Nace AI’s Drex for Search reports 92.05% on BrowseComp-Plus with GPT-5, using only 12.6 search calls per question.
Performance: 66.7% average on 5 DNA benchmarks, best of every open model tested (self-reported). Best: 74.9% on BioReason ...
TokenGate adds learned token pruning to existing LLMs, cutting long-context prefill time up to 11.3x and memory 3.4x.
Anthropic sandbox-runtime gives AI agents OS-level sandboxes without containers; Anthropic reports 84% fewer Claude Code ...
Microsoft open-sourced Agensh, a decentralized multi-agent harness that scales to 1,024 agents, lifting Pandoc pass rates to ...
Moonshot AI’s Kimi K3.1 Pro is a 2.8T-parameter open-weight model with 1M context, scoring 65.7% on Terminal-Bench 4.0.
The research report shows a Reachy Mini robot running on a Jetson Orin Nano 8GB. In that demo, Cosmos 3 Edge handles vision ...
Recursive Flint is a 40B MoE local coding model with 2.5B active parameters, scoring 74.2% on SWE-bench Verified.
TinyFish's agentic search architecture runs 7 phases; Search and Fetch scored 79.0% grounded completion at $0.050 per task.
Gradium Phonon is a 31M-parameter on-device TTS model under Apache 2.0, reporting 1.70% WER on hard English sentences.
Vercel open-sourced durable-harness, an Apache-2.0 package that makes Pi, OpenCode, Claude Code and Codex agent sessions ...
Perplexity’s JOLT trains one model as teacher and student, matching GRPO’s MATH accuracy with 6.5x fewer training tokens.
Results that may be inaccessible to you are currently showing.
Hide inaccessible results