Up to four models
GPT-6.1 Sol vs GPT-6.1 Terra
On the index (GPT-4 = 100), GPT-6.1 Sol scores 191 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.
GPT-6.1 Sol
191175–207
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1.05M
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
GPT-6.1 Sol and GPT-6.1 Terra are too close to call (5 points apart, within the uncertainty), ahead on 3 of 4 shared core tests, at 2.0× the price.
Test by testthird-party results
GPT-6.1 SolGPT-6.1 Terra
Every result as a table
| Test | GPT-6.1 Sol | GPT-6.1 Terra |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 95.4% | 94.3% |
| EBR-bench | 54.3% | 78.1% |
| SimpleBench | 82.9% | 72.2% |
| SimpleQA Verified | 73.9% | 57.3% |
| Maths | ||
| FrontierMath (tiers 1-3) | 93.7% | 90.9% |
| AIME-style maths (OTIS mock) | 100.0% | 100.0% |
| FrontierMath (tier 4) | 100.0% | 92.7% |
| Coding | ||
| Terminal-Bench 4.0 | 55.0% | 49.5% |
| Vibe Code Bench v1.1 | 88.9% | 84.0% |
| MirrorCode | 61.1% | 76.7% |
| Agents | ||
| APEX-Agents | 60.0% | 68.3% |
| Furniture assembly | 80.0% | 79.2% |
| Mystery game puzzles | 80.0% | 74.0% |
| Professional work | ||
| HLAB-Vals-1.1 | 6.3% | 1.7% |
| Legal Research Bench | 38.5% | 26.0% |
| Tax Agent Bench | 21.8% | 17.1% |
Tests at least two of these models have taken. Bold rows are the core tests.