Claude Fable 5 vs Claude Fable 5.2
| Spec | Claude Fable 5 | Claude Fable 5.2 |
|---|---|---|
| Respan Index | 63.9 (#17) | 80.9 (#1) |
| Blended price per 1M | $20 | $16 |
| Context window | 1M | - |
| Input / output per 1M | $10 / $50 | $8 / $40 |
| Max output | 128K | - |
| Input | text, vision | text |
| Released | 2026-06-09 | 2026-11-09 |
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 | Claude Fable 5.2 |
|---|---|---|
| Coding | 54.3 Claude Fable 5 | 73.0 Claude Fable 5.2 |
| Agents | 67.9 Claude Fable 5 | 85.5 Claude Fable 5.2 |
| Reasoning | 70.0 Claude Fable 5 | 90.0 Claude Fable 5.2 |
| Knowledge & language | 72.4 Claude Fable 5 | 94.0 Claude Fable 5.2 |
| Human preference | 57.5 Claude Fable 5 | 62.5 Claude Fable 5.2 |
Benchmarks both report
Claude Fable 5.2 leads on 15 of the 16 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Fable 5 | Claude Fable 5.2 |
|---|---|---|
| LMArena Agent (LMArena) | 0.0586 | 0.2742 |
| LMArena WebDev (LMArena) | 1626 | 1824 |
| Chess Puzzles (Epoch AI) | 47% | 79% |
| APEX-Agents (Mercor) | 63.6% | 80.1% |
| EBR-bench (Epoch AI) | 39.5% | 90.5% |
| FrontierMath Tier 4 v2 (Epoch AI) | 90.2% | 100% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 87% | 95.1% |
| FrontierSWE V2 (Proximal Labs) | 47% | 69.9% |
| Furniture Assembly (Epoch AI) | 35.8% | 90% |
| GPQA Diamond | 85.9% | 93.9% |
| Mystery Game Puzzles (Epoch AI) | 52% | 90% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 99.7% |
| SimpleQA Verified | 70.7% | 94% |
| Terminal-Bench 4.0 (Vals AI) | 41.4% | 65.2% |
| Vending-Bench 2 (Andon Labs) | 5680.26 | 9628.48 |
| SimpleBench (SimpleBench) | 81.9% | 94.9% |
FAQ
Is Claude Fable 5 better than Claude Fable 5.2?
Claude Fable 5.2 scores 80.9 on the Respan Index (#1), ahead of Claude Fable 5 at 63.9 (#17). Claude Fable 5.2 leads on 15 of the 16 benchmarks both report.
Which is cheaper, Claude Fable 5 or Claude Fable 5.2?
Claude Fable 5 lists at $10 input and $50 output per 1M tokens; Claude Fable 5.2 at $8 and $40. Claude Fable 5.2 is 1.3x cheaper per token at list price.
Compare other models
- vsClaude Fable 5.1 vs Claude Fable 5
- vsClaude Fable 5.2 vs Claude Fable 5.1
- vsGemini 4 Argon vs Claude Fable 5
- vsClaude Fable 5.2 vs Gemini 4 Neon
- vsClaude Fable 5 vs Claude Opus 5
- vsClaude Fable 5 vs GPT-6 Sol
- vsClaude Fable 5 vs GPT-6.2 Sol
- vsClaude Fable 5.2 vs Gemini 4 Carbon
- vsClaude Fable 5.2 vs Claude Opus 5.5