Claude Fable 5.1 vs GPT-6.1 Terra
| Spec | Claude Fable 5.1 | GPT-6.1 Terra |
|---|---|---|
| Respan Index | 72.1 (#3) | 68.9 (#9) |
| Blended price per 1M | $10 | $1 |
| Context window | 1M | 1.1M |
| Input / output per 1M | $5 / $25 | $0.5 / $2.5 |
| Max output | 128K | 128K |
| Input | text, vision | text, vision |
| Released | 2026-09-01 | 2026-10-26 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Claude Fable 5.1 | GPT-6.1 Terra |
|---|---|---|
| Coding | 71.1 Claude Fable 5.1 | 57.9 GPT-6.1 Terra |
| Agents | 73.9 Claude Fable 5.1 | 77.0 GPT-6.1 Terra |
| Reasoning | 78.9 Claude Fable 5.1 | 83.0 GPT-6.1 Terra |
| Knowledge & language | 71.5 Claude Fable 5.1 | 57.4 GPT-6.1 Terra |
| Human preference | 59.8 Claude Fable 5.1 | 57.9 GPT-6.1 Terra |
Benchmarks both report
GPT-6.1 Terra leads on 6 of the 12 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Fable 5.1 | GPT-6.1 Terra |
|---|---|---|
| LMArena Agent (LMArena) | 0.1335 | 0.1057 |
| LMArena WebDev (LMArena) | 1746 | 1673 |
| APEX-Agents (Mercor) | 68.6% | 68.3% |
| EBR-bench (Epoch AI) | 57.1% | 78.1% |
| FrontierMath Tier 4 v2 (Epoch AI) | 87.8% | 92.7% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 90.2% | 90.9% |
| Furniture Assembly (Epoch AI) | 70% | 79.2% |
| Mystery Game Puzzles (Epoch AI) | 58% | 74% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 100% |
| SimpleQA Verified | 70.8% | 57.3% |
| Terminal-Bench 4.0 (Vals AI) | 58.1% | 49.5% |
| Vending-Bench 2 (Andon Labs) | 5421.56 | 9107.46 |
FAQ
Is Claude Fable 5.1 better than GPT-6.1 Terra?
Claude Fable 5.1 scores 72.1 on the Respan Index (#3), ahead of GPT-6.1 Terra at 68.9 (#9). GPT-6.1 Terra leads on 6 of the 12 benchmarks both report.
Which is cheaper, Claude Fable 5.1 or GPT-6.1 Terra?
Claude Fable 5.1 lists at $5 input and $25 output per 1M tokens; GPT-6.1 Terra at $0.5 and $2.5. GPT-6.1 Terra is 10x cheaper per token at list price.
Which has the larger context window?
Claude Fable 5.1 accepts 1M tokens and GPT-6.1 Terra 1.1M tokens.