Up to four models
Claude Sonnet 5.5 vs GPT-6.1 Terra
On the index (GPT-4 = 100), Claude Sonnet 5.5 scores 187 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 Sonnet 5.5
187171–203
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1M
Core tests taken7 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 Sonnet 5.5 and GPT-6.1 Terra are too close to call (0 points apart, within the uncertainty), ahead on 3 of 4 shared core tests, at 2.0× the price.
Test by testthird-party results
Claude Sonnet 5.5GPT-6.1 Terra
Every result as a table
| Test | Claude Sonnet 5.5 | GPT-6.1 Terra |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 95.6% | 94.3% |
| SimpleBench | 75.9% | 72.2% |
| SimpleQA Verified | 46.5% | 57.3% |
| Maths | ||
| FrontierMath (tiers 1-3) | 88.8% | 90.9% |
| AIME-style maths (OTIS mock) | 100.0% | 100.0% |
| FrontierMath (tier 4) | 80.5% | 92.7% |
| Coding | ||
| Terminal-Bench 4.0 | 64.1% | 49.5% |
| Vibe Code Bench v1.1 | 92.4% | 84.0% |
| MirrorCode | 97.8% | 76.7% |
| Agents | ||
| APEX-Agents | 75.5% | 68.3% |
| Furniture assembly | 75.0% | 79.2% |
| Mystery game puzzles | 65.0% | 74.0% |
| Professional work | ||
| HLAB-Vals-1.1 | 10.4% | 1.7% |
| Legal Research Bench | 48.1% | 26.0% |
| Tax Agent Bench | 42.0% | 17.1% |
Tests at least two of these models have taken. Bold rows are the core tests.