← Back to leaderboard

qwen3:32b

22 GB measured VRAM · 12GB+ tier · tool-gauntlet-v1
Tier 1 — floor 5/5
seed 1 (passed): correct single call
92 tokens · 14.792s
assistant
get_weather({'city': 'Seattle'})
Tier 2 — restraint 5/5
seed 1 (passed): correctly answered directly, no spurious tool call
122 tokens · 3.207s
assistant
The capital of Japan is Tokyo.
Tier 3 — selection 5/5
seed 1 (passed): correctly selected get_time among 3 plausible tools
147 tokens · 3.969s
assistant
get_time({'city': 'Tokyo'})
Tier 4 — extraction 5/5
seed 1 (passed): correctly extracted and typed all fields from messy prose
204 tokens · 5.386s
assistant
book_flight({'destination': 'Denver', 'date': '2026-03-24', 'passengers': 3, 'origin': 'Chicago'})
Tier 5 — chaining 5/5
seed 1 (passed): correctly chained: location lookup, then weather for that result
302 tokens · 8.099s
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
275 tokens · 7.199s
assistant
create_calendar_event({'title': 'Budget Review', 'date': '2026-04-02', 'priority': 'high', 'attendees': ['Maria', 'James']})