Claude Fable 5.2 vs Claude Opus 5
| Spec | Claude Fable 5.2 | Claude Opus 5 |
|---|---|---|
| Respan Index | 80.9 (#1) | 67.1 (#16) |
| Blended price per 1M | $16 | $10 |
| Context window | - | 1M |
| Input / output per 1M | $8 / $40 | $5 / $25 |
| Max output | - | 128K |
| Input | text | text, vision |
| Released | 2026-11-09 | 2026-07-24 |
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 5.2 | Claude Opus 5 |
|---|---|---|
| Coding | 73.0 Claude Fable 5.2 | 64.0 Claude Opus 5 |
| Agents | 85.5 Claude Fable 5.2 | 70.5 Claude Opus 5 |
| Reasoning | 90.0 Claude Fable 5.2 | 73.9 Claude Opus 5 |
| Knowledge & language | 94.0 Claude Fable 5.2 | 61.1 Claude Opus 5 |
| Human preference | 62.5 Claude Fable 5.2 | 59.0 Claude Opus 5 |
Benchmarks both report
Claude Fable 5.2 leads on 15 of the 17 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Fable 5.2 | Claude Opus 5 |
|---|---|---|
| LMArena Agent (LMArena) | 0.2742 | 0.0626 |
| LMArena WebDev (LMArena) | 1824 | 1692 |
| Vending-Bench 2 (Andon Labs) | 9628.48 | 11181.87 |
| APEX-Agents (Mercor) | 80.1% | 65.8% |
| Chess Puzzles (Epoch AI) | 79% | 43% |
| EBR-bench (Epoch AI) | 90.5% | 45.7% |
| FrontierMath Tier 4 v2 (Epoch AI) | 100% | 73.2% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 95.1% | 85.6% |
| FrontierSWE V2 (Proximal Labs) | 69.9% | 52% |
| Furniture Assembly (Epoch AI) | 90% | 60.8% |
| GPQA Diamond | 93.9% | 93.9% |
| Mystery Game Puzzles (Epoch AI) | 90% | 59% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 99.7% | 98.9% |
| SimpleBench (SimpleBench) | 94.9% | 80.6% |
| SimpleQA Verified | 94% | 59.9% |
| Terminal-Bench 4.0 (Vals AI) | 65.2% | 53.5% |
| Terminal-Bench Science 0.1 | 74.6% | 29% |
FAQ
Is Claude Fable 5.2 better than Claude Opus 5?
Claude Fable 5.2 scores 80.9 on the Respan Index (#1), ahead of Claude Opus 5 at 67.1 (#16). Claude Fable 5.2 leads on 15 of the 17 benchmarks both report.
Which is cheaper, Claude Fable 5.2 or Claude Opus 5?
Claude Fable 5.2 lists at $8 input and $40 output per 1M tokens; Claude Opus 5 at $5 and $25. Claude Opus 5 is 1.6x cheaper per token at list price.
Compare other models
- vsClaude Fable 5.2 vs Claude Fable 5.1
- vsClaude Opus 5 vs Claude Opus 4.8
- vsClaude Opus 5.5 vs Claude Opus 5
- vsGemini 4 Argon vs Claude Opus 5
- vsClaude Opus 5 vs Gemini 3.8 Flash
- vsClaude Fable 5.2 vs Gemini 4 Neon
- vsClaude Fable 5.2 vs Gemini 4 Carbon
- vsClaude Fable 5.2 vs Claude Opus 5.5
- vsClaude Opus 5 vs GPT-6.2 Sol
- vsClaude Opus 5 vs Claude Fable 5
- vsClaude Opus 5 vs GPT-6.1 Terra