Compare / head-to-head
GPT-5.4 minivso3
GPT-5.4 mini leads 3 of 4 shared benchmarks. GPT-5.4 mini is 1.9x cheaper per token. GPT-5.4 mini has the larger context window (400K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
3 – 1
GPT-5.4 mini leads
Cheaper per token
GPT-5.4 mini
1.9x cheaper, input + output
Larger context
GPT-5.4 mini
400K tokens
Provider uptime (30d)
94.386%
OpenAI
GPT-5.4 mini
OpenAI · released 2026-03-17
textvision
Quality
Benchmark matrix
4 shared · 5 only GPT-5.4 mini · 3 only o3| Benchmark | GPT-5.4 mini | o3 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 4 | ||||
| GPQA Diamond | 88% ↗ | 81.8% ↗epoch | +6.2 pt | GPT-5.4 mini |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 51.2% ↗epoch | 33.3% ↗epoch | +17.9 pt | GPT-5.4 mini |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 88.9% ↗epoch | 84.4% ↗epoch | +4.5 pt | GPT-5.4 mini |
| SimpleQA Verified | 29.4% ↗epoch | 49.4% ↗epoch | -20 pt | o3 |
| Only GPT-5.4 mini reports · 5 | ||||
| FrontierMath Tier 4 v2 (Epoch AI run) | 9.8% ↗epoch | not reported | — | — |
| OSWorld-Verified | 72.1% ↗ | not reported | — | — |
| SWE-Bench Pro | 54.4% ↗ | not reported | — | — |
| Terminal-Bench 2.0 | 60% ↗ | not reported | — | — |
| Toolathlon | 42.9% ↗ | not reported | — | — |
| Only o3 reports · 3 | ||||
| SWE-bench Verified | not reported | 69.1% ↗ | — | — |
| AIME 2025 | not reported | 89.2% ↗matharena ⚠ | — | — |
| SWE-bench Verified (Epoch AI run) | not reported | 62.3% ↗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 GPT-5.4 mini 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-5.4 mini | o3 | Edge |
|---|---|---|---|
| Context window | 400K tokens | 200K tokens | GPT-5.4 mini |
| Max output | 128K tokens | 100K tokens | GPT-5.4 mini |
| Input price / 1M | $0.75 ↗ | $2 ↗ | GPT-5.4 mini |
| Output price / 1M | $4.5 ↗ | $8 ↗ | GPT-5.4 mini |
| Cached input / 1M | $0.075 ↗ | $0.5 ↗ | GPT-5.4 mini |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $5.25 | $10 | GPT-5.4 mini |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-03-17 | 2025-04-16 | — |
| Cited benchmark scores | 10 | 7 | — |
Reliability
OpenAI status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
GPT-5.4 mini 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-5.4 mini and o3 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.