Compare / head-to-head
GPT-5vso3
GPT-5 leads 7 of 7 shared benchmarks. o3 is 1.1x cheaper per token. GPT-5 has the larger context window (400K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
7 – 0
GPT-5 leads
Cheaper per token
o3
1.1x cheaper, input + output
Larger context
GPT-5
400K tokens
Provider uptime (30d)
94.2446%
OpenAI
GPT-5
OpenAI · released 2025-08-07
textvision
Quality
Benchmark matrix
7 shared · 1 only GPT-5 · 0 only o3| Benchmark | GPT-5 | o3 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 7 | ||||
| SWE-bench Verified | 74.9% ↗ | 69.1% ↗ | +5.8 pt | GPT-5 |
| GPQA Diamond | 86.2% ↗epoch | 81.8% ↗epoch | +4.4 pt | GPT-5 |
| AIME 2025 | 94.6% ↗ | 89.2% ↗matharena ⚠ | +5.4 pt | GPT-5 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 55.4% ↗epoch | 33.3% ↗epoch | +22.1 pt | GPT-5 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 91.4% ↗epoch | 84.4% ↗epoch | +7 pt | GPT-5 |
| SimpleQA Verified | 50.1% ↗epoch | 49.4% ↗epoch | +0.7 pt | GPT-5 |
| SWE-bench Verified (Epoch AI run) | 73.6% ↗epoch | 62.3% ↗epoch | +11.3 pt | GPT-5 |
| Only GPT-5 reports · 1 | ||||
| FrontierMath Tier 4 v2 (Epoch AI run) | 22% ↗epoch | not reported | — | — |
| Only o3 reports · 0 | ||||
| o3 reports nothing GPT-5 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 minus o3 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 | o3 | Edge |
|---|---|---|---|
| Context window | 400K tokens | 200K tokens | GPT-5 |
| Max output | 128K tokens | 100K tokens | GPT-5 |
| Input price / 1M | $1.25 ↗ | $2 ↗ | GPT-5 |
| Output price / 1M | $10 ↗ | $8 ↗ | o3 |
| Cached input / 1M | $0.125 ↗ | $0.5 ↗ | GPT-5 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $11.25 | $10 | o3 |
| Modalities | text · vision | text · vision | Tie |
| Released | 2025-08-07 | 2025-04-16 | — |
| Cited benchmark scores | 9 | 7 | — |
Reliability
OpenAI status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
GPT-5 vs …
Models sharing the most benchmarksMore matchups
o3 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GPT-5 and o3 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.