arxiv:2601.11518
Jonathan Roberts PRO
jonathan-roberts1
AI & ML interests
VLMs, LLMs, LMMs
Recent Activity
upvoted a paper about 1 month ago
Beyond Outcomes: Transparent Assessment of LLM Reasoning in Games authored
a paper
about 1 month ago
Humanity's Last Exam authored
a paper
about 1 month ago
Beyond Outcomes: Transparent Assessment of LLM Reasoning in Games Organizations
models 0
None public yet
datasets 35
jonathan-roberts1/GRAB-lite
Viewer
• Updated
• 500 • 30
jonathan-roberts1/GRAB
Viewer
• Updated
• 2.17k • 37 • 4
jonathan-roberts1/GRAB-real
Viewer
• Updated
• 1.11k • 55
jonathan-roberts1/zerobench
Viewer
• Updated
• 434 • 705 • 29
jonathan-roberts1/zerobench_no_answers
Viewer
• Updated
• 434 • 12
jonathan-roberts1/SciFIBench
Viewer
• Updated
• 2k • 69 • 4
jonathan-roberts1/needle-threading
Viewer
• Updated
• 10.9k • 70 • 3
jonathan-roberts1/SATIN
Updated
• 72 • 8
jonathan-roberts1/EuroSAT
Viewer
• Updated
• 27k • 131 • 3
jonathan-roberts1/AID_MultiLabel
Viewer
• Updated
• 3k • 31