Model comparison
Grok 4.20 (Non-Reasoning) vs Qwen3.5 Plus
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 42.3 on the Noometry Index. Qwen3.5 Plus costs 1.7× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Last verified . 11 shared benchmarks.
Alibaba (Qwen)Summary
- They share 11 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 4 categories and Qwen3.5 Plus in 0 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.2 to 32.0.
- The biggest single-benchmark swing is DTBench: 90.1% for Grok 4.20 (Non-Reasoning) and 80.5% for Qwen3.5 Plus.
- Qwen3.5 Plus is cheaper at $0.40 / $2.40 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
Side by side
| Grok 4.20 (Non-Reasoning) | Qwen3.5 Plus | |
|---|---|---|
| Provider | xAI | Alibaba (Qwen) |
| Noometry Index | 48.5 | 42.3 |
| Released | 2026-02-17 | 2026-02-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1M |
| Max output | 30K | 66K |
| Input $ / M tokens | $1.25 | $0.40 |
| Output $ / M tokens | $2.50 | $2.40 |
| Results tracked | 46 | 15 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
Grok 4.20 (Non-Reasoning): 41.8 (#104), Qwen3.5 Plus: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.5 Plus |
|---|---|---|
| ALE-Bench | 1,150 | 621.92 |
| LMArena WebDev | 1374 | — |
| WeirdML | 52.3% | — |
| LMArena Coding | 1458 | — |
Agentic & Tool Use Not comparable
Grok 4.20 (Non-Reasoning): 34.3 (#43), Qwen3.5 Plus: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.5 Plus |
|---|---|---|
| Vending-Bench 2 | 4,663 | 0.54 |
| Terminal-Bench | 57.3% | — |
| τ²-bench Banking | 18% | — |
| LMArena Search | 1189 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.2 (#30), Qwen3.5 Plus: 32.0 (#67)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.5 Plus |
|---|---|---|
| Chess Puzzles | 24% | 22% |
| DTBench | 90.1% | 80.5% |
| LMCA | 38.7% | 36.4% |
| Epoch Capabilities Index | 152.01 | 146.79 |
| ARC-AGI-2 | 65.1% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 85.4% | — |
| ARC-AGI-1 | 89.5% | — |
| Thematic Generalization | 63.8% | — |
| LMArena Hard Prompts | 1451 | — |
| Mystery Game Puzzles | — | 17% |
| ForecastBench | 61.4 | — |
Math Too close to call
Grok 4.20 (Non-Reasoning): 48.0 (#54), Qwen3.5 Plus: 47.9 (#55)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.5 Plus |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 92.2% | 86.7% |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| ProofBench | 14% | — |
| LMArena Math | 1455 | — |
| FrontierMath (Feb 2025 set) | — | 21% |
| FrontierMath Tier 4 (v1) | — | 2.1% |
Knowledge Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.8 (#54), Qwen3.5 Plus: 46.0 (#78)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.5 Plus |
|---|---|---|
| GPQA Diamond | 89.3% | 84.8% |
| SimpleQA Verified | 30.2% | 25.4% |
| Vectara Hallucination Rate | — | 10.7% |
| LMArena Expert | 1440 | — |
Multimodal Not comparable
Grok 4.20 (Non-Reasoning): 33.2 (#88), Qwen3.5 Plus: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.5 Plus |
|---|---|---|
| LMArena Vision | 1263 | — |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
Multilingual Not comparable
Grok 4.20 (Non-Reasoning): 54.7 (#38), Qwen3.5 Plus: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.5 Plus |
|---|---|---|
| LMArena Non-English | 1440 | — |
| LMArena Chinese | 1481 | — |
| LMArena French | 1477 | — |
| LMArena German | 1463 | — |
| LMArena Japanese | 1450 | — |
| LMArena Korean | 1417 | — |
| LMArena Russian | 1457 | — |
| LMArena Spanish | 1442 | — |
Instruction Following Not comparable
Grok 4.20 (Non-Reasoning): 75.0 (#79), Qwen3.5 Plus: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.5 Plus |
|---|---|---|
| LMArena Instruction Following | 1420 | — |
Long Context Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 45.4 (#33), Qwen3.5 Plus: 42.9 (#109)
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.5 Plus |
|---|---|---|
| CL-bench | 22.2% | 19.8% |
| CL-bench Life | 11.9% | 12.4% |
| LMArena Longer Query | 1436 | — |
Writing & Preference Not comparable
Grok 4.20 (Non-Reasoning): 65.9 (#42), Qwen3.5 Plus: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Qwen3.5 Plus |
|---|---|---|
| LMArena Text | 1451 | — |
| LMArena Creative Writing | 1439 | — |
| EQ-Bench Creative Writing | 1574 | — |
| LMArena Multi-Turn | 1456 | — |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Qwen3.5 Plus?
Grok 4.20 (Non-Reasoning) is the stronger model overall, scoring 48.5 to 42.3 on the Noometry Index. Qwen3.5 Plus costs 1.7× less per token, which makes it the better buy when Grok 4.20 (Non-Reasoning)'s lead doesn't matter for your workload.
Which is cheaper, Grok 4.20 (Non-Reasoning) or Qwen3.5 Plus?
Qwen3.5 Plus is cheaper. It lists at $0.40 per million input tokens and $2.40 per million output tokens; Grok 4.20 (Non-Reasoning) lists at $1.25 and $2.50.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Qwen3.5 Plus share?
11 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Qwen3.5 Plus has 15.