Model comparison
Grok 4.20 (Non-Reasoning) vs Qwen3.6 Plus
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 47.5 on the Noometry Index.
Last verified . 31 shared benchmarks.
Alibaba (Qwen)Summary
- They share 31 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 5 categories and Qwen3.6 Plus in 3 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 29.3.
- The biggest single-benchmark swing is NYT Connections (extended): 85.4% for Grok 4.20 (Non-Reasoning) 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 (Non-Reasoning).
Side by side
| Grok 4.20 (Non-Reasoning) | Qwen3.6 Plus | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 48.6 | 47.5 |
| Released | 2026-02-17 | 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 | 46 | 37 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 42.1 (#112), Qwen3.6 Plus: 40.8 (#130)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Plus |
|---|---|---|
| LMArena WebDev | 1375 | 1461 |
| LMArena Coding | 1459 | 1467 |
| ALE-Bench | 1,150 | 670.15 |
| SWE-bench Verified | — | 57.9% |
| SciCode | — | 40.7% |
| WeirdML | 52.3% | — |
Agentic & Tool Use Not comparable
Grok 4.20 (Non-Reasoning): 34.4 (#46), Qwen3.6 Plus: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Plus |
|---|---|---|
| Vending-Bench 2 | 4,663 | 5,115 |
| Terminal-Bench | 57.3% | — |
| τ²-bench Banking | 18% | — |
| LMArena Search | 1189 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.3 (#32), Qwen3.6 Plus: 29.3 (#93)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Plus |
|---|---|---|
| NYT Connections (extended) | 85.4% | 60.3% |
| Chess Puzzles | 24% | 17% |
| Thematic Generalization | 63.8% | 59.5% |
| LMArena Hard Prompts | 1451 | 1449 |
| DTBench | 90.1% | 81.9% |
| LMCA | 38.7% | 33.1% |
| Epoch Capabilities Index | 151.98 | 147.65 |
| ARC-AGI-2 | 65.1% | — |
| Kagi LLM Benchmark | 75% | — |
| ARC-AGI-1 | 89.5% | — |
| CritPt | — | 2.9% |
| Mystery Game Puzzles | — | 12% |
| ForecastBench | 61.4 | — |
Math Qwen3.6 Plus leads
Grok 4.20 (Non-Reasoning): 48.2 (#65), Qwen3.6 Plus: 51.8 (#54)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Plus |
|---|---|---|
| FrontierMath (Tiers 1-3) | 44.9% | 38.2% |
| OTIS Mock AIME 2024-2025 | 92.2% | 93.3% |
| LMArena Math | 1455 | 1450 |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 14% | — |
| FrontierMath (Feb 2025 set) | — | 26.2% |
| FrontierMath Tier 4 (v1) | — | 8.3% |
Knowledge Qwen3.6 Plus leads
Grok 4.20 (Non-Reasoning): 52.8 (#60), Qwen3.6 Plus: 56.1 (#45)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Plus |
|---|---|---|
| GPQA Diamond | 89.3% | 88.4% |
| SimpleQA Verified | 30.2% | 44.1% |
| LMArena Expert | 1439 | 1454 |
Multimodal Not comparable
Grok 4.20 (Non-Reasoning): 33.3 (#98), Qwen3.6 Plus: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Plus |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
Multilingual Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 54.5 (#40), Qwen3.6 Plus: 53.3 (#70)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Plus |
|---|---|---|
| LMArena Non-English | 1441 | 1424 |
| LMArena Chinese | 1481 | 1477 |
| LMArena French | 1476 | 1455 |
| LMArena German | 1465 | 1452 |
| LMArena Japanese | 1449 | 1389 |
| LMArena Korean | 1417 | 1379 |
| LMArena Russian | 1458 | 1434 |
| LMArena Spanish | 1443 | 1432 |
Instruction Following Too close to call
Grok 4.20 (Non-Reasoning): 74.8 (#83), Qwen3.6 Plus: 75.0 (#74)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Plus |
|---|---|---|
| LMArena Instruction Following | 1420 | 1425 |
Long Context Too close to call
Grok 4.20 (Non-Reasoning): 45.5 (#34), Qwen3.6 Plus: 45.2 (#49)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Plus |
|---|---|---|
| CL-bench | 22.2% | 20.3% |
| LMArena Longer Query | 1437 | 1439 |
| CL-bench Life | 11.9% | — |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 65.7 (#44), Qwen3.6 Plus: 62.2 (#82)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Plus |
|---|---|---|
| LMArena Text | 1451 | 1437 |
| LMArena Creative Writing | 1438 | 1404 |
| LMArena Multi-Turn | 1456 | 1438 |
| EQ-Bench Creative Writing | 1574 | — |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Qwen3.6 Plus?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.6 to 47.5 on the Noometry Index.
Which is cheaper, Grok 4.20 (Non-Reasoning) 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 (Non-Reasoning) lists at $1.25 and $2.50.
Is Grok 4.20 (Non-Reasoning) or Qwen3.6 Plus better for coding?
Grok 4.20 (Non-Reasoning) scores higher on coding benchmarks: 42.1 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 (Non-Reasoning) and Qwen3.6 Plus share?
31 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Qwen3.6 Plus has 37.