Up to four models
Claude Fable 5.2 vs GPT-6.1 Terra
On the index (GPT-4 = 100), Claude Fable 5.2 scores 202 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 Fable 5.2
202185–218
WeightsClosed
ReleasedNov 2026
Price in / out$8.0 / $40
Context1M
Core tests taken4 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 Fable 5.2 leads GPT-6.1 Terra by 15 points, ahead on 4 of 4 shared core tests, at 8.0× the price.
Test by testthird-party results
Claude Fable 5.2GPT-6.1 Terra
Every result as a table
| Test | Claude Fable 5.2 | GPT-6.1 Terra |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 96.0% | 94.3% |
| EBR-bench | 90.5% | 78.1% |
| SimpleBench | 94.9% | 72.2% |
| SimpleQA Verified | 94.0% | 57.3% |
| Maths | ||
| FrontierMath (tiers 1-3) | 95.1% | 90.9% |
| AIME-style maths (OTIS mock) | 99.7% | 100.0% |
| FrontierMath (tier 4) | 100.0% | 92.7% |
| Coding | ||
| Terminal-Bench 4.0 | 65.1% | 49.5% |
| Vibe Code Bench v1.1 | 93.8% | 84.0% |
| Agents | ||
| APEX-Agents | 80.1% | 68.3% |
| Furniture assembly | 90.0% | 79.2% |
| Mystery game puzzles | 90.0% | 74.0% |
| Professional work | ||
| HLAB-Vals-1.1 | 5.0% | 1.7% |
| Legal Research Bench | 46.2% | 26.0% |
| Tax Agent Bench | 32.1% | 17.1% |
Tests at least two of these models have taken. Bold rows are the core tests.