← Leaderboard · task_1760d1afd7bb3cffda496e2b
S-CR08-N · Pool Buy/Sell Transaction-Count Imbalance — count of matchesMarket & SignalSignal detectionDEX poolsNUMBERHARDproxy of PRD S-CR08 buy/sell VOLUME imbalancepublic example

Question

Buy/sell transaction ratio = number of buy swaps divided by number of sell swaps over 24h (transaction COUNTS, not volume — v0.1 proxy for the PRD's buy/sell volume imbalance). Find DEX liquidity pools in the top-200-by-24h-volume universe of each supported network with buy/sell transaction ratio greater than 3, pool liquidity greater than $1M. Scope: only entities with a known value for buy sell txn ratio 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. How many entities match ALL of the conditions above? Answer with the integer count (0 if none).
Data as of 2026-09-10 · grader numeric_tolerance

Expected / gold answer

8 (8 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 330.1s · cost $0.0132
tool calls 14
Model answer
8 (8 count)
Why this score
Expected 8, got 8 (0% off) — within tolerance.
expected 8 · got 8 · error 0.0% · within tolerance
Tool calls (14)
list_metrics → search_dex_pools → search_dex_pools → run_calculation → search_dex_pools → search_dex_pools → search_dex_pools → search_dex_pools → search_dex_pools → search_dex_pools → run_calculation → search_dex_pools → search_dex_pools → submit_answer
DeepSeek
deepseek/deepseek-v4.1-flash
100.0strict pass
latency 37.3s · cost $0.0925
tool calls 8
Model answer
8 (8 pools)
Why this score
Expected 8, got 8 (0% off) — within tolerance.
expected 8 · got 8 · error 0.0% · within tolerance
Tool calls (8)
list_metrics → search_dex_pools → search_dex_pools → search_dex_pools → run_calculation → run_calculation → run_calculation → submit_answer
Anthropic
Claude Opus 5.5
100.0strict pass
latency 35.2s · cost $0.5716
tool calls 5
Model answer
8 (8 count)
Why this score
Expected 8, got 8 (0% off) — within tolerance.
expected 8 · got 8 · error 0.0% · within tolerance
Tool calls (5)
list_metrics → search_dex_pools → search_dex_pools → run_calculation → submit_answer
Gemini
google/gemini-3.8-flash
100.0strict pass
latency 47.9s · cost $0.1768
tool calls 11
Model answer
8 (8 ratio)
Why this score
Expected 8, got 8 (0% off) — within tolerance.
expected 8 · got 8 · error 0.0% · within tolerance
Tool calls (11)
list_metrics → search_dex_pools → search_dex_pools → search_dex_pools → search_dex_pools → run_calculation → get_dex_pool → run_calculation → run_calculation✗ → run_calculation → submit_answer
Z.ai
z-ai/glm-5.3-flash
100.0strict pass
latency 59.0s · cost $0.0075
tool calls 6
Model answer
8 (8 ratio)
Why this score
Expected 8, got 8 (0% off) — within tolerance.
expected 8 · got 8 · error 0.0% · within tolerance
Tool calls (6)
list_metrics → search_dex_pools → search_dex_pools → search_dex_pools → run_calculation → submit_answer
Grok
x-ai/grok-4.7
100.0strict pass
latency 16.6s · cost $0.1169
tool calls 5
Model answer
8 (8 shares)
Why this score
Expected 8, got 8 (0% off) — within tolerance.
expected 8 · got 8 · error 0.0% · within tolerance
Tool calls (5)
list_metrics → search_dex_pools → search_dex_pools → run_calculation → submit_answer
Qwen
qwen/qwen3.8-flash
0.0not a strict pass
latency 81.3s · cost $0.0102
tool calls 6
Model answer
11 (11 shares)
Why this score
Expected 8, got 11 (38% off) — outside tolerance.
expected 8 · got 11 · error 37.5% · outside tolerance
Tool calls (6)
list_metrics → search_dex_pools → search_dex_pools → run_calculation → run_calculation → submit_answer
Minimax
MiniMax M3
0.0not a strict pass
latency 4.0s · cost $0.0034
tool calls 2
Model answer
0 (0 ratio)
Why this score
Expected 8, got 0 (1.00 off) — outside tolerance.
expected 8 · got 0 · error 1.0000 · outside tolerance
Tool calls (2)
list_metrics → submit_answer