← Leaderboard · task_4ba044eab2c61c4434c73cc0
S-EQ15-M · Gap + Volume — median of a rebuilt metric over the matchesMarket & SignalSignal detectionEquityNUMBERHARDpublic example
Question
Gap = today's open / yesterday's close − 1; relative volume = today's volume / 20-day average volume. Find US-listed common equities (instruments without a reported market cap — warrants, units, rights, preferred series, notes — are not in the universe) with market cap greater than $1B, opening gap greater than 3%, relative volume (today / 20-day average) greater than 2. Scope: only entities with a known value for opening gap, relative volume (today / 20-day average) in the snapshot; entities lacking any of them are out of scope and must not be returned. Across ALL entities that match the conditions above, what is the median Opening gap (Current session open relative to the previous close, minus one.)? Median = the middle value, or the mean of the two middle values for an even count. Answer as a decimal ratio (0.25 for 25%).
Rebuild policy: metrics that are not served as fields (fundamental ratios, growth rates, valuation, technical signals) must be recomputed by you from the raw facts and daily bars the tools serve, following the definitions in list_metrics.compute_yourself to the letter (period selection, latest-filing copy, quarter arithmetic); do the arithmetic with run_calculation over the fetched data. The reference answer was computed from the same facts by the same definitions.
Data as of 2026-09-10 · grader numeric_tolerance
Expected / gold answer
0.03532 (0.035322777101096214 ratio)Computed by code from the frozen snapshot and verified by an independent recomputation before the batch was frozen. No model ever saw it.
Model answers (8)
Model answer
0.03532 (0.035322777101096214 ratio)
Why this score
Expected 0.03532, got 0.03532 (0% off) — within tolerance.
expected 0.035322777101096214 · got 0.035322777101096214 · error 0.0% · within tolerance
Tool calls (31)
list_metrics → search_equities → get_market_history → get_market_history → search_equities → search_equities → search_equities → search_equities → search_equities → get_market_history → search_equities → search_equities → run_calculation → search_equities → search_equities → search_equities → search_equities → search_equities → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → get_equity_metrics → get_equity_metrics → run_calculation → run_calculation → get_market_history → get_equity_metrics → run_calculation → submit_answer
Model answer
0.03532 (0.035322777101096214 ratio)
Why this score
Expected 0.03532, got 0.03532 (0% off) — within tolerance.
expected 0.035322777101096214 · got 0.035322777101096214 · error 0.0% · within tolerance
Tool calls (25)
list_metrics → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → run_calculation → get_market_history → run_calculation → get_market_history → get_market_history → get_market_history → get_market_history → run_calculation → run_calculation → run_calculation → submit_answer
Model answer
0.03532 (0.035322777 ratio)
Why this score
Expected 0.03532, got 0.03532 (0% off) — within tolerance.
expected 0.035322777101096214 · got 0.035322777 · error 0.0% · within tolerance
Tool calls (22)
list_metrics → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → run_calculation → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → run_calculation → submit_answer
Model answer
0.03532 (0.035322777101096214 ratio)
Why this score
Expected 0.03532, got 0.03532 (0% off) — within tolerance.
expected 0.035322777101096214 · got 0.035322777101096214 · error 0.0% · within tolerance
Tool calls (23)
list_metrics → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → run_calculation → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → run_calculation → run_calculation → submit_answer
Model answer
0.03532 (0.0353227771010962 ratio)
Why this score
Expected 0.03532, got 0.03532 (0% off) — within tolerance.
expected 0.035322777101096214 · got 0.0353227771010962 · error 0.0% · within tolerance
Tool calls (39)
list_metrics → search_equities → search_equities → get_market_history → run_calculation → search_equities → search_equities → get_market_history → run_calculation → search_equities → run_calculation → search_equities → run_calculation → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → run_calculation → run_calculation → run_calculation → run_calculation → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → run_calculation → run_calculation → get_market_history → get_equity_metrics → run_calculation → submit_answer
Model answer
0.03532 (0.035322777101096214 ratio)
Why this score
Expected 0.03532, got 0.03532 (0% off) — within tolerance.
expected 0.035322777101096214 · got 0.035322777101096214 · error 0.0% · within tolerance
Tool calls (25)
list_metrics → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → run_calculation → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → run_calculation → get_equity_metrics → get_market_history → submit_answer
Model answer
0.03532 (0.035322777101096214 ratio)
Why this score
Expected 0.03532, got 0.03532 (0% off) — within tolerance.
expected 0.035322777101096214 · got 0.035322777101096214 · error 0.0% · within tolerance
Tool calls (30)
list_metrics → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → get_market_history → run_calculation → run_calculation → submit_answer
MiniMax M3
tool calls 33
0.0not a strict pass
budget exhausted → forced answer
latency 774.1s · cost $0.3292tool calls 33
Model answer
0.04240 (0.042400568181818254 ratio)
Why this score
Budget ran out and the answer was forced. Expected 0.03532, got 0.04240 (20% off) — outside tolerance.
expected 0.035322777101096214 · got 0.042400568181818254 · error 20.0% · outside tolerance
Tool calls (33)
list_metrics → search_equities → run_calculation → search_equities → search_equities → search_equities → search_equities → search_equities → run_calculation → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → search_equities → run_calculation → get_market_history → get_market_history → get_market_history → get_market_history → get_equity_metrics → get_equity_metrics → run_calculation → get_equity_metrics → get_equity_metrics → get_equity_metrics → run_calculation → run_calculation → run_calculation → get_equity_metrics → get_equity_metrics → submit_answer