Compare / head-to-head
GPT-5.4vsGPT-5.5
GPT-5.5 leads 13 of 17 shared benchmarks. GPT-5.4 is 2x 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
3 – 13
GPT-5.5 leads · 1 tied
Cheaper per token
GPT-5.4
2x cheaper, input + output
Larger context
GPT-5.4
1.1M tokens
Provider uptime (30d)
95.4286%
OpenAI
GPT-5.4
OpenAI · released 2026-03-05
textvision
Quality
Benchmark matrix
17 shared · 3 only GPT-5.4 · 4 only GPT-5.5| Benchmark | GPT-5.4 | GPT-5.5 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 17 | ||||
| GPQA Diamond | 92.8% ↗ | 90.7% ↗epoch | +2.1 pt | GPT-5.4 |
| AIME 2026 | 99.2% ↗matharena ⚠ | 100% ↗matharena ⚠ | -0.8 pt | GPT-5.5 |
| LMArena Elo | 1452.6 ↗ | 1465.6 ↗ | -13 | GPT-5.5 |
| BrowseComp | 82.7% ↗ | 84.4% ↗ | -1.7 pt | GPT-5.5 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 49% ↗epoch | 72.5% ↗epoch | -23.5 pt | GPT-5.5 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 78.6% ↗epoch | 85.3% ↗epoch | -6.7 pt | GPT-5.5 |
| GDPval (wins or ties) | 83% ↗ | 84.9% ↗ | -1.9 pt | GPT-5.5 |
| MCP Atlas | 67.2% ↗ | 75.3% ↗ | -8.1 pt | GPT-5.5 |
| MMMU-Pro (no tools) | 81.2% ↗ | 81.2% ↗ | 0 | Tie |
| MMMU-Pro (with tools) | 82.1% ↗ | 83.2% ↗ | -1.1 pt | GPT-5.5 |
| OSWorld-Verified | 75% ↗ | 78.7% ↗ | -3.7 pt | GPT-5.5 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 97.8% ↗epoch | 84.4% ↗epoch | +13.4 pt | GPT-5.4 |
| SimpleQA Verified | 45.1% ↗epoch | 63% ↗epoch | -17.9 pt | GPT-5.5 |
| SWE-Bench Pro | 57.7% ↗ | 58.6% ↗ | -0.9 pt | GPT-5.5 |
| Tau2-bench Telecom | 98.9% ↗ | 98% ↗ | +0.9 pt | GPT-5.4 |
| Terminal-Bench 2.0 | 75.1% ↗ | 82.7% ↗ | -7.6 pt | GPT-5.5 |
| Toolathlon | 54.6% ↗ | 55.6% ↗ | -1 pt | GPT-5.5 |
| Only GPT-5.4 reports · 3 | ||||
| Humanity's Last Exam (no tools) | 39.8% ↗ | not reported | — | — |
| Humanity's Last Exam (with tools) | 52.1% ↗ | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 76.9% ↗epoch | not reported | — | — |
| Only GPT-5.5 reports · 4 | ||||
| ARC-AGI-1 (Verified) | not reported | 95% ↗ | — | — |
| ARC-AGI-2 (Verified) | not reported | 85% ↗ | — | — |
| FrontierMath Tier 1-3 | not reported | 51.7% ↗ | — | — |
| FrontierMath Tier 4 | not reported | 35.4% ↗ | — | — |
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 minus GPT-5.5 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 | GPT-5.5 | Edge |
|---|---|---|---|
| Context window | 1.1M tokens | 1M tokens | GPT-5.4 |
| Max output | 128K tokens | 128K tokens | Tie |
| Input price / 1M | $2.5 ↗ | $5 ↗ | GPT-5.4 |
| Output price / 1M | $15 ↗ | $30 ↗ | GPT-5.4 |
| Cached input / 1M | $0.25 ↗ | $0.5 ↗ | GPT-5.4 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $17.5 | $35 | GPT-5.4 |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-03-05 | 2026-04-23 | — |
| Cited benchmark scores | 21 | 21 | — |
Reliability
OpenAI status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
GPT-5.4 vs …
Models sharing the most benchmarksMore matchups
GPT-5.5 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run GPT-5.4 and GPT-5.5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.