Compare / head-to-head
Gemini 2.5 ProvsGPT-5.4
GPT-5.4 leads 6 of 7 shared benchmarks. Gemini 2.5 Pro is 1.6x cheaper per token. GPT-5.4 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 – 6
GPT-5.4 leads
Cheaper per token
Gemini 2.5 Pro
1.6x cheaper, input + output
Larger context
GPT-5.4
1.1M tokens
Provider uptime (30d)
100% · 95.3488%
Google · OpenAI
Gemini 2.5 Pro
Google · released 2025-06-17
textvisionaudio
Quality
Benchmark matrix
7 shared · 5 only Gemini 2.5 Pro · 13 only GPT-5.4| Benchmark | Gemini 2.5 Pro | GPT-5.4 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 7 | ||||
| GPQA Diamond | 86.4% ↗ | 92.8% ↗ | -6.4 pt | GPT-5.4 |
| Humanity's Last Exam (no tools) | 21.6% ↗ | 39.8% ↗ | -18.2 pt | GPT-5.4 |
| LMArena Elo | 1457.8 ↗ | 1452.6 ↗ | +5.2 | Gemini 2.5 Pro |
| FrontierMath Tier 4 v2 (Epoch AI run) | 0% ↗epoch | 49% ↗epoch | -49 pt | GPT-5.4 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 24.6% ↗epoch | 78.6% ↗epoch | -54 pt | GPT-5.4 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 84.7% ↗epoch | 97.8% ↗epoch | -13.1 pt | GPT-5.4 |
| SWE-bench Verified (Epoch AI run) | 57.6% ↗epoch | 76.9% ↗epoch | -19.3 pt | GPT-5.4 |
| Only Gemini 2.5 Pro reports · 5 | ||||
| SWE-bench Verified | 59.6% ↗ | not reported | — | — |
| AIME 2025 | 88% ↗ | not reported | — | — |
| Aider Polyglot | 82.2% ↗ | not reported | — | — |
| LiveCodeBench | 74.2% ↗ | not reported | — | — |
| MMMU | 82% ↗ | not reported | — | — |
| Only GPT-5.4 reports · 13 | ||||
| AIME 2026 | not reported | 99.2% ↗matharena ⚠ | — | — |
| BrowseComp | not reported | 82.7% ↗ | — | — |
| GDPval (wins or ties) | not reported | 83% ↗ | — | — |
| Humanity's Last Exam (with tools) | not reported | 52.1% ↗ | — | — |
| MCP Atlas | not reported | 67.2% ↗ | — | — |
| MMMU-Pro (no tools) | not reported | 81.2% ↗ | — | — |
| MMMU-Pro (with tools) | not reported | 82.1% ↗ | — | — |
| OSWorld-Verified | not reported | 75% ↗ | — | — |
| SimpleQA Verified | not reported | 45.1% ↗epoch | — | — |
| SWE-Bench Pro | not reported | 57.7% ↗ | — | — |
| Tau2-bench Telecom | not reported | 98.9% ↗ | — | — |
| Terminal-Bench 2.0 | not reported | 75.1% ↗ | — | — |
| Toolathlon | not reported | 54.6% ↗ | — | — |
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 2.5 Pro minus GPT-5.4 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 2.5 Pro | GPT-5.4 | Edge |
|---|---|---|---|
| Context window | 1.0M tokens | 1.1M tokens | GPT-5.4 |
| Max output | 66K tokens | 128K tokens | GPT-5.4 |
| Input price / 1M | $1.25 ↗ | $2.5 ↗ | Gemini 2.5 Pro |
| Output price / 1M | $10 ↗ | $15 ↗ | Gemini 2.5 Pro |
| Cached input / 1M | $0.125 ↗ | $0.25 ↗ | Gemini 2.5 Pro |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $11.25 | $17.5 | Gemini 2.5 Pro |
| Modalities | text · vision · audio | text · vision | Gemini 2.5 Pro |
| Released | 2025-06-17 | 2026-03-05 | — |
| Cited benchmark scores | 14 | 21 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Gemini 2.5 Pro vs …
Models sharing the most benchmarksMore matchups
GPT-5.4 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Gemini 2.5 Pro and GPT-5.4 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.