← Back to leaderboard

qwen3:14b

10 GB measured VRAM · 8-12GB tier · tool-gauntlet-v1
Tier 1 — floor 5/5
seed 1 (passed): correct single call
111 tokens · 11.424s
assistant
get_weather({'city': 'Seattle'})
Tier 2 — restraint 5/5
seed 1 (passed): correctly answered directly, no spurious tool call
201 tokens · 2.553s
assistant
The capital of Japan is Tokyo. Since this question does not require weather information, I cannot use the provided tool to answer it. However, I can share this knowledge directly.
Tier 3 — selection 5/5
seed 1 (passed): correctly selected get_time among 3 plausible tools
131 tokens · 1.762s
assistant
get_time({'city': 'Tokyo'})
Tier 4 — extraction 5/5
seed 1 (passed): correctly extracted and typed all fields from messy prose
197 tokens · 2.568s
assistant
book_flight({'origin': 'Chicago', 'destination': 'Denver', 'date': '2026-03-24', 'passengers': 3})
Tier 5 — chaining 5/5
seed 1 (passed): correctly chained: location lookup, then weather for that result
307 tokens · 4.039s
assistant
get_user_location({})
assistant
get_weather({'city': 'Seattle'})
Tier 6 — strict schema 5/5
seed 1 (passed): correctly extracted enum, array, and date under full schema constraints
271 tokens · 3.483s
assistant
create_calendar_event({'title': 'Budget Review', 'date': '2026-04-02', 'priority': 'high', 'attendees': ['Maria', 'James']})