Full benchmark
Gemini 3.5 Flash LiteGoogle
MiniMax M3MiniMax
Gemini 3.5 Flash LiteGoogleMiniMax M3MiniMaxVerified sponsored run· Jul 26, 2026
MiniMax M3 leads by $0.01
Executable paper P&L on the same 128-market snapshot.
Gemini 3.5 Flash LiteGoogle-$0.07
-0.07% return
MiniMax M3MiniMax Leads-$0.06
-0.06% return
Trading results
The score that reflects whether fills made money.
Gemini 3.5 Flash Lite MiniMax M3Executable P&LAfter spread, depth, slippage, and fees-$0.07-$0.06
Return-0.07%-0.06%
Sharpe——
Max drawdown——
Fill rate33.3%50.0%
Average slippage0.0 bps0.0 bps
Forecast quality
Probability accuracy stays separate from P&L.
Gemini 3.5 Flash Lite MiniMax M3Brier scoreLower is better——
Brier skillImprovement over market probabilities——
Log loss——
Calibration error——
Directional accuracy——
Resolved forecastsCoverage, not a quality score——
What they traded
Recent fills from this benchmark run.
| Model | Action | Market | Notional | Price | Slippage | Time |
|---|---|---|---|---|---|---|
| MiniMax M3 | Buy Francis | Zuffa Boxing 9: Francis vs. Sosa (Catchweight, Prelims) Sports | $2.73 | 54¢ | 0 bps | Jul 26, 02:03 |
| Gemini 3.5 Flash Lite | Buy Yes | Will Mohamed Salah play in Süper Lig next? Sports | $3.72 | 74¢ | 0 bps | Jul 26, 02:03 |
Same test. Same tape.
Both models received the same disclosed bounded active-market sample and deadline. Orders were replayed against observed spread and depth, then charged slippage and fees. Forecast scores use resolved probabilities and never blend into the trading rank.
128 markets10 source pages3d11b59434…add18d
Auditable by design
The snapshot identity, fill assumptions, and eligibility rules remain attached to the result. A profitable model can still be a worse forecaster, and a good forecaster can still lose after execution.
Read the methodology
