Compare / head-to-head
Grok 4.20 ReasoningvsQwen3.6-Plus
Grok 4.20 Reasoning and Qwen3.6-Plus split their 4 shared benchmarks evenly. Qwen3.6-Plus is 1.9x cheaper per token. Both offer a 1M-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
2 – 2
even split
Cheaper per token
Qwen3.6-Plus
1.9x cheaper, input + output
Larger context
Tie
both 1M tokens
Provider uptime (30d)
— · —
xAI · Qwen
Grok 4.20 Reasoning
xAI · released 2026-03-09
textvision
Qwen3.6-Plus
Qwen · released 2026-04-02
textvision
Quality
Benchmark matrix
4 shared · 1 only Grok 4.20 Reasoning · 2 only Qwen3.6-Plus| Benchmark | Grok 4.20 Reasoning | Qwen3.6-Plus | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 4 | ||||
| GPQA Diamond | 89.3% ↗epoch | 88.4% ↗epoch | +0.9 pt | Grok 4.20 Reasoning |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 44.9% ↗epoch | 38.2% ↗epoch | +6.7 pt | Grok 4.20 Reasoning |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 92.2% ↗epoch | 93.3% ↗epoch | -1.1 pt | Qwen3.6-Plus |
| SimpleQA Verified | 30.2% ↗epoch | 44.1% ↗epoch | -13.9 pt | Qwen3.6-Plus |
| Only Grok 4.20 Reasoning reports · 1 | ||||
| FrontierMath Tier 4 v2 (Epoch AI run) | 17.1% ↗epoch | not reported | — | — |
| Only Qwen3.6-Plus reports · 2 | ||||
| LMArena Elo | not reported | 1436.7 ↗ | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 57.9% ↗epoch | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Grok 4.20 Reasoning minus Qwen3.6-Plus in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Grok 4.20 Reasoning | Qwen3.6-Plus | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1M tokens | Tie |
| Max output | — | — | — |
| Input price / 1M | $1.25 ↗ | $0.276 ↗ | Qwen3.6-Plus |
| Output price / 1M | $2.5 ↗ | $1.65 ↗ | Qwen3.6-Plus |
| Cached input / 1M | $0.2 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $3.75 | $1.93 | Qwen3.6-Plus |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-03-09 | 2026-04-02 | — |
| Cited benchmark scores | 5 | 6 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Grok 4.20 Reasoning vs …
Models sharing the most benchmarksMore matchups
Qwen3.6-Plus vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Grok 4.20 Reasoning and Qwen3.6-Plus on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.