Compare / head-to-head
Amazon Nova PremiervsGPT-4o
Amazon Nova Premier leads 1 of 1 shared benchmark. Amazon Nova Premier has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 0
Amazon Nova Premier leads
Cheaper per token
—
list price, input + output
Larger context
Amazon Nova Premier
1M tokens
Provider uptime (30d)
— · 94.2446%
Amazon · OpenAI
Amazon Nova Premier
Amazon · released 2025-04-30
textvision
- Context
- 1M
- Max out
- 10K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 6 · 2 core
Quality
Benchmark matrix
1 shared · 5 only Amazon Nova Premier · 7 only GPT-4o| Benchmark | Amazon Nova Premier | GPT-4o | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 1 | ||||
| MMLU | 87.4% ↗ | 85.7% ↗ | +1.7 pt | Amazon Nova Premier |
| Only Amazon Nova Premier reports · 5 | ||||
| SWE-bench Verified | 42.4% ↗ | not reported | — | — |
| BFCL | 63.7% ↗ | not reported | — | — |
| CharXiv | 84.6% ↗ | not reported | — | — |
| MATH-500 | 82% ↗ | not reported | — | — |
| SimpleQA with RAG | 86.3% ↗ | not reported | — | — |
| Only GPT-4o reports · 7 | ||||
| GPQA Diamond | not reported | 46% ↗ | — | — |
| AIME 2025 | not reported | 11.7% ↗matharena | — | — |
| AIME 2024 | not reported | 13.1% ↗ | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 0.4% ↗epoch | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | not reported | 6.4% ↗epoch | — | — |
| SimpleQA Verified | not reported | 26% ↗epoch | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 31% ↗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 Amazon Nova Premier minus GPT-4o 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 Premier | GPT-4o | Edge |
|---|---|---|---|
| Context window | 1M tokens | 128K tokens | Amazon Nova Premier |
| Max output | 10K tokens | 16K tokens | GPT-4o |
| Input price / 1M | — | $2.5 ↗ | — |
| Output price / 1M | — | $10 ↗ | — |
| Cached input / 1M | — | $1.25 ↗ | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $12.5 | — |
| Modalities | text · vision | text · vision | Tie |
| Released | 2025-04-30 | 2024-05-13 | — |
| Cited benchmark scores | 6 | 9 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Amazon Nova Premier vs …
Models sharing the most benchmarksMore matchups
GPT-4o vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Amazon Nova Premier and GPT-4o on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.