Merge Fusion claims Fable 5-level results at one quarter the cost in a single API call
bigaiguy · x · 2026-07-24
Merge Fusion is being launched as a single API call that sends one prompt to a panel of models, then uses a judge to synthesize a better answer.
The claim is bold: it says Fusion beats Fable 5 outright while costing one quarter as much, and that it also reaches the top score on the DRACO benchmark. The repost frames it as a way to get frontier-level performance at 25% of the cost.
More from Models
- Astra Scores 83% on GauntletBench, First Computer-Use Agent to Beat Human Baseline — ducha_aiki · 2026-09-11
- Kimi K2.8 Preview rolls out: near-K3 coding performance, 1M context for all tiers — teortaxesTex · 2026-09-11
- Looking for a classifier of software engineering task shapes to pick models per task — StewartalsopIII · 2026-09-11
- DeepSeek V4 Pro API to continue after Sept 2026, billing unchanged — teortaxesTex · 2026-09-11
- DeepSeek V4.1 Flash Hits 98% of GPT-6 Astra's Score at 1.4% of the Cost in Third-Party Benchmark — ayushtweetshere · 2026-09-11
- TheZvi Polls: Has Your Coding Model Choice Changed Since Fable 5.1 and Astra? — TheZvi · 2026-09-11