Compare / head-to-head
GPT-5.2vsLlama 3.3 70B Instruct
GPT-5.2 leads 3 of 3 shared benchmarks. GPT-5.2 has the larger context window (400K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
3 – 0
GPT-5.2 leads
Cheaper per token
—
list price, input + output
Larger context
GPT-5.2
400K tokens
Provider uptime (30d)
94.2446% · —
OpenAI · Meta
GPT-5.2
OpenAI · released 2025-12-11
textvision
Llama 3.3 70B Instruct
Meta · released 2024-12-06
text
- Context
- 131K
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 5 · 4 core
Quality
Benchmark matrix
3 shared · 11 only GPT-5.2 · 1 only Llama 3.3 70B Instruct| Benchmark | GPT-5.2 | Llama 3.3 70B Instruct | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 3 | ||||
| GPQA Diamond | 92.4% ↗ | 50.5% ↗ | +41.9 pt | GPT-5.2 |
| LMArena Elo | 1412.4 ↗ | 1274 ↗ | +138.4 | GPT-5.2 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 96.1% ↗epoch | 5.1% ↗epoch | +91 pt | GPT-5.2 |
| Only GPT-5.2 reports · 11 | ||||
| SWE-bench Verified | 80% ↗ | not reported | — | — |
| AIME 2025 | 100% ↗ | not reported | — | — |
| AIME 2026 | 98.3% ↗matharena | not reported | — | — |
| ARC-AGI-1 (Verified) | 86.2% ↗ | not reported | — | — |
| ARC-AGI-2 (Verified) | 52.9% ↗ | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 31.7% ↗epoch | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 67.4% ↗epoch | not reported | — | — |
| GDPval (wins or ties) | 70.9% ↗ | not reported | — | — |
| SimpleQA Verified | 37.1% ↗epoch | not reported | — | — |
| SWE-Bench Pro | 55.6% ↗ | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 73.8% ↗epoch | not reported | — | — |
| Only Llama 3.3 70B Instruct reports · 1 | ||||
| MMLU-Pro | not reported | 68.9% ↗ | — | — |
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 Llama 3.3 70B Instruct 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 | Llama 3.3 70B Instruct | Edge |
|---|---|---|---|
| Context window | 400K tokens | 131K tokens | GPT-5.2 |
| Max output | 128K tokens | — | — |
| Input price / 1M | $1.75 ↗ | — | — |
| Output price / 1M | $14 ↗ | — | — |
| Cached input / 1M | $0.175 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $15.75 | — | — |
| Modalities | text · vision | text | GPT-5.2 |
| Released | 2025-12-11 | 2024-12-06 | — |
| 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
Llama 3.3 70B Instruct 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 Llama 3.3 70B Instruct on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.