Xentir GPT-4.1 vs GPT-4.5
GPT-4.1 · OpenAI, released 2025-04-14
GPT-4.5 · OpenAI, released 2025-02-27
“Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource].” · epoch.ai/benchmarks · Licensed CC BY 4.0 · data last verified 2026-09-09 · Methodology · Data Sources
GPT-4.1 leads on more of the 4 benchmarks where both are measured — GPT-4.1 on 3, GPT-4.5 on 1. The remaining 5 of 9 tracked benchmarks cannot be compared: 5 have a result for only one of the two models, 0 for neither. Nothing on this page is estimated to fill those in.
Head-to-head
Measured on 4 of 9 tracked benchmarks for both models — GPT-4.1 leads on 3, GPT-4.5 leads on 1.
| Benchmark | GPT-4.1 | GPT-4.5 | Leads |
|---|---|---|---|
| Epoch Capabilities Index (ECI) | 136.8 | 136.8 | GPT-4.1 |
| SWE-bench Verified | 0.485 | Not measured | Comparison unavailable — GPT-4.5 has no published result |
| GPQA Diamond | 0.669 | 0.687 | GPT-4.5 |
| MATH Level 5 | 0.830 | 0.786 | GPT-4.1 |
| OTIS Mock AIME 2024-2025 | 0.383 | 0.378 | GPT-4.1 |
| FrontierMath | 0.055 | Not measured | Comparison unavailable — GPT-4.5 has no published result |
| FrontierMath Tier 4 | 0.000 | Not measured | Comparison unavailable — GPT-4.5 has no published result |
| SimpleQA Verified | 0.311 | Not measured | Comparison unavailable — GPT-4.5 has no published result |
| Chess Puzzles | 0.060 | Not measured | Comparison unavailable — GPT-4.5 has no published result |
What remains uncertain
- GPT-4.5 has no published result on Chess Puzzles, FrontierMath, FrontierMath Tier 4, SWE-bench Verified, SimpleQA Verified.
A missing result means Xentir has not found one published by the source it cites, not that the model performs badly. See Data Sources.
Reference price
| Per 1M tokens | GPT-4.1 | GPT-4.5 |
|---|---|---|
| Output | $8.00 | — |
List price as published by the vendor. Xentir does not verify negotiated or enterprise rates, and price is not a measure of capability — see Data Sources.