Compare / head-to-head
Amazon Nova ProvsGPT-5.6 Luna
Amazon Nova Pro and GPT-5.6 Luna do not yet share a public benchmark, so quality cannot be compared apples-to-apples. GPT-5.6 Luna is 2.9x cheaper per token. GPT-5.6 Luna has the larger context window (1.1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0
no overlap yet
Cheaper per token
GPT-5.6 Luna
2.9x cheaper, input + output
Larger context
GPT-5.6 Luna
1.1M tokens
Provider uptime (30d)
— · 94.2446%
Amazon · OpenAI
Amazon Nova Pro
Amazon · released 2024-12-02
textvision
GPT-5.6 Luna
OpenAI · released 2026-07-09
textvision
Quality
Benchmark matrix
0 shared · 8 only Amazon Nova Pro · 7 only GPT-5.6 Luna| Benchmark | Amazon Nova Pro | GPT-5.6 Luna | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 0 | ||||
| No public benchmark is reported for both models yet. | ||||
| Only Amazon Nova Pro reports · 8 | ||||
| MMLU | 85.9% ↗ | not reported | — | — |
| ARC-C | 94.8% ↗ | not reported | — | — |
| BBH | 86.9% ↗ | not reported | — | — |
| DROP | 85.4% ↗ | not reported | — | — |
| GPQA | 46.9% ↗ | not reported | — | — |
| GSM8K | 94.8% ↗ | not reported | — | — |
| IFEval | 92.1% ↗ | not reported | — | — |
| MATH | 76.6% ↗ | not reported | — | — |
| Only GPT-5.6 Luna reports · 7 | ||||
| GPQA Diamond | not reported | 92.3% ↗ | — | — |
| DeepSWE v1.1 | not reported | 67.2% ↗ | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 61% ↗epoch | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 82.1% ↗epoch | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | not reported | 98.3% ↗epoch | — | — |
| SimpleQA Verified | not reported | 41% ↗epoch | — | — |
| SWE-Bench Pro | not reported | 62.7% ↗ | — | — |
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 Amazon Nova Pro minus GPT-5.6 Luna 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 | Amazon Nova Pro | GPT-5.6 Luna | Edge |
|---|---|---|---|
| Context window | 300K tokens | 1.1M tokens | GPT-5.6 Luna |
| Max output | 10K tokens | 128K tokens | GPT-5.6 Luna |
| Input price / 1M | $0.8 ↗ | $0.2 ↗ | GPT-5.6 Luna |
| Output price / 1M | $3.2 ↗ | $1.2 ↗ | GPT-5.6 Luna |
| Cached input / 1M | — | $0.02 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $4 | $1.4 | GPT-5.6 Luna |
| Modalities | text · vision | text · vision | Tie |
| Released | 2024-12-02 | 2026-07-09 | — |
| Cited benchmark scores | 8 | 8 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Amazon Nova Pro vs …
Models sharing the most benchmarksMore matchups
GPT-5.6 Luna vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Amazon Nova Pro and GPT-5.6 Luna on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.