Alex Firsov retweeted
Fortytwo Engine more than doubled Qwen3.8-27B’s score on @scaling01's LisanBench
Standalone BF16: 2,452
Fortytwo Engine swarm: 5,197 (+112%)
LisanBench tests strategic planning, memory and constraint following: build the longest word chain possible using single-letter edits, dictionary words and no repeats.
Both runs: 50 starting words × 3 trials, temperature 1.0, 100k-token cap, xhigh reasoning, leaderboard scoring.
What improved:
• Repetition loops observed in the standalone run; none observed on Engine
• Higher mean scores on 40/50 starting words
• Mean link validity: 92.2% → 97.1%
• Fully valid chains: 5.6% → 22.9% of recorded answers
• Answers after retries: 72/150 → 140/150
Against the October 16 leaderboard, these scores would place 28th → 14th, putting Qwen3.8-27B on Fortytwo Engine between GPT 5.4 (medium) and DeepSeek V3.2 Speciale.
These are our runs, not official leaderboard entries.
Alex Firsov retweeted
Qwen3.8-27B by @Alibaba_Qwen is now live on Fortytwo Engine.
Same model, with better answers:
• 24.7% fewer tokens per run
• DeepSWE: +13% accuracy
• GDP.pdf: +11.4% accuracy
• Same per-token price and speed
Test it on your own tasks:
engine.fortytwo.network
Alex Firsov retweeted
Swarm Inference 🤖
Introducing Fortytwo Engine
An inference API that runs open-weight models through Swarm Inference
• 7% higher scores on average vs. the base model
• Nearly 25% fewer tokens per task
• Same per-token price and speed
• Private by default
First model: Qwen3.8-27B
Try it: engine.fortytwo.network
Alex Firsov retweeted
try it
Introducing Fortytwo Engine
An inference API that runs open-weight models through Swarm Inference
• 7% higher scores on average vs. the base model
• Nearly 25% fewer tokens per task
• Same per-token price and speed
• Private by default
First model: Qwen3.8-27B
Try it: engine.fortytwo.network
Alex Firsov retweeted
Introducing Fortytwo Engine
An inference API that runs open-weight models through Swarm Inference
• 7% higher scores on average vs. the base model
• Nearly 25% fewer tokens per task
• Same per-token price and speed
• Private by default
First model: Qwen3.8-27B
Try it: engine.fortytwo.network
Alex Firsov retweeted
The Liquid Inference router network is growing quickly. We now have 28 verified companies serving >1000 models, offering capacity dynamically and updating quotes in real-time. Average time for providers to onboard and integrate models is 3 hours, full verification within a day.
Alex Firsov retweeted
while you wait for the big moment, you can always check out what @fortytwo is capable of here: showcase.fortytwo.network
Alex Firsov retweeted
Excited to be joining Hub71’s Cohort 18 in Abu Dhabi!
We’re working closely with new design partners across robotics, engineering, aviation, and supply chains to scale swarm intelligence for real-world domains.
The future of innovation starts here ✨
We're proud to welcome Cohort18 to Hub71, a new group of ambitious founders building solutions that will shape industries, solve global challenges, and drive the next wave of technological advancement.
Read more here: go.hub71.com/cohort18
#Hub71 #Cohort18 #InAbuDhabi
@persium_aq I @digistain I @matregenix I @LifeRubedo
Alex Firsov retweeted
The self-evolving network of AI models powering AGI for everyone
fortytwo.network/
Alex Firsov retweeted
Decentralized AI is our industry's response to increasingly centralized SuperLabs
Alex Firsov retweeted
We just updated Fortytwo Prime.
Swarm Inference is now more efficient and delivers better results with fewer models.
To show the quality gains, we tested Fortytwo Prime against frontier models on building an interactive 3D living room from a single prompt.
Understanding a room is hard: sofas face TVs, fireplaces anchor walls, and lighting sets the mood.
Results breakdown ↓
Alex Firsov retweeted
We are open-sourcing x402Escrow
An escrow extension for the x402 payment protocol that enables pay-per-token billing for AI inference where costs are unknown at request time
MIT licensed: github.com/Fortytwo-Network/…
Alex Firsov retweeted
fortytwo’s Q1 in simple terms:
> they rolled out new infrastructure (relay nodes) to scale the network, launched swarm-based AI where agents can earn and spend rewards, and saw strong traction with their coding model (20k+ downloads).
> they also introduced a higher-accuracy inference system (prime) and open-sourced a flexible escrow tool for pay-per-use AI.
> overall, they’re pushing toward a more scalable, agent-driven AI network with better reliability and monetization.
G42
Q1 at Fortytwo
→ Relay Nodes launched: a community-operated node type that scales the network by letting GPU nodes connect without requiring public IPs. First operators onboarded.
→ Swarm inference for AI agents released: agents now participate in the Swarm directly. They earn rewards by answering queries and spend them to ask their own.
→ Fortytwo’s Strand-Rust-Coder-14B-v1 coding model trained on swarm data crossed 20,000 downloads on Hugging Face.
→ Fortytwo Prime launched: swarm inference via MCP. Frontier models run in parallel, rank each other, and return one answer. A service for agents that can't afford to be wrong.
→ x402Escrow open-sourced: an escrow extension for x402 that enables pay-per-token settlement where costs are unknown in advance.
More to come in Q2. Links below.
