GPT-5.1 vs GPT-5.4 mini
| Spec | GPT-5.1 | GPT-5.4 mini |
|---|---|---|
| Respan Index | 34.7 (#81) | 34.1 (#82) |
| Blended price per 1M | $3.44 | $1.69 |
| Context window | 400K | 400K |
| Input / output per 1M | $1.25 / $10 | $0.75 / $4.5 |
| Max output | 128K | 128K |
| Input | text, vision | text, vision |
| Released | 2025-11-13 | 2026-03-17 |
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-5.1 | GPT-5.4 mini |
|---|---|---|
| Coding | 14.7 GPT-5.1 | 13.1 GPT-5.4 mini |
| Agents | 33.9 GPT-5.1 | 48.5 GPT-5.4 mini |
| Reasoning | 40.2 GPT-5.1 | 32.6 GPT-5.4 mini |
| Knowledge & language | 47.9 GPT-5.1 | 28.9 GPT-5.4 mini |
| Human preference | 51.1 GPT-5.1 | 51.1 GPT-5.4 mini |
Benchmarks both report
GPT-5.1 leads on 6 of the 10 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | GPT-5.1 | GPT-5.4 mini |
|---|---|---|
| LMArena WebDev (LMArena) | 1397 | 1398 |
| LMArena Elo | 1456 | 1447 |
| LMArena Vision (LMArena) | 1251 | 1250 |
| Chess Puzzles (Epoch AI) | 42% | 23% |
| GPQA Diamond | 87.6% | 88% |
| Mystery Game Puzzles (Epoch AI) | 19% | 11% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 88.6% | 88.9% |
| SAGE (Vals AI) | 43.2% | 50.8% |
| SimpleQA Verified | 48% | 29.4% |
| WeirdML (Håvard Tveit Ihle) | 60.8% | 60.3% |
FAQ
Is GPT-5.1 better than GPT-5.4 mini?
GPT-5.1 scores 34.7 on the Respan Index (#81), ahead of GPT-5.4 mini at 34.1 (#82). GPT-5.1 leads on 6 of the 10 benchmarks both report.
Which is cheaper, GPT-5.1 or GPT-5.4 mini?
GPT-5.1 lists at $1.25 input and $10 output per 1M tokens; GPT-5.4 mini at $0.75 and $4.5. GPT-5.4 mini is 2.0x cheaper per token at list price.
Which has the larger context window?
Both accept 400K tokens of context.