GPT-5.4 nano vs o4-mini
| Spec | GPT-5.4 nano | o4-mini |
|---|---|---|
| Respan Index | 23.8 (#98) | 23.6 (#99) |
| Blended price per 1M | $0.463 | $1.93 |
| Context window | 400K | 200K |
| Input / output per 1M | $0.2 / $1.25 | $1.1 / $4.4 |
| Max output | 128K | 100K |
| Input | text, vision | text, vision |
| Released | 2026-03-17 | 2025-04-16 |
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 nano | o4-mini |
|---|---|---|
| Coding | 9.2 GPT-5.4 nano | 7.7 o4-mini |
| Agents | 21.5 GPT-5.4 nano | 23.7* o4-mini |
| Reasoning | 32.0 GPT-5.4 nano | 27.2 o4-mini |
| Knowledge & language | 13.2 GPT-5.4 nano | 19.6 o4-mini |
| Human preference | 45.2 GPT-5.4 nano | 46.7* o4-mini |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
GPT-5.4 nano leads on 6 of the 8 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | GPT-5.4 nano | o4-mini |
|---|---|---|
| Chess Puzzles (Epoch AI) | 45% | 22% |
| FrontierMath Tier 4 v2 (Epoch AI) | 12.2% | 4.9% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 44.9% | 36.1% |
| GPQA Diamond | 82.8% | 77.6% |
| Mystery Game Puzzles (Epoch AI) | 9% | 5% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 87.8% | 81.7% |
| SimpleQA Verified | 11.7% | 19.6% |
| WeirdML (Håvard Tveit Ihle) | 49.2% | 52.6% |
FAQ
Is GPT-5.4 nano better than o4-mini?
GPT-5.4 nano scores 23.8 on the Respan Index (#98), ahead of o4-mini at 23.6 (#99). GPT-5.4 nano leads on 6 of the 8 benchmarks both report.
Which is cheaper, GPT-5.4 nano or o4-mini?
GPT-5.4 nano lists at $0.2 input and $1.25 output per 1M tokens; o4-mini at $1.1 and $4.4. GPT-5.4 nano is 4.2x cheaper per token at list price.
Which has the larger context window?
GPT-5.4 nano accepts 400K tokens and o4-mini 200K tokens.