← Leaderboard · task_7e94110d84771e89df04917a
S-X06 · Compound Screen with Staged Narrative (liquidity → growth → momentum → rank)Market & SignalMulti-stepEquityRANKED_SETHARDpublic example

Question

Work in stages, narrowing the candidate pool at each step: Stage 1 (liquidity): keep US-listed equities with market cap greater than $2B and 20-day average dollar volume greater than $100M, sector equal to Energy. Stage 2 (growth): keep names whose latest-quarter revenue growth (YoY) is greater than 20% (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.). Stage 3 (momentum): keep names whose 60-session return (adjusted close today / adjusted close 60 sessions ago − 1) is greater than 0%. Finally rank the survivors by 60-session return descending and return the top 5 tickers in order; order is graded. Scope: only entities with a known value for 20-day average dollar volume, sector, latest-quarter revenue growth (YoY), 60-day return in the snapshot; entities lacking any of them are out of scope and must not be returned. 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 top_k_precision

Expected / gold answer

ranked · 5 items
1. SM2. AR3. EOG4. EXE5. EQT

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 232.2s · cost $0.0092
tool calls 6
Model answer
ranked · 5 items
1. SM2. AR3. EOG4. EXE5. EQT
Why this score
Gold has 5, the model returned 5: 5 correct → F1 100%; order agreement 100%. Strict pass.
gold 5 · returned 5 · correct 5 · false positives 0 · missed 0
precision 100.0% · recall 100.0% · F1 100.0% · order agreement 100.0% · strict pass
Tool calls (6)
list_metrics → search_equities → get_equity_financials → get_market_history → run_calculation → submit_answer
DeepSeek
deepseek/deepseek-v4.1-flash
100.0strict pass
latency 43.5s · cost $0.1020
tool calls 9
Model answer
ranked · 5 items
1. SM2. AR3. EOG4. EXE5. EQT
Why this score
Gold has 5, the model returned 5: 5 correct → F1 100%; order agreement 100%. Strict pass.
gold 5 · returned 5 · correct 5 · false positives 0 · missed 0
precision 100.0% · recall 100.0% · F1 100.0% · order agreement 100.0% · strict pass
Tool calls (9)
list_metrics → search_equities → get_equity_financials → run_calculation → get_market_history → run_calculation → run_calculation → get_equity_metrics → submit_answer
Anthropic
Claude Opus 5.5
100.0strict pass
latency 37.3s · cost $0.6359
tool calls 6
Model answer
ranked · 5 items
1. SM2. AR3. EOG4. EXE5. EQT
Why this score
Gold has 5, the model returned 5: 5 correct → F1 100%; order agreement 100%. Strict pass.
gold 5 · returned 5 · correct 5 · false positives 0 · missed 0
precision 100.0% · recall 100.0% · F1 100.0% · order agreement 100.0% · strict pass
Tool calls (6)
list_metrics → search_equities → get_equity_financials → get_market_history → run_calculation → submit_answer
Qwen
qwen/qwen3.8-flash
100.0strict pass
latency 84.6s · cost $0.0161
tool calls 8
Model answer
ranked · 5 items
1. SM2. AR3. EOG4. EXE5. EQT
Why this score
Gold has 5, the model returned 5: 5 correct → F1 100%; order agreement 100%. Strict pass.
gold 5 · returned 5 · correct 5 · false positives 0 · missed 0
precision 100.0% · recall 100.0% · F1 100.0% · order agreement 100.0% · strict pass
Tool calls (8)
list_metrics → search_equities → get_equity_financials → run_calculation → get_market_history → run_calculation → run_calculation → submit_answer
Gemini
google/gemini-3.8-flash
100.0strict pass
latency 65.6s · cost $0.1271
tool calls 14
Model answer
ranked · 5 items
1. SM2. AR3. EOG4. EXE5. EQT
Why this score
Gold has 5, the model returned 5: 5 correct → F1 100%; order agreement 100%. Strict pass.
gold 5 · returned 5 · correct 5 · false positives 0 · missed 0
precision 100.0% · recall 100.0% · F1 100.0% · order agreement 100.0% · strict pass
Tool calls (14)
list_metrics → search_equities → run_calculation → get_equity_financials → run_calculation → get_equity_financials → run_calculation✗ → run_calculation → get_market_history → run_calculation → get_equity_metrics → get_equity_financials → run_calculation → submit_answer
Z.ai
z-ai/glm-5.3-flash
100.0strict pass
latency 182.2s · cost $0.0130
tool calls 7
Model answer
ranked · 5 items
1. SM2. AR3. EOG4. EXE5. EQT
Why this score
Gold has 5, the model returned 5: 5 correct → F1 100%; order agreement 100%. Strict pass.
gold 5 · returned 5 · correct 5 · false positives 0 · missed 0
precision 100.0% · recall 100.0% · F1 100.0% · order agreement 100.0% · strict pass
Tool calls (7)
list_metrics → search_equities → get_equity_financials → run_calculation → get_market_history → run_calculation → submit_answer
Grok
x-ai/grok-4.7
100.0strict pass
latency 24.8s · cost $0.1464
tool calls 6
Model answer
ranked · 5 items
1. SM2. AR3. EOG4. EXE5. EQT
Why this score
Gold has 5, the model returned 5: 5 correct → F1 100%; order agreement 100%. Strict pass.
gold 5 · returned 5 · correct 5 · false positives 0 · missed 0
precision 100.0% · recall 100.0% · F1 100.0% · order agreement 100.0% · strict pass
Tool calls (6)
list_metrics → search_equities → get_equity_financials → get_market_history → run_calculation → submit_answer
Minimax
MiniMax M3
100.0strict pass
latency 103.6s · cost $0.0320
tool calls 11
Model answer
ranked · 5 items
1. SM2. AR3. EOG4. EXE5. EQT
Why this score
Gold has 5, the model returned 5: 5 correct → F1 100%; order agreement 100%. Strict pass.
gold 5 · returned 5 · correct 5 · false positives 0 · missed 0
precision 100.0% · recall 100.0% · F1 100.0% · order agreement 100.0% · strict pass
Tool calls (11)
list_metrics → search_equities → get_equity_financials → get_market_history → run_calculation → run_calculation✗ → run_calculation✗ → run_calculation → run_calculation → run_calculation → submit_answer