GPT-5.4 scores 47.2 on the Respan Index (#28), ahead of GPT-6 Luna at 46.8 (#30). GPT-5.4 leads on 12 of the 20 benchmarks both report. GPT-6 Luna is 28x cheaper per token at list price.
* Estimated: no published scores in that category. How the Respan Index works
| Furniture Assembly (Epoch AI) |
| 37.5% |
| 44.2% |
| GPQA Diamond | 92.8% | 90.5% |
| LiveBench Agentic Coding (LiveBench) | 53.8% | 51.2% |
| LiveBench Coding (LiveBench) | 77.5% | 79% |
| LiveBench Data Analysis (LiveBench) | 79.3% | 73.4% |
| LiveBench Instruction Following (LiveBench) | 70.2% | 55.9% |
| LiveBench Language (LiveBench) | 82.6% | 73.8% |
| LiveBench Mathematics (LiveBench) | 94.1% | 89.1% |
| LiveBench Reasoning (LiveBench) | 88.1% | 81.8% |
| Mystery Game Puzzles (Epoch AI) | 37% | 7% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 97.8% | 98.9% |
| SAGE (Vals AI) | 43.3% | 48.1% |
| SimpleQA Verified | 45.1% | 41.4% |
| LMArena Agent (LMArena) | 0.0105 | 0.0135 |
| LMArena Elo | 1453 | 1443 |
| LMArena WebDev (LMArena) | 1395 | 1579 |
Higher is better. Each score links to where it was published.