Claude Fable 5.2 High
| Released | 2026-11-09 |
|---|---|
| Price per 1M | $8.00 in · $40.00 out |
| Overall score | 65.9 · rank 15 |
| Context window | 1,000,000 tokens |
| Provider | Anthropic |
| Weights | Proprietary |
| Configuration | High |
Scores
| Dimension | Score | Rank | Benchmarks |
|---|---|---|---|
| Overall: Balanced | 65.9 | 15 | 21 |
| Overall: Coding | 66.1 | 15 | 19 |
| Overall: Reasoning | 67.2 | 18 | 9 |
| Overall: Agentic work | 65.2 | 17 | 18 |
| Overall: Frontend | 65.8 | 11 | 6 |
| Coding | 66.8 | 16 | 5 |
| Agents | 63.8 | 14 | 6 |
| Reasoning | 67.9 | 18 | 7 |
| Math | 69.4 | 3 | 1 |
| Knowledge | 61.7 | 22 | 1 |
| Frontend | 65.3 | 5 | 1 |
| Value vs price | +7.9 | 73 |
Buzz
| Posts on X | About 9,830 a day |
|---|---|
| Mood | 40% positive, 15% negative |
| Hacker News | 173 mentions this week |
| Checked | 2026-11-11 |
- I've been waiting to make my agentic video editing series for a while... It's time. Oh my god fable 5.2 is the breakthrough. It's funny my first instinct is i need to hire 5 editors to use these tools to scale content. That's how much leverage these tools will give creative t…
- THE 10 BEST CODING IDES IN THE AGE OF CODEX AND CLAUDE CODE A coding IDE is no longer only a place you type. OpenAI Codex and Anthropic's Claude Code run as terminal agents that read a repo, edit files, run tests and open pull requests. The editor's job is to host those agents…
- I used Fable 5.2 for this. and it did a good job explaining the product https://t.co/m6OFfUqTKz
Evidence
Coding 66.8 ±3.0
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Code Migration v1.1 | 83.3% | Vals AI | 2026-11-09 |
| CursorBench | 56.9% | Epoch AI | 2026-11-11 |
| SWE-bench Multimodal | 62.3% | Vals AI | 2026-11-09 |
| SciCode | 59.5% | Epoch AI | 2026-11-11 |
| ProgramBench | 19.0% | Vals AI | 2026-11-09 |
Agents 63.8 ±1.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Terminal-Bench 4.0 (Vals run) | 65.2% | Vals AI | 2026-11-09 |
| Terminal-Bench-Science | 55.7% | Vals AI | 2026-11-09 |
| EMB v1.1 (Excel financial modeling) | 77.4% | Vals AI | 2026-11-09 |
| Tax Agent Bench | 32.1% | Vals AI | 2026-11-09 |
| Finance Agent v2.1 | 69.5% | Vals AI | 2026-11-09 |
| HLAB-Vals 1.1 (legal agent) | 5.0% | Vals AI | 2026-11-09 |
Reasoning 67.9 ±1.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ARC-AGI-2 | 90.4% | Epoch AI | 2026-11-11 |
| Extended NYT Connections | 97.3% | Lech Mazur | 2026-11-10 |
| ARC-AGI-2 (ARC Prize verified) | 90.4% | ARC Prize | 2026-11-11 |
| MysteryMechanism | 51.8% | Vals AI | 2026-11-09 |
| CritPt | 32.9% | Epoch AI | 2026-11-11 |
| ARC-AGI-1 (ARC Prize verified) | 97.5% | ARC Prize | 2026-11-11 |
| ARC-AGI-1 | 97.5% | Epoch AI | 2026-11-11 |
| BioMysteryBench | 83.7% | Vals AI | 2026-11-09 |
| ARC-AGI-3 | 97.7% | ARC Prize | 2026-11-11 |
Math 69.4 ±2.7
| Benchmark | Result | Source | Date |
|---|---|---|---|
| ProofBench v1.1 | 100.0% | Vals AI | 2026-11-09 |
Knowledge 61.7 ±6.5
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Legal Research Bench | 46.2% | Vals AI | 2026-11-09 |
Frontend 65.3 ±0.8
| Benchmark | Result | Source | Date |
|---|---|---|---|
| Vibe Code Bench v1.1 | 93.8% | Vals AI | 2026-11-09 |
Results not used in the score
| Benchmark | Result | Source | Why not used |
|---|---|---|---|
| ARC-AGI-3 | 79.3% | ARC Prize | Lower duplicate run on the same benchmark |
Names matched to this model
claude-fable-5-2-high