Model WarsJune 13, 2026via The Decoder
Claude Fable 5 outpaces GPT-5.5 by 13 points on FrontierMath's toughest problems
Why it matters
Anthropic has dramatically closed the reasoning gap with OpenAI. Claude Fable 5's jump from <10% to 88% accuracy on frontier math signals a fundamental shift in who owns AI's reasoning tier.
Key signals
- Claude Fable 5: 88% accuracy on FrontierMath hardest tier
- Claude Opus 4.5: <10% accuracy on same tier (early 2026)
- OpenAI GPT-5.5: 75% accuracy on FrontierMath hardest tier
- 13-point performance gap favoring Anthropic
- Benchmark: FrontierMath toughest problems
- Capability focus: Mathematical reasoning at frontier level
The hook
13 points. That's how much Claude Fable 5 now leads GPT-5.5 on the hardest math problems AI can solve.
Anthropic's Claude Fable 5 hits 88 percent accuracy on the hardest FrontierMath tier, a massive jump from Opus 4.5, which sat below 10 percent in early 2026. OpenAI's GPT-5.5 reaches about 75 percent on the same tier. The pace of improvement in AI math keeps accelerating.