← Leaderboard · task_0ca60928e42dc07d86cd1b7b
S-EQ18-A · Low-Drawdown Leader — count, mean and median of a rebuilt metric over the matchesMarket & SignalScreeningEquitySTRUCTURED_FIELDSHARDpublic example

Question

120-session return = adjusted close today / adjusted close 120 sessions ago − 1; max drawdown = largest peak-to-trough decline of the adjusted close over the same 120 sessions. 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 $2B, 20-day average dollar volume greater than $50M, sector equal to Health Care, 120-day return greater than 20%, 120-day max drawdown less than 10%. Scope: only entities with a known value for 20-day average dollar volume, sector, 120-day return, 120-day max drawdown in the snapshot; entities lacking any of them are out of scope and must not be returned. For the set of ALL entities that match the conditions above, report three numbers: count = how many match; mean = the arithmetic mean of 120-session return (Split-adjusted close now divided by the close 120 trading sessions ago, minus one.) across them; median = its median (middle value, or the mean of the two middle values for an even count). Give mean and median as a decimal ratio (0.25 for 25%). Every matching entity's value must be rebuilt exactly — one wrong value moves the mean. 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 structured_fields

Expected / gold answer

count8 (8 count)
mean0.3668 (0.36680734461325704 ratio)
median0.3245 (0.3245383709968629 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)

XiaomiMiMo
xiaomi/mimo-v2.6-flash
100.0strict pass
latency 119.2s · cost $0.0097
tool calls 6
Model answer
count8 (8)
mean0.3668 (0.36680734461325704)
median0.3245 (0.3245383709968629)
Why this score
All 3 fields correct.
passed weight 3 / 3
fieldweightmust passresultdetail
count1✓
expected 8 · got 8 · error 0.0% · within tolerance
mean1✓
expected 0.36680734461325704 · got 0.36680734461325704 · error 0.0% · within tolerance
median1✓
expected 0.3245383709968629 · got 0.3245383709968629 · error 0.0% · within tolerance
Tool calls (6)
list_metrics → search_equities → get_market_history → run_calculation → run_calculation → submit_answer
DeepSeek
deepseek/deepseek-v4.1-flash
100.0strict pass
latency 30.6s · cost $0.0430
tool calls 6
Model answer
count8 (8)
mean0.3668 (0.36680734461325704)
median0.3245 (0.3245383709968629)
Why this score
All 3 fields correct.
passed weight 3 / 3
fieldweightmust passresultdetail
count1✓
expected 8 · got 8 · error 0.0% · within tolerance
mean1✓
expected 0.36680734461325704 · got 0.36680734461325704 · error 0.0% · within tolerance
median1✓
expected 0.3245383709968629 · got 0.3245383709968629 · error 0.0% · within tolerance
Tool calls (6)
list_metrics → search_equities → get_market_history → run_calculation → run_calculation → submit_answer
Anthropic
Claude Opus 5.5
100.0strict pass
latency 29.2s · cost $0.5568
tool calls 5
Model answer
count8 (8)
mean0.3668 (0.36680734461325704)
median0.3245 (0.3245383709968629)
Why this score
All 3 fields correct.
passed weight 3 / 3
fieldweightmust passresultdetail
count1✓
expected 8 · got 8 · error 0.0% · within tolerance
mean1✓
expected 0.36680734461325704 · got 0.36680734461325704 · error 0.0% · within tolerance
median1✓
expected 0.3245383709968629 · got 0.3245383709968629 · error 0.0% · within tolerance
Tool calls (5)
list_metrics → search_equities → get_market_history → run_calculation → submit_answer
Qwen
qwen/qwen3.8-flash
100.0strict pass
latency 145.9s · cost $0.0145
tool calls 10
Model answer
count8 (8)
mean0.3668 (0.36680734461325704)
median0.3245 (0.3245383709968629)
Why this score
All 3 fields correct.
passed weight 3 / 3
fieldweightmust passresultdetail
count1✓
expected 8 · got 8 · error 0.0% · within tolerance
mean1✓
expected 0.36680734461325704 · got 0.36680734461325704 · error 0.0% · within tolerance
median1✓
expected 0.3245383709968629 · got 0.3245383709968629 · error 0.0% · within tolerance
Tool calls (10)
list_metrics → search_equities → get_market_history → run_calculation → run_calculation → get_market_history → run_calculation → get_market_history → run_calculation → submit_answer
Gemini
google/gemini-3.8-flash
100.0strict pass
latency 52.4s · cost $0.0961
tool calls 12
Model answer
mean0.3668 (0.366807344613257)
count8 (8)
median0.3245 (0.324538370996863)
Why this score
All 3 fields correct.
passed weight 3 / 3
fieldweightmust passresultdetail
count1✓
expected 8 · got 8 · error 0.0% · within tolerance
mean1✓
expected 0.36680734461325704 · got 0.366807344613257 · error 0.0% · within tolerance
median1✓
expected 0.3245383709968629 · got 0.324538370996863 · error 0.0% · within tolerance
Tool calls (12)
list_metrics → search_equities → run_calculation → get_market_history → run_calculation → run_calculation → run_calculation → run_calculation → run_calculation → run_calculation → run_calculation → submit_answer
Z.ai
z-ai/glm-5.3-flash
100.0strict pass
latency 172.5s · cost $0.0099
tool calls 6
Model answer
count8 (8)
mean0.3668 (0.36680734461325704)
median0.3245 (0.3245383709968629)
Why this score
All 3 fields correct.
passed weight 3 / 3
fieldweightmust passresultdetail
count1✓
expected 8 · got 8 · error 0.0% · within tolerance
mean1✓
expected 0.36680734461325704 · got 0.36680734461325704 · error 0.0% · within tolerance
median1✓
expected 0.3245383709968629 · got 0.3245383709968629 · error 0.0% · within tolerance
Tool calls (6)
list_metrics → search_equities → get_market_history → run_calculation → run_calculation → submit_answer
Grok
x-ai/grok-4.7
100.0strict pass
latency 93.9s · cost $0.1691
tool calls 6
Model answer
count8 (8)
mean0.3668 (0.36680734461325704)
median0.3245 (0.3245383709968629)
Why this score
All 3 fields correct.
passed weight 3 / 3
fieldweightmust passresultdetail
count1✓
expected 8 · got 8 · error 0.0% · within tolerance
mean1✓
expected 0.36680734461325704 · got 0.36680734461325704 · error 0.0% · within tolerance
median1✓
expected 0.3245383709968629 · got 0.3245383709968629 · error 0.0% · within tolerance
Tool calls (6)
list_metrics → search_equities → get_market_history → run_calculation → run_calculation → submit_answer
Minimax
MiniMax M3
33.3not a strict pass
latency 24.5s · cost $0.0217
tool calls 7
Model answer
count8 (8)
mean0.3628 (0.36275830560717914)
median0.3346 (0.3345908861843657)
Why this score
1 of 3 fields correct; wrong: mean, median.
passed weight 1 / 3
fieldweightmust passresultdetail
count1✓
expected 8 · got 8 · error 0.0% · within tolerance
mean1✗
expected 0.36680734461325704 · got 0.36275830560717914 · error 1.1% · outside tolerance
median1✗
expected 0.3245383709968629 · got 0.3345908861843657 · error 3.1% · outside tolerance
Tool calls (7)
list_metrics → search_equities → get_market_history → run_calculation → run_calculation✗ → run_calculation → submit_answer