Claude Opus 5 scores 63.9 on the Respan Index (#7), ahead of GPT-5.6 Terra at 53.5 (#14). Claude Opus 5 leads on 21 of the 26 benchmarks both report. GPT-5.6 Terra is 2.2x cheaper per token at list price. GPT-5.6 Terra has the larger context window (1.1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| FrontierMath Tiers 1-3 v2 (Epoch AI) |
| 85.6% |
| 86% |
| Furniture Assembly (Epoch AI) | 60.8% | 54.2% |
| GPQA Diamond | 93.9% | 92.9% |
| LiveBench Agentic Coding (LiveBench) | 65.2% | 54.9% |
| LiveBench Coding (LiveBench) | 81.4% | 78.2% |
| LiveBench Data Analysis (LiveBench) | 74.6% | 79.3% |
| LiveBench Instruction Following (LiveBench) | 63.8% | 64.6% |
| LiveBench Language (LiveBench) | 88.7% | 82.9% |
| LiveBench Mathematics (LiveBench) | 95.7% | 94.9% |
| LiveBench Reasoning (LiveBench) | 91.2% | 90.6% |
| Mystery Game Puzzles (Epoch AI) | 59% | 35% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 98.9% | 99.7% |
| SAGE (Vals AI) | 49.4% | 47% |
| SimpleQA Verified | 59.9% | 43.2% |
| Terminal-Bench 4.0 (Vals AI) | 53.5% | 22.7% |
| Vending-Bench 2 (Andon Labs) | 11181.87 | 7343.21 |
| WeirdML (Håvard Tveit Ihle) | 91.8% | 78.3% |
| LMArena Agent (LMArena) | 0.0867 | 0.004 |
| LMArena Elo | 1490 | 1466 |
| LMArena Vision (LMArena) | 1289 | 1268 |
| BALROG (BALROG) | 63.4% | 53.2% |
| SimpleBench (SimpleBench) | 80.6% | 48.9% |
Higher is better. Each score links to where it was published.