Claude Fable 5 vs GPT-5.5 vs Gemini 3.1 Pro: Who Leads Now?

Chronological Source Flow
Back

AI Fusion Summary

Claude Fable 5, released June 9, 2026, leads SWE-Bench Pro with 80.3 percent, surpassing GPT-5.5 and Gemini 3.1 Pro. Anthropic introduced a two-tier safety design for risky prompts. Meanwhile, flash-tier coding models compete: Gemini 3.5 Flash leads agentic benchmarks with a 1M-token context window, Claude Haiku 4.5 offers the lowest output cost, and Microsoft's MAI-Code-1-Flash, available via GitHub Copilot, outperforms both on SWE-Bench Pro with a 51.2 percent score.
Community Comments
Loading updates...
0