Compare / Claude Opus 4.7 vs GPT-5.6 Terra
Claude Opus 4.7 vs GPT-5.6 Terra
25 results from 7 sources that measured both models. Each row is in the source's own units; there is no overall winner.
| Benchmark | Metric | Claude Opus 4.7 | GPT-5.6 Terra |
|---|---|---|---|
| APEX-Agentsreported | Tasks passed% of tasks | 49.2% | 58.2% |
| Arena (formerly LMArena)reported | OverallArena rating | 1,494 | 1,477 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,477 | 1,467 |
| Arena (formerly LMArena)reported | Business, management and financeArena rating | 1,508 | 1,466 |
| Arena (formerly LMArena)reported | Creative writingArena rating | 1,488 | 1,428 |
| Arena (formerly LMArena)reported | Expert promptsArena rating | 1,535 | 1,504 |
| Arena (formerly LMArena)reported | Instruction followingArena rating | 1,503 | 1,462 |
| Arena (formerly LMArena)reported | OverallArena rating | 1,502 | 1,465 |
| Arena (formerly LMArena)reported | Writing, literature and languageArena rating | 1,496 | 1,445 |
| Artificial Analysisreported | Artificial Analysis Coding Indexindex score | 73.6 | 76.7 |
| Artificial Analysisreported | Artificial Analysis Intelligence Indexindex score | 40.7 | 42.1 |
| Artificial Analysisreported | GPQA Diamond% of questions | 91.4% | 92.5% |
| Artificial Analysisreported | Humanity's Last Exam% of questions | 42.3% | 42.9% |
| Artificial Analysisreported | IFBench% of instructions | 58.6% | 71.2% |
| Artificial Analysisreported | Long-context reasoning (AA-LCR)% of questions | 78.7% | 83.0% |
| Artificial Analysisreported | Terminal-Bench 2.1% of tasks | 83.1% | 88.0% |
| Artificial Analysisreported | Terminal-Bench Hard% of tasks | 54.5% | 62.9% |
| Artificial Analysisreported | Τ-bench banking% of tasks | 34.6% | 40.2% |
| Artificial Analysisreported | Τ²-bench telecom% of tasks | 88.6% | 86.3% |
| GDP.pdfreported | Professional document tasks% of rubric | 21.0% | 24.7% |
| SimpleQA Verified (Epoch AI)reported | Correct answers% of questions | 51.7% | 43.2% |
| UGI Leaderboardreported | Requested-length error% off the requested word count | 1.0% | 22.0% |
| UGI Leaderboardreported | Style adherencescore from 0 to 1 | 0.41 | 0.39 |
| UGI Leaderboardreported | Writing scorescore out of 100 | 61.4 | 60.4 |
| Vending-Bench 2reported | Money after a yearUS dollars | $10,936.76 | $7,343.21 |
Bold green marks the better value on that metric. Where a source reports ranges that overlap, the difference may not be meaningful; see the benchmark page for ranges.