Compare / head-to-head
GPT-5.2vsGrok 4.20 Reasoning
GPT-5.2 leads 5 of 5 shared benchmarks. Grok 4.20 Reasoning is 4.2x cheaper per token. Grok 4.20 Reasoning has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
5 – 0
GPT-5.2 leads
Cheaper per token
Grok 4.20 Reasoning
4.2x cheaper, input + output
Larger context
Grok 4.20 Reasoning
1M tokens
Provider uptime (30d)
94.2446% · —
OpenAI · xAI
GPT-5.2
OpenAI · released 2025-12-11
textvision
Grok 4.20 Reasoning
xAI · released 2026-03-09
textvision
Quality
Benchmark matrix
5 shared · 9 only GPT-5.2 · 0 only Grok 4.20 Reasoning| Benchmark | GPT-5.2 | Grok 4.20 Reasoning | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 5 | ||||
| GPQA Diamond | 92.4% ↗ | 89.3% ↗epoch | +3.1 pt | GPT-5.2 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 31.7% ↗epoch | 17.1% ↗epoch | +14.6 pt | GPT-5.2 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 67.4% ↗epoch | 44.9% ↗epoch | +22.5 pt | GPT-5.2 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 96.1% ↗epoch | 92.2% ↗epoch | +3.9 pt | GPT-5.2 |
| SimpleQA Verified | 37.1% ↗epoch | 30.2% ↗epoch | +6.9 pt | GPT-5.2 |
| Only GPT-5.2 reports · 9 | ||||
| SWE-bench Verified | 80% ↗ | not reported | — | — |
| AIME 2025 | 100% ↗ | not reported | — | — |
| AIME 2026 | 98.3% ↗matharena | not reported | — | — |
| LMArena Elo | 1412.4 ↗ | not reported | — | — |
| ARC-AGI-1 (Verified) | 86.2% ↗ | not reported | — | — |
| ARC-AGI-2 (Verified) | 52.9% ↗ | not reported | — | — |
| GDPval (wins or ties) | 70.9% ↗ | not reported | — | — |
| SWE-Bench Pro | 55.6% ↗ | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 73.8% ↗epoch | not reported | — | — |
| Only Grok 4.20 Reasoning reports · 0 | ||||
| Grok 4.20 Reasoning reports nothing GPT-5.2 does not. | ||||
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 GPT-5.2 minus Grok 4.20 Reasoning 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 | GPT-5.2 | Grok 4.20 Reasoning | Edge |
|---|---|---|---|
| Context window | 400K tokens | 1M tokens | Grok 4.20 Reasoning |
| Max output | 128K tokens | — | — |
| Input price / 1M | $1.75 ↗ | $1.25 ↗ | Grok 4.20 Reasoning |
| Output price / 1M | $14 ↗ | $2.5 ↗ | Grok 4.20 Reasoning |
| Cached input / 1M | $0.175 ↗ | $0.2 ↗ | GPT-5.2 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $15.75 | $3.75 | Grok 4.20 Reasoning |
| Modalities | text · vision | text · vision | Tie |
| Released | 2025-12-11 | 2026-03-09 | — |
| Cited benchmark scores | 16 | 5 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
GPT-5.2 vs …
Models sharing the most benchmarksMore matchups
Grok 4.20 Reasoning vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GPT-5.2 and Grok 4.20 Reasoning on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.