Tech
Dex OkaforOn assignment
Not verified yet. Dex Okafor is reporting this story for the newsroom. Until then, this is gathered automatically from the outlets below.
Claude Fable 5.2 Scores 65 on Artificial Analysis, Highest So Far
Dex Okafor is reporting this story
What's new
- artificialanalysis.ai is now reporting this
How Claude Fable 5.2 compares
Full scoreboard →AnthropicNew
Claude Fable 5.2
- Released Nov. 9, 2026
- Paid API
- $8 in / $40 out per million tokens
- Reads up to 1M tokens at once
Not enough tests yet for an overall score. The results so far:
| Test | Claude Fable 5.2 | GPT-6 AstraOpenAI | Gemini 4 ArgonGoogle DeepMind | Muse WonderMeta AI | Claude Opus 5.5Same lab, earlier |
|---|---|---|---|---|---|
| OverallEpoch Capabilities Index | —Not tested yet | 169.1 (best here) | 166.5 | 162.0 | 168.4 |
| ScienceGPQA Diamond | 93.9% | 95.8% | 96.4% (best here) | —Not tested yet | 90.6% |
| MathFrontierMath, Tiers 1–3 | 95.1% (best here) | 93.7% | 86% | 82.1% | 91.2% |
| PuzzlesARC-AGI-2 | 93.8% | 95% (best here) | 91.3% | —Not tested yet | 93.3% |
| FactsSimpleQA Verified | 94% (best here) | 75.6% | 76% | —Not tested yet | 72.2% |
| Priceper million tokens | $8 in / $40 out | $10 in / $50 out | $2 in / $10 out | $4 in / $20 out | $4 in / $20 out |
No published result yet for Claude Fable 5.2 on: Coding, Science code, Office work, Physics.
Scores: Epoch AI Benchmarking Hub (CC BY 4.0), each the model’s best result across the settings tested, as of Nov. 9, 2026. Release dates and prices: OpenRouter. The paper runs none of these tests.
