Fortytwo Engine boosts Qwen3.8-27B accuracy 7% and cuts tokens 25% via Swarm Inference
rohanpaul_ai · x · 2026-10-16
Fortytwo launched Fortytwo Engine, an inference API that runs open-weight models through Swarm Inference, claiming better answers without changing models.
- First model: Qwen3.8-27B, averaging +7% accuracy over the base model — DeepSWE 42.2→47.8 (+13.3%), GPQA-Diamond 90.9→95.1, LiveCodeBench v6 80.2→84.1
- Token efficiency: across 450 DeepSWE runs, average tokens per run dropped 24.7% (16.3M→12.3M)
- Same per-token pricing as the base model ($0.425/MTok input, $2.55/MTok output) with comparable speed and a 262K context window
- Private by default with zero data retention; supports function calling, structured outputs, image input, and streaming
More from Infra
- Nvidia MGX Power Rack session packed to standing room on final OCP day — firstadopter · 2026-10-16
- Intel hosts 816B-param Muse Spark Open air-cooled on four 160GB D-series GPUs — BenBajarin · 2026-10-16
- Filecoin marks 6 years of mainnet, pivots storage stack to AI workloads with new S3 offering — juanbenet · 2026-10-16
- PrismML ships Bonsai 2 ternary models: 9B fits in 2GB for local AI — gajesh · 2026-10-16
- Artificial Analysis to add 4-bit formats and Splash Metal engine to agent benchmark — ArtificialAnlys · 2026-10-16
- NVIDIA RTX Spark laptop runs local agent workload 2x faster than MacBook Pro M5 Pro — ArtificialAnlys · 2026-10-16