GPT-5.4 mini vs GPT-5 mini
| Spec | GPT-5.4 mini | GPT-5 mini |
|---|---|---|
| Respan Index | 34.1 (#81) | 20.0 (#129) |
| Blended price per 1M | $1.69 | $0.688 |
| Context window | 400K | 400K |
| Input / output per 1M | $0.75 / $4.5 | $0.25 / $2 |
| Max output | 128K | 128K |
| Input | text, vision | text, vision |
| Released | 2026-03-17 | 2025-08-07 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | GPT-5.4 mini | GPT-5 mini |
|---|---|---|
| Coding | 13.1 GPT-5.4 mini | 9.1 GPT-5 mini |
| Agents | 48.4 GPT-5.4 mini | 4.4 GPT-5 mini |
| Reasoning | 32.6 GPT-5.4 mini | 31.5 GPT-5 mini |
| Knowledge & language | 28.9 GPT-5.4 mini | 21.6 GPT-5 mini |
| Human preference | 51.1 GPT-5.4 mini | 43.9 GPT-5 mini |
Benchmarks both report
GPT-5.4 mini leads on 9 of the 11 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | GPT-5.4 mini | GPT-5 mini |
|---|---|---|
| LMArena Elo | 1447 | 1390 |
| LMArena Vision (LMArena) | 1250 | 1185 |
| Chess Puzzles (Epoch AI) | 23% | 24% |
| FrontierMath Tier 4 v2 (Epoch AI) | 9.8% | 12.2% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 51.2% | 46.7% |
| GPQA Diamond | 88% | 81.6% |
| Mystery Game Puzzles (Epoch AI) | 11% | 10% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 88.9% | 86.7% |
| SAGE (Vals AI) | 50.8% | 43% |
| SimpleQA Verified | 29.4% | 21.6% |
| WeirdML (Håvard Tveit Ihle) | 60.3% | 52.7% |
FAQ
Is GPT-5.4 mini better than GPT-5 mini?
GPT-5.4 mini scores 34.1 on the Respan Index (#81), ahead of GPT-5 mini at 20.0 (#129). GPT-5.4 mini leads on 9 of the 11 benchmarks both report.
Which is cheaper, GPT-5.4 mini or GPT-5 mini?
GPT-5.4 mini lists at $0.75 input and $4.5 output per 1M tokens; GPT-5 mini at $0.25 and $2. GPT-5 mini is 2.5x cheaper per token at list price.
Which has the larger context window?
Both accept 400K tokens of context.