Apodex 1.1 achieved 97.8% pass rate on APEX-Agents-AA in an independent evaluation by Artificial Analysis, reaching a performance level comparable to Claude Opus 4.6 and GPT-5.4.
Public source
Publisher name
Public post
Built to deliver real-world professional work. ๐ฆ Apodex 1.1 achieved ๐ฏ๐ญ.๐ฎ% ๐ฃ๐ฎ๐๐@๐ญ on APEX-Agents-AA in an independent evaluation by Artificial Analysis, reachinโฆ
Company
Apodex
The World's First Self-Evolving Heavy-Duty Solver
- Industry
- Technology, Information and Internet
- Location
- Redwood, US
- Company size
- 51โ200 employees
About Apodex
Apodex is an enhanced open-source AI for deep research. Unlike simple chatbots, Apodex is the AI research partner that tackles complex challenges through systematic reasoning, real-time web exploration, and evidence-based verification.
See moreLatest activity
Latest activity from Apodex
7 signals
Research & Knowledge
Apodex published the Apodex 1.1 paper and its Agent Team results on HLE, GDPval, and FrontierScience-Research to Papers with Code.
Research & Knowledge
Apodex 1.1 (Agent Team) achieved a 63.3% pass rate across 60 tasks on FrontierScience-Research with a rubric score of โฅ7/10 counted as a pass.
Research & Knowledge
Apodex published a paper titled TRACES evaluating the discovery process for rigorous and evidence-grounded reasoning
Discover more
Similar signals
Similar public activity from other companies.
Products & Services
Artificial Analysis
Artificial Analysis reported that Claude Fable 5.1 and GPT-6 Astra lead the Intelligence Index with scores of 53 and 53 respectively, followed by Claude Opus 5 at 51 and GPT-5.6 Sol at 47.
Products & Services
Opper AI
Opper AI launched the new model GPT 6 Astra with benchmarks showing FrontierMath Tier 4 at 97.6%, ARC-AGI-3 at 99.9%, ExploitBench at 100%, OSWorld 2.0 at 72.6%, and Terminal-Bench 4.0 at 57.9%
Products & Services
Mirai Labs
Mirai Labs outperforms MTPLX and llama.cpp by almost 2x and over 3x at comparable quantization levels on Apple M5 chips.
Products & Services
Arena
Arena announced that GPT-6 Astra (Max) debuts at #2 overall with a 12.5% net improvement across 8.9K real-world agentic sessions.
Products & Services
Giskard