GPT-5.1vsGPT-4.5
Across 4 shared benchmarks, GPT-5.1 leads overall: GPT-5.1 wins 4, GPT-4.5 wins 0, with 0 ties and an average score difference of +27.70.
GPT-5.14 wins(100%)(0%)0 winsGPT-4.5
Benchmark scores
Grouped by capability, sorted by largest gap within each. 4 shared benchmarks.
Coding and Software Engineer
GPT-5.1 2/2| Benchmark | GPT-5.1 | GPT-4.5 | Diff |
|---|---|---|---|
| SWE-bench Verified | 76.3030 / 108 | 38100 / 108 | +38.30 |
| IC SWE-Lancer(Diamond) | 69.703 / 8Thinking High (No Tools) | 32.605 / 8 | +37.10 |
General Knowledge
GPT-5.1 1/1| Benchmark | GPT-5.1 | GPT-4.5 | Diff |
|---|---|---|---|
| GPQA Diamond | 88.1028 / 178 | 71.40105 / 178 | +16.70 |
Math and Reasoning
GPT-5.1 1/1| Benchmark | GPT-5.1 | GPT-4.5 | Diff |
|---|---|---|---|
| Simple Bench | 53.2010 / 27 | 34.5020 / 27 | +18.70 |
Specs
| Field | GPT-5.1 | GPT-4.5 |
|---|---|---|
| Publisher | OpenAI | OpenAI |
| Release date | 2025-11-12 | 2025-02-28 |
| Model type | Reasoning model | Chat model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 400K | 128K |
| Max output | 128K | Not available |
Summary
- GPT-5.1leads in:Coding and Software Engineer (2/2), General Knowledge (1/1), Math and Reasoning (1/1)
On average across the 4 shared benchmarks, GPT-5.1 scores 27.70 higher.
Largest single-benchmark gap: SWE-bench Verified — GPT-5.1 76.30 vs GPT-4.5 38 (+38.30).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.