GPT-5 vs GPT-5.1
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 | GPT-5.1 |
|---|---|---|
| Coding | 10.9 GPT-5 | 14.7 GPT-5.1 |
| Agents | 54.1 GPT-5 | 33.9 GPT-5.1 |
| Reasoning | 42.2 GPT-5 | 40.2 GPT-5.1 |
| Knowledge & language | 50.0 GPT-5 | 47.9 GPT-5.1 |
| Human preference | 51.3 GPT-5 | 51.1 GPT-5.1 |
Benchmarks both report
GPT-5 leads on 8 of the 14 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | GPT-5 | GPT-5.1 |
|---|---|---|
| LMArena Elo | 1435 | 1456 |
| LMArena Vision (LMArena) | 1212 | 1251 |
| LMArena WebDev (LMArena) | 1418 | 1397 |
| Chess Puzzles (Epoch AI) | 36% | 42% |
| GPQA Diamond | 86.2% | 87.6% |
| Mystery Game Puzzles (Epoch AI) | 23% | 19% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 91.4% | 88.6% |
| SAGE (Vals AI) | 43.7% | 43.2% |
| SimpleBench (SimpleBench) | 56.7% | 53.2% |
| SimpleQA Verified | 50.1% | 48% |
| SWE-bench Verified (Epoch AI) | 73.6% | 68% |
| WeirdML (Håvard Tveit Ihle) | 60.7% | 60.8% |
| AIME 2025 | 94.6% | 94.2% |
| GSO Opt@1 (GSO) | 5.9% | 12.8% |
FAQ
Is GPT-5 better than GPT-5.1?
GPT-5 scores 39.5 on the Respan Index (#71), ahead of GPT-5.1 at 34.7 (#81). GPT-5 leads on 8 of the 14 benchmarks both report.
Which is cheaper, GPT-5 or GPT-5.1?
GPT-5 lists at $1.25 input and $10 output per 1M tokens; GPT-5.1 at $1.25 and $10. Both cost about the same per token at list price.
Which has the larger context window?
Both accept 400K tokens of context.