Tencent Hy3 ranks 25th in Agent Arena after 8,000+ live sessions
arena · x · 2026-07-22
Tencent’s Hy3 ranks #25 in Agent Arena
Agent Arena shows Hy3 at #25 overall after 8K+ live agentic sessions.
- -2.2% net improvement overall
- -4.6% confirmed success
- -2.9% praise vs. complaint
- -7.1% steerability
- +2.6% bash recovery
- +0.9% tool hallucination
More from Models
- Benchmark scores drop from 89% to 19% on new evals — how benchmaxxing breaks leaderboard trust — airesearch12 · 2026-09-11
- ChatGPT tells user their question is too hard and to 'accept dumber answers' — phido3000 · 2026-09-11
- Developer Building a Unified Leaderboard of All Model Benchmark Scores — airesearch12 · 2026-09-11
- Rumor claims Kimi faked performance by serving Claude; DeepSeek new model surprises in evals — realsohamparekh · 2026-09-11
- GPT-5.6 writes well but is instantly forgettable, user complains — BasedRaddka · 2026-09-11
- Opus Refuses Protein Research Codebase Over 'Safety' Concerns, Dev Considers Rolling His Own — josephdviviano · 2026-09-11