Model comparison
Grok 4.20 Multi-Agent vs Qwen3.6 Plus
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 46.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
Alibaba (Qwen)Summary
- They share 18 benchmarks with published results for both. Grok 4.20 Multi-Agent scores higher in 4 categories and Qwen3.6 Plus in 4 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Qwen3.6 Plus leads 56.1 to 40.4.
- The biggest single-benchmark swing is NYT Connections (extended): 89.6% for Grok 4.20 Multi-Agent and 60.3% for Qwen3.6 Plus.
- Qwen3.6 Plus is cheaper at $0.50 / $3 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 Multi-Agent.
Side by side
| Grok 4.20 Multi-Agent | Qwen3.6 Plus | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 46.2 | 47.5 |
| Released | 2026-03-09 | 2026-03-31 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 30K | 66K |
| Input $ / M tokens | $1.25 | $0.50 |
| Output $ / M tokens | $2.50 | $3 |
| Results tracked | 20 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 43.0 (#92), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | Grok 4.20 Multi-Agent | Qwen3.6 Plus |
|---|---|---|
| LMArena Coding | 1457 | 1467 |
| SWE-bench Verified | — | 57.9% |
| LMArena WebDev | — | 1461 |
| SciCode | — | 40.7% |
| ALE-Bench | — | 670.15 |
Agentic & Tool Use Not comparable
Grok 4.20 Multi-Agent: —, Qwen3.6 Plus: —
| Benchmark | Grok 4.20 Multi-Agent | Qwen3.6 Plus |
|---|---|---|
| LMArena Search | 1204 | — |
| Vending-Bench 2 | — | 5,115 |
Reasoning Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 43.9 (#48), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | Grok 4.20 Multi-Agent | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 89.6% | 60.3% |
| LMArena Hard Prompts | 1448 | 1449 |
| CritPt | — | 2.9% |
| Chess Puzzles | — | 17% |
| Thematic Generalization | — | 59.5% |
| Mystery Game Puzzles | — | 12% |
| DTBench | — | 81.9% |
| LMCA | — | 33.1% |
| Epoch Capabilities Index | — | 147.65 |
Math Qwen3.6 Plus leads
Grok 4.20 Multi-Agent: 39.4 (#104), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | Grok 4.20 Multi-Agent | Qwen3.6 Plus |
|---|---|---|
| LMArena Math | 1442 | 1450 |
| FrontierMath (Tiers 1-3) | — | 38.2% |
| OTIS Mock AIME 2024-2025 | — | 93.3% |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Qwen3.6 Plus leads
Grok 4.20 Multi-Agent: 40.4 (#119), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | Grok 4.20 Multi-Agent | Qwen3.6 Plus |
|---|---|---|
| LMArena Expert | 1445 | 1454 |
| GPQA Diamond | — | 88.4% |
| SimpleQA Verified | — | 44.1% |
Multimodal Not comparable
Grok 4.20 Multi-Agent: 40.5 (#48), Qwen3.6 Plus: —
| Benchmark | Grok 4.20 Multi-Agent | Qwen3.6 Plus |
|---|---|---|
| LMArena Vision | 1259 | — |
Multilingual Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 54.4 (#43), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | Grok 4.20 Multi-Agent | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1440 | 1424 |
| LMArena Chinese | 1475 | 1477 |
| LMArena French | 1466 | 1455 |
| LMArena German | 1456 | 1452 |
| LMArena Japanese | 1405 | 1389 |
| LMArena Korean | 1416 | 1379 |
| LMArena Russian | 1457 | 1434 |
| LMArena Spanish | 1447 | 1432 |
Instruction Following Too close to call
Grok 4.20 Multi-Agent: 74.8 (#84), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | Grok 4.20 Multi-Agent | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1420 | 1425 |
Long Context Qwen3.6 Plus leads
Grok 4.20 Multi-Agent: 43.7 (#88), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | Grok 4.20 Multi-Agent | Qwen3.6 Plus |
|---|---|---|
| LMArena Longer Query | 1431 | 1439 |
| CL-bench | — | 20.3% |
Writing & Preference Grok 4.20 Multi-Agent leads
Grok 4.20 Multi-Agent: 64.0 (#59), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | Grok 4.20 Multi-Agent | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1450 | 1437 |
| LMArena Creative Writing | 1436 | 1404 |
| LMArena Multi-Turn | 1452 | 1438 |
Frequently asked questions
Is Grok 4.20 Multi-Agent better than Qwen3.6 Plus?
Qwen3.6 Plus is the stronger model overall, scoring 47.5 to 46.2 on the Noometry Index.
Which is cheaper, Grok 4.20 Multi-Agent or Qwen3.6 Plus?
Qwen3.6 Plus is cheaper. It lists at $0.50 per million input tokens and $3 per million output tokens; Grok 4.20 Multi-Agent lists at $1.25 and $2.50.
Is Grok 4.20 Multi-Agent or Qwen3.6 Plus better for coding?
Grok 4.20 Multi-Agent scores higher on coding benchmarks: 43.0 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Grok 4.20 Multi-Agent and Qwen3.6 Plus share?
18 benchmarks have published results for both models. Grok 4.20 Multi-Agent has 20 scored results on Noometry and Qwen3.6 Plus has 37.