Model comparison
Grok 4.20 (Non-Reasoning) vs Qwen3.6 Max Preview
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 48.6 on the Noometry Index. Grok 4.20 (Non-Reasoning) costs 1.9× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Last verified . 24 shared benchmarks.
Alibaba (Qwen)Summary
- They share 24 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 4 categories and Qwen3.6 Max Preview in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 41.7.
- The biggest single-benchmark swing is SimpleQA Verified: 30.2% for Grok 4.20 (Non-Reasoning) and 52% for Qwen3.6 Max Preview.
- Grok 4.20 (Non-Reasoning) is cheaper at $1.25 / $2.50 per million input/output tokens, against $1.30 / $7.80 for Qwen3.6 Max Preview.
- Grok 4.20 (Non-Reasoning) accepts more context: 1M tokens versus 262K.
Side by side
| Grok 4.20 (Non-Reasoning) | Qwen3.6 Max Preview | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 48.6 | 51.5 |
| Released | 2026-02-17 | 2026-04-20 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 262K |
| Max output | 30K | 66K |
| Input $ / M tokens | $1.25 | $1.30 |
| Output $ / M tokens | $2.50 | $7.80 |
| Results tracked | 46 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Qwen3.6 Max Preview leads
Grok 4.20 (Non-Reasoning): 42.1 (#112), Qwen3.6 Max Preview: 48.7 (#54)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena WebDev | 1375 | 1482 |
| LMArena Coding | 1459 | 1471 |
| SWE-bench Verified | — | 76.7% |
| WeirdML | 52.3% | — |
| ALE-Bench | 1,150 | — |
Agentic & Tool Use Not comparable
Grok 4.20 (Non-Reasoning): 34.4 (#46), Qwen3.6 Max Preview: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Max Preview |
|---|---|---|
| Vending-Bench 2 | 4,663 | 4,254 |
| 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 Max Preview: 41.7 (#53)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Max Preview |
|---|---|---|
| NYT Connections (extended) | 85.4% | 74.1% |
| Chess Puzzles | 24% | 20% |
| LMArena Hard Prompts | 1451 | 1457 |
| DTBench | 90.1% | 87.2% |
| LMCA | 38.7% | 42.5% |
| Epoch Capabilities Index | 151.98 | 149.24 |
| ARC-AGI-2 | 65.1% | — |
| SimpleBench | — | 63% |
| Kagi LLM Benchmark | 75% | — |
| ARC-AGI-1 | 89.5% | — |
| Thematic Generalization | 63.8% | — |
| Mystery Game Puzzles | — | 19% |
| ForecastBench | 61.4 | — |
Math Qwen3.6 Max Preview leads
Grok 4.20 (Non-Reasoning): 48.2 (#65), Qwen3.6 Max Preview: 54.1 (#46)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Max Preview |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 92.2% | 91.1% |
| LMArena Math | 1455 | 1465 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 14% | — |
| FrontierMath (Feb 2025 set) | — | 23.1% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge Qwen3.6 Max Preview leads
Grok 4.20 (Non-Reasoning): 52.8 (#60), Qwen3.6 Max Preview: 57.6 (#39)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Max Preview |
|---|---|---|
| GPQA Diamond | 89.3% | 87.4% |
| SimpleQA Verified | 30.2% | 52% |
| LMArena Expert | 1439 | 1478 |
Multimodal Not comparable
Grok 4.20 (Non-Reasoning): 33.3 (#98), Qwen3.6 Max Preview: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
Multilingual Too close to call
Grok 4.20 (Non-Reasoning): 54.5 (#40), Qwen3.6 Max Preview: 54.2 (#48)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Non-English | 1441 | 1437 |
| LMArena Chinese | 1481 | 1487 |
| LMArena French | 1476 | 1449 |
| LMArena Russian | 1458 | 1445 |
| LMArena Spanish | 1443 | 1454 |
| LMArena German | 1465 | — |
| LMArena Japanese | 1449 | — |
| LMArena Korean | 1417 | — |
Instruction Following Too close to call
Grok 4.20 (Non-Reasoning): 74.8 (#83), Qwen3.6 Max Preview: 75.7 (#55)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Instruction Following | 1420 | 1438 |
Long Context Too close to call
Grok 4.20 (Non-Reasoning): 45.5 (#34), Qwen3.6 Max Preview: 44.6 (#61)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Longer Query | 1437 | 1457 |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 65.7 (#44), Qwen3.6 Max Preview: 63.8 (#60)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.6 Max Preview |
|---|---|---|
| LMArena Text | 1451 | 1447 |
| LMArena Creative Writing | 1438 | 1435 |
| LMArena Multi-Turn | 1456 | 1456 |
| EQ-Bench Creative Writing | 1574 | — |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Qwen3.6 Max Preview?
Qwen3.6 Max Preview is the stronger model overall, scoring 51.5 to 48.6 on the Noometry Index. Grok 4.20 (Non-Reasoning) costs 1.9× less per token, which makes it the better buy when Qwen3.6 Max Preview's lead doesn't matter for your workload.
Which is cheaper, Grok 4.20 (Non-Reasoning) or Qwen3.6 Max Preview?
Grok 4.20 (Non-Reasoning) is cheaper. It lists at $1.25 per million input tokens and $2.50 per million output tokens; Qwen3.6 Max Preview lists at $1.30 and $7.80.
Is Grok 4.20 (Non-Reasoning) or Qwen3.6 Max Preview better for coding?
Qwen3.6 Max Preview scores higher on coding benchmarks: 48.7 versus 42.1 in the Noometry coding category.
Which has the bigger context window?
Grok 4.20 (Non-Reasoning) does, with 1M tokens against 262K.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Qwen3.6 Max Preview share?
24 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Qwen3.6 Max Preview has 29.