xiaomi/mimo-v2.6-flash

Correctness?

Efficiency?

Robustness?

Correctness says whether it can do the work; efficiency whether it finishes inside the same budget everyone gets; robustness whether it invents or omits. A low score should be readable as one of these, not a mystery.

Task type × domain?

Strict pass over this model’s tasks (share answered exactly right · task count). Rows are task types, columns are the data the answer lives in.

Where the points went?

Every task not answered exactly right, bucketed by what went wrong. 1 tasks.

Task families?

Lowest-scoring tasks?

Public example tasks link to the full question and every model’s answer; hidden tasks show only the family, the score and why.

• 0.0
  S-EQ34-NMulti-period Consistency — count of matchesview task

  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. The condition must hold in EACH of the last three reported quarters (i.e. the minimum YoY growth across them exceeds the threshold). 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 $100M, minimum revenue growth (YoY) across the last 3 quarters greater than 15%. Scope: only entities with a known value for 20-day average dollar volume, minimum revenue growth (YoY) across the last 3 quarters 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.

  Budget ran out and the answer was forced. Expected 178, got 180 (1% off) — outside tolerance.
• 100.0
  J05Statement Audit — Equity Technicalshidden

  Gold has 1, the model returned 1: 1 correct → F1 100%. Strict pass.
• 100.0
  S-CR12-APool Buyer/Seller Breadth — count, mean and median of a rebuilt metric over the matchesview task

  Unique buyers / unique sellers = distinct buying addresses divided by distinct selling addresses over 24h. Find DEX liquidity pools in the top-200-by-24h-volume universe of each supported network with unique buyers / unique sellers greater than 2, 24h unique buyers at least 100, pool liquidity greater than $1M. Scope: only entities with a known value for buyer seller ratio, buyers 24h in the snapshot; entities lacking any of them are out of scope and must not be returned. Entity ids are pool ids of the form network:pooladdress exactly as listed in the snapshot. EVM pool addresses (0x…) are lowercase hex and case-insensitive; Solana and other base58 addresses are CASE-SENSITIVE and must be returned exactly as shown. For the set of ALL entities that match the conditions above, report three numbers: count = how many match; mean = the arithmetic mean of Unique buyers / unique sellers (Distinct buyers divided by distinct sellers over 24h (breadth of demand).) 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.

  All 3 fields correct.
• 100.0
  J05Statement Audit — Equity Technicalshidden

  Gold has 1, the model returned 1: 1 correct → F1 100%. Strict pass.
• 100.0
  S-EQ21-XXGrowth Acceleration — plus two more hidden conditionsview task

  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. Acceleration means the latest quarter's revenue YoY growth is higher than the previous quarter's. 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 $1B, sector equal to Basic Materials, revenue growth accelerating (latest-quarter YoY above the prior quarter's), P/E (market cap / trailing-twelve-month net income from the filings) less than 40, EMA50 above EMA200. Scope: only entities with a known value for 20-day average dollar volume, sector, revenue growth accelerating (latest-quarter YoY above the prior quarter's), P/E (market cap / trailing-twelve-month net income from the filings), EMA50 above EMA200 in the snapshot; entities lacking any of them are out of scope and must not be returned. Return every matching ticker; order does not matter. 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.

  Gold has 2, the model returned 2: 2 correct → F1 100%. Strict pass.
• 100.0
  J02Statement Audit — Perpetualshidden

  Gold has 2, the model returned 2: 2 correct → F1 100%. Strict pass.
• 100.0
  J05Statement Audit — Equity Technicalshidden

  Gold has 2, the model returned 2: 2 correct → F1 100%. Strict pass.
• 100.0
  S-CR18-APerp RSI Range + Positive Trend — count, mean and median of a rebuilt metric over the matchesview task

  Perpetual technicals use COMPLETED UTC daily bars only (Hyperliquid 1d candles). "The session" below means the last closed UTC session — its date is the row attribute last_closed_bar — never the bar still forming at snapshot time. RSI = 14-day Wilder RSI on daily closes, as of the session; trend alignment = the session's close > EMA20 > EMA50 (EMAs of daily closes). Open interest (USD) is taken at snapshot time, not at the session close. Find Hyperliquid perpetual markets with open interest greater than $20M, perp rsi 14 between 55 and 70, perp trend alignment. Scope: only entities with a known value for perp rsi 14, perp trend alignment 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 Perp RSI14 (14-day Wilder RSI on daily closes.) 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 plain number in the metric's unit (index). 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.

  All 3 fields correct.