Compare / head-to-head
Gemini 3 Flash PreviewvsGPT-5.4 Pro
GPT-5.4 Pro leads 4 of 5 shared benchmarks. GPT-5.4 Pro has the larger context window (1.1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
1 – 4
GPT-5.4 Pro leads
Cheaper per token
—
list price, input + output
Larger context
GPT-5.4 Pro
1.1M tokens
Provider uptime (30d)
100% · 94.2446%
Google · OpenAI
Gemini 3 Flash Preview
Google · released 2025-12-17
textvisionaudio
- Context
- 1.0M
- Max out
- 66K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 13 · 9 core
GPT-5.4 Pro
OpenAI · released 2026-03-05
textvision
Quality
Benchmark matrix
5 shared · 6 only Gemini 3 Flash Preview · 7 only GPT-5.4 Pro| Benchmark | Gemini 3 Flash Preview | GPT-5.4 Pro | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 5 | ||||
| GPQA Diamond | 90.4% ↗ | 94.4% ↗ | -4 pt | GPT-5.4 Pro |
| Humanity's Last Exam (no tools) | 33.7% ↗ | 42.7% ↗ | -9 pt | GPT-5.4 Pro |
| FrontierMath Tier 4 v2 (Epoch AI run) | 17.1% ↗epoch | 58.5% ↗epoch | -41.4 pt | GPT-5.4 Pro |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 51.2% ↗epoch | 82.5% ↗epoch | -31.3 pt | GPT-5.4 Pro |
| SimpleQA Verified | 68.7% ↗ | 46.3% ↗epoch | +22.4 pt | Gemini 3 Flash Preview |
| Only Gemini 3 Flash Preview reports · 6 | ||||
| SWE-bench Verified | 78% ↗ | not reported | — | — |
| AIME 2025 | 95.2% ↗ | not reported | — | — |
| MMMU-Pro | 81.2% ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 95.6% ↗epoch | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 75.4% ↗epoch | not reported | — | — |
| Terminal-Bench 2.0 | 47.6% ↗ | not reported | — | — |
| Only GPT-5.4 Pro reports · 7 | ||||
| ARC-AGI-1 (Verified) | not reported | 94.5% ↗ | — | — |
| ARC-AGI-2 (Verified) | not reported | 83.3% ↗ | — | — |
| BrowseComp | not reported | 89.3% ↗ | — | — |
| FrontierMath Tier 1-3 | not reported | 50% ↗ | — | — |
| FrontierMath Tier 4 | not reported | 38% ↗ | — | — |
| GDPval (wins or ties) | not reported | 82% ↗ | — | — |
| Humanity's Last Exam (with tools) | not reported | 58.7% ↗ | — | — |
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 Gemini 3 Flash Preview minus GPT-5.4 Pro 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 | Gemini 3 Flash Preview | GPT-5.4 Pro | Edge |
|---|---|---|---|
| Context window | 1.0M tokens | 1.1M tokens | GPT-5.4 Pro |
| Max output | 66K tokens | 128K tokens | GPT-5.4 Pro |
| Input price / 1M | — | $30 ↗ | — |
| Output price / 1M | — | $180 ↗ | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | $210 | — |
| Modalities | text · vision · audio | text · vision | Gemini 3 Flash Preview |
| Released | 2025-12-17 | 2026-03-05 | — |
| Cited benchmark scores | 13 | 13 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Gemini 3 Flash Preview vs …
Models sharing the most benchmarksMore matchups
GPT-5.4 Pro vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Gemini 3 Flash Preview and GPT-5.4 Pro on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.