GPT-4.1 vs GPT-5
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 | GPT-5 |
|---|---|---|
| Coding | 3.8 GPT-4.1 | 10.9 GPT-5 |
| Agents | 11.9* GPT-4.1 | 54.1 GPT-5 |
| Reasoning | 20.5 GPT-4.1 | 42.2 GPT-5 |
| Knowledge & language | 30.9 GPT-4.1 | 50.0 GPT-5 |
| Human preference | 47.3 GPT-4.1 | 51.3 GPT-5 |
* Estimated: no published scores in that category. How the Respan Index works
Benchmarks both report
GPT-5 leads on 11 of the 12 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | GPT-4.1 | GPT-5 |
|---|---|---|
| Chess Puzzles (Epoch AI) | 11% | 36% |
| LMArena Vision (LMArena) | 1214 | 1212 |
| LMArena Elo | 1415 | 1435 |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 6% | 55.4% |
| GPQA Diamond | 66.3% | 86.2% |
| MATH Level 5 (Epoch AI) | 83% | 98.1% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 38.3% | 91.4% |
| SimpleBench (SimpleBench) | 27% | 56.7% |
| SimpleQA Verified | 31.1% | 50.1% |
| SWE-bench Verified (Epoch AI) | 48.5% | 73.6% |
| WeirdML (Håvard Tveit Ihle) | 39% | 60.7% |
| SWE-bench Verified | 54.6% | 74.9% |
FAQ
Is GPT-4.1 better than GPT-5?
GPT-5 scores 39.5 on the Respan Index (#71), ahead of GPT-4.1 at 19.2 (#134). GPT-5 leads on 11 of the 12 benchmarks both report.
Which is cheaper, GPT-4.1 or GPT-5?
GPT-4.1 lists at $2 input and $8 output per 1M tokens; GPT-5 at $1.25 and $10. Both cost about the same per token at list price.
Which has the larger context window?
GPT-4.1 accepts 1.0M tokens and GPT-5 400K tokens.