Model comparison
Claude Sonnet 4.6 vs Grok 4.20 Multi-Agent
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 46.2 on the Noometry Index. Grok 4.20 Multi-Agent costs 3.8× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.
Last verified . 20 shared benchmarks.
Summary
- They share 20 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 8 categories and Grok 4.20 Multi-Agent in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Claude Sonnet 4.6 leads 52.9 to 39.4.
- The biggest single-benchmark swing is NYT Connections (extended): 80.9% for Claude Sonnet 4.6 and 89.6% for Grok 4.20 Multi-Agent.
- Grok 4.20 Multi-Agent is cheaper at $1.25 / $2.50 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
Side by side
| Claude Sonnet 4.6 | Grok 4.20 Multi-Agent | |
|---|---|---|
| Provider | Anthropic | xAI |
| Noometry Index | 50.3 | 46.2 |
| Released | 2026-02-17 | 2026-03-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 128K | 30K |
| Input $ / M tokens | $3 | $1.25 |
| Output $ / M tokens | $15 | $2.50 |
| Results tracked | 57 | 20 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.3 (#67), Grok 4.20 Multi-Agent: 43.0 (#92)
| Benchmark | Claude Sonnet 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Coding | 1504 | 1457 |
| SWE-bench Verified | 75.2% | — |
| DeepSWE | 29.9% | — |
| FrontierCode | 24.3% | — |
| LMArena WebDev | 1522 | — |
| SciCode | 46.8% | — |
| WeirdML | 66.1% | — |
| ALE-Bench | 1,327 | — |
Agentic & Tool Use Not comparable
Claude Sonnet 4.6: 39.1 (#28), Grok 4.20 Multi-Agent: —
| Benchmark | Claude Sonnet 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Search | 1221 | 1204 |
| Terminal-Bench | 53.4% | — |
| APEX-Agents | 43% | — |
| OSWorld 2.0 | 9.3% | — |
| DeepResearch Bench | 54.9% | — |
| OSWorld | 72.1% | — |
| ExploitBench | 23.6% | — |
| GBAEval | 48.8% | — |
| GDP.pdf | 18% | — |
| Vending-Bench 2 | 7,204 | — |
Reasoning Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 46.1 (#45), Grok 4.20 Multi-Agent: 43.9 (#48)
| Benchmark | Claude Sonnet 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| NYT Connections (extended) | 80.9% | 89.6% |
| LMArena Hard Prompts | 1484 | 1448 |
| ARC-AGI-2 | 60.4% | — |
| ARC-AGI-1 | 86.5% | — |
| CritPt | 3.1% | — |
| Chess Puzzles | 13% | — |
| Thematic Generalization | 76.3% | — |
| Mystery Game Puzzles | 16% | — |
| DTBench | 89.9% | — |
| LMCA | 46.5% | — |
| Epoch Capabilities Index | 152.24 | — |
| ForecastBench | 62 | — |
Math Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 52.9 (#49), Grok 4.20 Multi-Agent: 39.4 (#104)
| Benchmark | Claude Sonnet 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Math | 1462 | 1442 |
| OTIS Mock AIME 2024-2025 | 85.8% | — |
| ProofBench | 45% | — |
| FrontierMath (Feb 2025 set) | 32.4% | — |
| FrontierMath Tier 4 (v1) | 8.3% | — |
Knowledge Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 51.7 (#65), Grok 4.20 Multi-Agent: 40.4 (#119)
| Benchmark | Claude Sonnet 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Expert | 1500 | 1445 |
| GPQA Diamond | 87.4% | — |
| SimpleQA Verified | 35.5% | — |
| Vectara Hallucination Rate | 10.6% | — |
Multimodal Grok 4.20 Multi-Agent leads
Claude Sonnet 4.6: 38.0 (#68), Grok 4.20 Multi-Agent: 40.5 (#48)
| Benchmark | Claude Sonnet 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Vision | 1283 | 1259 |
| Blueprint-Bench 2 | 6.7% | — |
| LMArena Document | 1482 | — |
Multilingual Too close to call
Claude Sonnet 4.6: 54.4 (#41), Grok 4.20 Multi-Agent: 54.4 (#43)
| Benchmark | Claude Sonnet 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Non-English | 1440 | 1440 |
| LMArena Chinese | 1491 | 1475 |
| LMArena French | 1465 | 1466 |
| LMArena German | 1428 | 1456 |
| LMArena Japanese | 1420 | 1405 |
| LMArena Korean | 1411 | 1416 |
| LMArena Russian | 1440 | 1457 |
| LMArena Spanish | 1464 | 1447 |
Instruction Following Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 77.4 (#25), Grok 4.20 Multi-Agent: 74.8 (#84)
| Benchmark | Claude Sonnet 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Instruction Following | 1475 | 1420 |
Long Context Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 45.3 (#44), Grok 4.20 Multi-Agent: 43.7 (#88)
| Benchmark | Claude Sonnet 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Longer Query | 1479 | 1431 |
Writing & Preference Claude Sonnet 4.6 leads
Claude Sonnet 4.6: 70.2 (#22), Grok 4.20 Multi-Agent: 64.0 (#59)
| Benchmark | Claude Sonnet 4.6 | Grok 4.20 Multi-Agent |
|---|---|---|
| LMArena Text | 1458 | 1450 |
| LMArena Creative Writing | 1435 | 1436 |
| LMArena Multi-Turn | 1464 | 1452 |
| EQ-Bench Creative Writing | 1810 | — |
| EQ-Bench 4 | 1207 | — |
Frequently asked questions
Is Claude Sonnet 4.6 better than Grok 4.20 Multi-Agent?
Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 46.2 on the Noometry Index. Grok 4.20 Multi-Agent costs 3.8× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.
Which is cheaper, Claude Sonnet 4.6 or Grok 4.20 Multi-Agent?
Grok 4.20 Multi-Agent is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Claude Sonnet 4.6 lists at $3 and $15.
Is Claude Sonnet 4.6 or Grok 4.20 Multi-Agent better for coding?
Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 43.0 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Sonnet 4.6 and Grok 4.20 Multi-Agent share?
20 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and Grok 4.20 Multi-Agent has 20.