GPT-4.1 mini vs GPT-5 mini
| Spec | GPT-4.1 mini | GPT-5 mini |
|---|---|---|
| Respan Index | 15.3 (#159) | 20.0 (#129) |
| Blended price per 1M | $0.7 | $0.688 |
| Context window | 1.0M | 400K |
| Input / output per 1M | $0.4 / $1.6 | $0.25 / $2 |
| Max output | 33K | 128K |
| Input | text, vision | text, vision |
| Released | 2025-04-14 | 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-4.1 mini | GPT-5 mini |
|---|---|---|
| Coding | 4.0 GPT-4.1 mini | 9.1 GPT-5 mini |
| Agents | 7.1* GPT-4.1 mini | 4.3 GPT-5 mini |
| Reasoning | 18.8 GPT-4.1 mini | 31.5 GPT-5 mini |
| Knowledge & language | 12.6 GPT-4.1 mini | 21.6 GPT-5 mini |
| Human preference | 43.9 GPT-4.1 mini | 43.9 GPT-5 mini |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
GPT-5 mini leads on 9 of the 10 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | GPT-4.1 mini | GPT-5 mini |
|---|---|---|
| Chess Puzzles (Epoch AI) | 1% | 24% |
| LMArena Vision (LMArena) | 1201 | 1186 |
| LMArena Elo | 1383 | 1390 |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 6.7% | 46.7% |
| GPQA Diamond | 65% | 81.6% |
| MATH Level 5 (Epoch AI) | 87.3% | 97.8% |
| Mystery Game Puzzles (Epoch AI) | 7% | 10% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 44.7% | 86.7% |
| SimpleQA Verified | 12.7% | 21.6% |
| WeirdML (Håvard Tveit Ihle) | 37.6% | 52.7% |
FAQ
Is GPT-4.1 mini better than GPT-5 mini?
GPT-5 mini scores 20.0 on the Respan Index (#129), ahead of GPT-4.1 mini at 15.3 (#159). GPT-5 mini leads on 9 of the 10 benchmarks both report.
Which is cheaper, GPT-4.1 mini or GPT-5 mini?
GPT-4.1 mini lists at $0.4 input and $1.6 output per 1M tokens; GPT-5 mini at $0.25 and $2. Both cost about the same per token at list price.
Which has the larger context window?
GPT-4.1 mini accepts 1.0M tokens and GPT-5 mini 400K tokens.