OpenCodePapers

agents-on-bench-airline

Agents
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeAccuracyModelNameReleaseDate
Trajectory-Level Speculation with Semantic Verification for Tool-Using Agents✓ Link86.0SpecAgent2026-10-15
Rufus-Air: An Open LLM Post-Training Recipe84.0Rufus-Air2026-09-24
Progressive Agent Skill Generation via Reinforcement Learning✓ Link80.0Claude Sonnet 4.5 + Skill-α2026-08-03
PolicyGuide: From Guarding One Action to Guiding the Whole Workflow for Policy-Compliant LLM Agents✓ Link77.5PolicyGuide (GPT-5.4)2026-08-20
Kolibri: A Sovereign European Model on the Pareto Frontier✓ Link76.7Kolibri2026-10-03
Towards General Agentic Intelligence via Environment Scaling✓ Link60.0AgentScaler-30B-A3B2025-09-16
Kimi K2: Open Agentic Intelligence✓ Link56.5Kimi K2 Instruct2025-07-28
NVIDIA Nemotron 3: Efficient and Open Intelligence✓ Link56.25Nemotron 3 Super2025-12-24
MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use45.4MUA-RL-32B2025-08-26
CoVe: Training Interactive Tool-Use Agents via Constraint-Guided Verification43.0CoVe-4B2026-03-02
Check out how to contribute new results. Then edit this file on GitLab or GitHub.