Up to four models
Claude Opus 5.5 vs GPT-6.1 Terra
On the index (GPT-4 = 100), Claude Opus 5.5 scores 195 and GPT-6.1 Terra 186. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Claude Opus 5.5
195178–211
WeightsClosed
ReleasedSep 2026
Price in / out$4.0 / $20
Context1M
Core tests taken6 of 9
GPT-6.1 Terra
186170–203
WeightsClosed
ReleasedOct 2026
Price in / out$1.0 / $5.0
Context1.05M
Core tests taken4 of 9
Claude Opus 5.5 leads GPT-6.1 Terra by 8 points, ahead on 3 of 4 shared core tests, at 4.0× the price.
Test by testthird-party results
Claude Opus 5.5GPT-6.1 Terra
Every result as a table
| Test | Claude Opus 5.5 | GPT-6.1 Terra |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 94.1% | 94.3% |
| EBR-bench | 71.4% | 78.1% |
| SimpleBench | 88.4% | 72.2% |
| SimpleQA Verified | 72.2% | 57.3% |
| Maths | ||
| FrontierMath (tiers 1-3) | 91.2% | 90.9% |
| AIME-style maths (OTIS mock) | 100.0% | 100.0% |
| FrontierMath (tier 4) | 95.0% | 92.7% |
| Coding | ||
| Terminal-Bench 4.0 | 65.1% | 49.5% |
| Vibe Code Bench v1.1 | 90.3% | 84.0% |
| MirrorCode | 95.6% | 76.7% |
| Agents | ||
| APEX-Agents | 73.5% | 68.3% |
| Furniture assembly | 83.3% | 79.2% |
| Mystery game puzzles | 71.0% | 74.0% |
| Professional work | ||
| HLAB-Vals-1.1 | 9.2% | 1.7% |
| Legal Research Bench | 50.5% | 26.0% |
| Tax Agent Bench | 44.5% | 17.1% |
Tests at least two of these models have taken. Bold rows are the core tests.