LithosAI claims fastest Kimi K3.1 Pro inference at 4.7 min per Intelligence Index task
JiaZhihao · x · 2026-11-07
Inference provider LithosAI says it ranks #1 on Artificial Analysis' new time-per-task API benchmark for Kimi K3.1 Pro, at 4.7 minutes per Intelligence Index task — up to 230% faster than the rest of the top five (Stablestyle 5.4, Modal 8.9, Fireworks 21.0, DeepInfra 53.3). The K3.1 Pro weights and LithosAI's Ultra tier launched two days ago. Self-reported provider benchmark, not independent evaluation.
More from Infra
- Dev builds bash script to email Sam Altman daily about his 'RAM idle 95%' claim — IainKay · 2026-11-07
- Quantized Qwen3 beats small full-precision model on a 16GB laptop across 200 tasks — Nir777 · 2026-11-07
- Epoch AI: Huawei's largest China AI data center holds just 7% of Colossus 2's compute — Jsevillamol · 2026-11-07
- Musk says SpaceX will launch StarMind orbital supercomputers from Q3 2027, co-designed with NVIDIA — XFreeze · 2026-11-07
- Netflix builds ontology-driven observability: telemetry, incidents and services as one knowledge graph — JeremyCMorgan · 2026-11-07
- Google buys Crusoe's Wyoming data center site as hyperscaler takeover of neoclouds begins — SumitGup · 2026-11-07