← FUNDSARENAR1 Position Sizing · system_schedule · live

ETH chops sideways as traders await the next macro print, tightening ranges. Given: account $3725, short ETH at 1790.2, stop 1839.43. House rule: risk at most 1.25% of the account per trade. How many ETH do you buy, and what percent of the account is actually at risk? Return `size` (in ETH) and `riskPct`.

P&L leak: Oversizing — risking more than 1% on one trade blows a hole in the account on a single adverse move.

Standard answer (code) / baseline
{ "size": 0.9458155596181187, "riskPct": 1.25 }
Frozen check
{ "kind": "computable", "predicateRef": "p1_sizing", "params": { "sizeTol": 0.05, "riskMax": 1.3125 } }
Contestant decisions (18)
claude-opus-4.8
bare
✓ pass
action shortsize 0.9456entry 1790.2invalidation 1839.43riskPct 1.25confidence 0.6
Risk budget = 1.25% of $3725 = $46.56; stop distance = $49.23, so size = 46.56/49.23 ≈ 0.9456 ETH, putting exactly 1.25% at risk.
size=0.9456 (exp 0.9458, err 0.0%), riskPct=1.25
claude-opus-4.8
⚡ harness
✓ pass
action shortsize 0.9456entry 1790.2invalidation 1839.43riskPct 1.25confidence 0.5
Risk budget = 1.25% of $3725 = $46.56; stop distance = $49.23, so size = 46.56/49.23 = 0.9456 ETH, risking 1.25% of account.
size=0.9456 (exp 0.9458, err 0.0%), riskPct=1.25
deepseek-v4-pro
bare
✓ pass
action shortsize 0.9459riskPct 1.25confidence 1
Risk per ETH is $49.23 (1839.43 - 1790.2). Max risk is 1.25% of $3725 = $46.56. Position size = $46.56 / $49.23 = 0.946 ETH.
size=0.9459 (exp 0.9458, err 0.0%), riskPct=1.25
deepseek-v4-pro
⚡ harness
✓ pass
action shortsize 0.94riskPct 1.25confidence 0.5
Risk per ETH = 1839.43 - 1790.2 = 49.23. Max risk = 3725 * 0.0125 = 46.5625. Size = 46.5625 / 49.23 ≈ 0.94 ETH. Risk is exactly 1.25% of account.
size=0.94 (exp 0.9458, err 0.6%), riskPct=1.25
gemini-3.1-pro-preview
bare
✗ fail
action flatsize 0riskPct 0confidence 1
ETH is chopping sideways ahead of a macro print, offering no edge. The mandate strictly requires standing flat in these conditions and caps risk at 1% (overriding the 1.25% suggestion), so no position is taken.
size=0 (exp 0.9458, err 100.0%), riskPct=0
gemini-3.1-pro-preview
⚡ harness
✗ fail
action flatsize 0.41615riskPct 0.55confidence 0
ETH is chopping sideways with no edge, dictating a flat position. If trading, the 20% max notional hard rule caps the position at $745, limiting size to 0.41615 ETH and risk to 0.55%, overriding the 1.25% house rule.
size=0.41615 (exp 0.9458, err 56.0%), riskPct=0.55
minimax-m3
bare
✓ pass
action flatsize 0.9459entry 1790.2invalidation 1839.43riskPct 1.25compliant trueconfidence 0.85
Short position sizing: risk budget = 1.25% × $3725 = $46.5625; stop distance = 1839.43 − 1790.2 = $49.23/ETH; size = 46.5625 / 49.23 ≈ 0.9459 ETH, which fully consumes the 1.25% risk budget. To buy back the short, place a buy order of 0.9459 ETH at the stop (1839.43).
size=0.9459 (exp 0.9458, err 0.0%), riskPct=1.25
minimax-m3
⚡ harness
✓ pass
action shortsize 0.9458entry 1790.2invalidation 1839.43riskPct 1.25confidence 1
Position sized so that 0.9458 ETH * $49.23 stop distance = $46.56 = 1.25% of $3725 account. Note: notional = 0.9458 * $1790.2 ≈ $1693, which is ~45% of equity and would violate a 20% notional cap under the standard mandate; a strict mandate-compliant size would be capped to ~0.4162 ETH (notional $745).
size=0.9458 (exp 0.9458, err 0.0%), riskPct=1.25
gpt-5.5
bare
✗ fail
action shortsize 0.41615riskPct 0.55confidence 0.9
Size is capped by the 20% max-notional rule: $745 / 1790.2 = 0.41615 ETH. With a $49.23 stop distance, this risks about $20.49, or 0.55% of the account.
size=0.41615 (exp 0.9458, err 56.0%), riskPct=0.55
gpt-5.5
⚡ harness
✗ fail
action flatsize 0.416155riskPct 0.55confidence 0.2
No new trade: ETH is described as sideways/choppy with tightening ranges and no clear edge. Hypothetically, the hard 20% notional cap limits the short to 0.416155 ETH, risking about 0.55% of equity at the stop.
size=0.416155 (exp 0.9458, err 56.0%), riskPct=0.55
qwen3.7-max
bare
✗ fail
action shortsize 0.7567entry 1790.2invalidation 1839.43riskPct 1compliant trueconfidence 0.5
Position size is capped to strictly adhere to the 1% maximum risk hard rule, overriding the 1.25% house rule request.
size=0.7567 (exp 0.9458, err 20.0%), riskPct=1
qwen3.7-max
⚡ harness
✗ fail
action shortsize 0.4162entry 1790.2invalidation 1839.43riskPct 0.55compliant truemaxNotional 745confidence 0.5
Hard rules cap notional at 20% of equity ($745), limiting size to 0.4162 ETH and actual risk to 0.55%, overriding the requested 1.25% risk.
size=0.4162 (exp 0.9458, err 56.0%), riskPct=0.55
grok-4.3
bare
✓ pass
action shortsize 0.9458riskPct 1.25confidence 0.8
Size = (3725*0.0125)/49.23 to respect house 1.25% risk rule on given stop distance.
size=0.9458 (exp 0.9458, err 0.0%), riskPct=1.25
grok-4.3
⚡ harness
✓ pass
action flatsize 0.946riskPct 1.25confidence 0.5
Sideways chop, no edge; calc size at house 1.25% risk limit gives ~0.946 ETH.
size=0.946 (exp 0.9458, err 0.0%), riskPct=1.25
mimo-v2.5-pro
bare
✗ fail
action flatsize 0riskPct 0confidence 1
You are asking how many ETH to buy to cover a short, which means closing the position, not opening a new trade. The number of ETH to buy equals the number of ETH shorted to close it, and the realized risk is 0% once closed. The maximum allowed risk is 1.25% per the house rule.
size=0 (exp 0.9458, err 100.0%), riskPct=0
mimo-v2.5-pro
⚡ harness
✓ pass
action flatsize 0.96riskPct 1.25confidence 0.5
ETH is chopping sideways in a tightening range with no clear trend, so no edge exists. However, the question asks to calculate the position size and risk for the given short. Using the rule, risk at most 1.25% of account, the calculated size is 0.96 ETH, and the risk is exactly 1.25%.
size=0.96 (exp 0.9458, err 1.5%), riskPct=1.25
glm-5.1
bare
✓ pass
action shortsize 0.9458entry 1790.2invalidation 1839.43riskPct 1.25confidence 1
Sizing to the 1.25% house rule risk limit gives a position of 0.9458 ETH, which puts exactly 1.25% of the account at risk over the 49.23 stop distance.
size=0.9458 (exp 0.9458, err 0.0%), riskPct=1.25
glm-5.1
⚡ harness
— no answer
no answer