3 Sonnet | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Search | — | 1204 |
Reasoning Grok 4.20 Multi-Agent leads
Claude 3 Sonnet: 20.5 (#237), Grok 4.20 Multi-Agent: 43.9 (#48)
| Benchmark | Claude 3 Sonnet | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Hard Prompts | 1197 | 1448 |
| NYT Connections (extended) | — | 89.6% |
| DTBench | 53.6% | — |
| Epoch Capabilities Index | 120.7 | — |
| WinoGrande | 75.1% | — |
Math Grok 4.20 Multi-Agent leads
Claude 3 Sonnet: 10.7 (#310), Grok 4.20 Multi-Agent: 39.4 (#104)
| Benchmark | Claude 3 Sonnet | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Math | 1213 | 1442 |
| OTIS Mock AIME 2024-2025 | 2.5% | — |
| MATH Level 5 | 18.2% | — |
Knowledge Grok 4.20 Multi-Agent leads
Claude 3 Sonnet: 21.1 (#276), Grok 4.20 Multi-Agent: 40.4 (#119)
| Benchmark | Claude 3 Sonnet | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Expert | 1173 | 1445 |
| GPQA Diamond | 40.6% | — |
| MMLU | 75.9% | — |
Multimodal Grok 4.20 Multi-Agent leads
Claude 3 Sonnet: 25.2 (#125), Grok 4.20 Multi-Agent: 40.5 (#48)
| Benchmark | Claude 3 Sonnet | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Vision | 984 | 1259 |
Multilingual Grok 4.20 Multi-Agent leads
Claude 3 Sonnet: 37.8 (#234), Grok 4.20 Multi-Agent: 54.4 (#43)
| Benchmark | Claude 3 Sonnet | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Non-English | 1205 | 1440 |
| LMArena Chinese | 1189 | 1475 |
| LMArena French | 1229 | 1466 |
| LMArena German | 1204 | 1456 |
| LMArena Japanese | 1131 | 1405 |
| LMArena Korean | 1128 | 1416 |
| LMArena Russian | 1227 | 1457 |
| LMArena Spanish | 1204 | 1447 |
Instruction Following Grok 4.20 Multi-Agent leads
Claude 3 Sonnet: 62.8 (#235), Grok 4.20 Multi-Agent: 74.8 (#84)
| Benchmark | Claude 3 Sonnet | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Instruction Following | 1199 | 1420 |
Long Context Grok 4.20 Multi-Agent leads
Claude 3 Sonnet: 36.7 (#228), Grok 4.20 Multi-Agent: 43.7 (#88)
| Benchmark | Claude 3 Sonnet | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Longer Query | 1211 | 1431 |
Writing & Preference Grok 4.20 Multi-Agent leads
Claude 3 Sonnet: 42.1 (#238), Grok 4.20 Multi-Agent: 64.0 (#59)
| Benchmark | Claude 3 Sonnet | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Text | 1218 | 1450 |
| LMArena Creative Writing | 1186 | 1436 |
| LMArena Multi-Turn | 1227 | 1452 |
Frequently asked questions
Is Claude 3 Sonnet better than Grok 4.20 Multi-Agent?
Grok 4.20 Multi-Agent is the stronger model overall, scoring 46.2 to 29.0 on the Noometry Index.
Is Claude 3 Sonnet or Grok 4.20 Multi-Agent better for coding?
Grok 4.20 Multi-Agent scores higher on coding benchmarks: 43.0 versus 29.6 in the Noometry coding category.
How many benchmarks do Claude 3 Sonnet and Grok 4.20 Multi-Agent share?
18 benchmarks have published results for both models. Claude 3 Sonnet has 30 scored results on Noometry and Grok 4.20 Multi-Agent has 20.