← Leaderboard · task_4658b8d0beb8b0254a80a5f0
S-EQ07-XX-N · Breakdown 60D — plus two more hidden conditions — count of matchesMarket & SignalSignal detectionEquityNUMBERHARDpublic example

Question

Fundamental ratios are not served as fields: rebuild each one from the raw SEC facts (get_equity_financials) exactly as defined in list_metrics.compute_yourself, using the latest filing at or before the data cutoff; a company whose filings lack the needed facts is out of scope. A breakdown means today's close is below the lowest low of the previous 60 complete sessions (split-adjusted). 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 $10B, 20-day average dollar volume greater than $50M, sector equal to Real Estate, a close below the previous 60-day low, net margin (latest fiscal year) greater than 10%, turnover ratio greater than 0.002%. Scope: only entities with a known value for 20-day average dollar volume, sector, a close below the previous 60-day low, net margin (latest fiscal year), turnover ratio in the snapshot; entities lacking any of them are out of scope and must not be returned. How many entities match ALL of the conditions above? Answer with the integer count (0 if none). Filing-version policy: every financial value is taken from the LATEST filing accepted by the SEC at or before the data cutoff that reports the requested period. If a later filing (before the cutoff) restates an earlier period, the restated value is the answer; the original filing's value is not. A fiscal-year value is taken only from an annual report (10-K / 20-F / 40-F, including amendments) — a quarterly report never supplies an annual value. 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

10 (10 count)

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)

XiaomiMiMo
xiaomi/mimo-v2.6-flash
100.0strict pass
latency 579.0s · cost $0.0097
tool calls 10
Model answer
10 (10 count)
Why this score
Expected 10, got 10 (0% off) — within tolerance.
expected 10 · got 10 · error 0.0% · within tolerance
Tool calls (10)
list_metrics → search_equities → get_market_history → run_calculation → get_equity_financials → run_calculation → get_equity_financials → get_equity_financials → run_calculation → submit_answer
DeepSeek
deepseek/deepseek-v4.1-flash
100.0strict pass
latency 52.1s · cost $0.1334
tool calls 11
Model answer
10 (10 count)
Why this score
Expected 10, got 10 (0% off) — within tolerance.
expected 10 · got 10 · error 0.0% · within tolerance
Tool calls (11)
list_metrics → search_equities → get_market_history → get_equity_financials → run_calculation → run_calculation → run_calculation✗ → run_calculation✗ → run_calculation → run_calculation → submit_answer
Anthropic
Claude Opus 5.5
100.0strict pass
latency 24.2s · cost $0.5769
tool calls 6
Model answer
10 (10 count)
Why this score
Expected 10, got 10 (0% off) — within tolerance.
expected 10 · got 10 · error 0.0% · within tolerance
Tool calls (6)
list_metrics → search_equities → get_market_history → run_calculation → get_equity_financials → submit_answer
Qwen
qwen/qwen3.8-flash
100.0strict pass
latency 91.7s · cost $0.0131
tool calls 7
Model answer
10 (10 ratio)
Why this score
Expected 10, got 10 (0% off) — within tolerance.
expected 10 · got 10 · error 0.0% · within tolerance
Tool calls (7)
list_metrics → search_equities → get_market_history → get_equity_financials → run_calculation → run_calculation → submit_answer
Gemini
google/gemini-3.8-flash
100.0strict pass
latency 78.6s · cost $0.1073
tool calls 14
Model answer
10 (10 ratio)
Why this score
Expected 10, got 10 (0% off) — within tolerance.
expected 10 · got 10 · error 0.0% · within tolerance
Tool calls (14)
list_metrics → search_equities → get_equity_metrics → get_market_history → run_calculation → run_calculation → get_equity_financials → get_equity_financials → get_equity_financials → get_equity_financials → run_calculation → run_calculation → search_equities → submit_answer
Z.ai
z-ai/glm-5.3-flash
100.0strict pass
latency 223.9s · cost $0.0116
tool calls 6
Model answer
10 (10 ratio)
Why this score
Expected 10, got 10 (0% off) — within tolerance.
expected 10 · got 10 · error 0.0% · within tolerance
Tool calls (6)
list_metrics → search_equities → get_market_history → get_equity_financials → run_calculation → submit_answer
Grok
x-ai/grok-4.7
100.0strict pass
latency 40.9s · cost $0.3286
tool calls 12
Model answer
10 (10 shares)
Why this score
Expected 10, got 10 (0% off) — within tolerance.
expected 10 · got 10 · error 0.0% · within tolerance
Tool calls (12)
list_metrics → search_equities → get_market_history → get_equity_financials → run_calculation → run_calculation → get_equity_financials → get_equity_financials → get_equity_financials → run_calculation → get_equity_financials → submit_answer
Minimax
MiniMax M3
0.0not a strict pass
latency 106.3s · cost $0.0157
tool calls 7
Model answer
3 (3 count)
Why this score
Expected 10, got 3 (70% off) — outside tolerance.
expected 10 · got 3 · error 70.0% · outside tolerance
Tool calls (7)
list_metrics → search_equities → get_market_history → run_calculation → get_equity_financials → run_calculation → submit_answer