Up to four models
GPT-6.1 Terra vs Claude Opus 5
On the index (GPT-4 = 100), GPT-6.1 Terra scores 186 and Claude Opus 5 185. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
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
185169–201
WeightsClosed
ReleasedJul 2026
Price in / out$5.0 / $25
Context1M
Core tests taken6 of 9
GPT-6.1 Terra and Claude Opus 5 are too close to call (2 points apart, within the uncertainty), ahead on 3 of 4 shared core tests, and costs 5.0× less.
Test by testthird-party results
GPT-6.1 TerraClaude Opus 5
Every result as a table
| Test | GPT-6.1 Terra | Claude Opus 5 |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 94.3% | 93.9% |
| EBR-bench | 78.1% | 45.7% |
| SimpleBench | 72.2% | 80.6% |
| SimpleQA Verified | 57.3% | 59.9% |
| Maths | ||
| FrontierMath (tiers 1-3) | 90.9% | 85.6% |
| AIME-style maths (OTIS mock) | 100.0% | 98.9% |
| FrontierMath (tier 4) | 92.7% | 73.2% |
| Coding | ||
| Terminal-Bench 4.0 | 49.5% | 53.5% |
| Vibe Code Bench v1.1 | 84.0% | 88.4% |
| MirrorCode | 76.7% | 87.8% |
| Agents | ||
| APEX-Agents | 68.3% | 65.8% |
| Furniture assembly | 79.2% | 60.8% |
| Mystery game puzzles | 74.0% | 59.0% |
| Professional work | ||
| Legal Research Bench | 26.0% | 55.3% |
| Tax Agent Bench | 17.1% | 47.1% |
Tests at least two of these models have taken. Bold rows are the core tests.