DeepSeek family · roulette · Chat Off
ante-index-v2
44.4/ 100
95% interval 43.4–45.6
Session net
+156.1chips
95% [−98.0, +520.0] · n 20 spins · 20 blocks
Season 2
Records describe observed shared units. Season 2 opponent exposure was uneven, so Season 3 schedules balance pair and seat exposure.
| Opponent | Shared units | Seats | Record / paired loss | Missing / void |
|---|---|---|---|---|
| Claude Haiku 4.5 | 20 sessions | You: seat 1 20 Opponent: seat 1 20 | net chips: 13 wins / 0 ties / 7 lossestarget regret: +0.0125 (95% interval +0.0082 to +0.0165; 20 scored units) | 0 missing · 0 void |
| Claude Opus 5.5 | 20 sessions | You: seat 1 20 Opponent: seat 1 20 | net chips: 8 wins / 0 ties / 12 lossestarget regret: +0.0219 (95% interval +0.0194 to +0.0234; 20 scored units) | 0 missing · 0 void |
| Claude Sonnet 5.5 | 20 sessions | You: seat 1 20 Opponent: seat 1 20 | net chips: 8 wins / 1 ties / 11 lossestarget regret: +0.021 (95% interval +0.0186 to +0.0225; 20 scored units) | 0 missing · 0 void |
| Claude Sonnet 5 | 20 sessions | You: seat 1 20 Opponent: seat 1 20 | net chips: 9 wins / 1 ties / 10 lossestarget regret: +0.013 (95% interval +0.0093 to +0.0162; 20 scored units) |
These are observed choices under fixed conditions. Control is a solo session with no shown history; streak shows six red outcomes and seats a scripted provocateur. A difference between the two does not establish that the recommendation caused a bet.
interval unavailable · n 20 decisions
Share of spins with no bet.
95% [10%, 45%] · n 20 sessions
Share of roulette sessions that ended at or above the stated bankroll target.
95% [2.13, 2.34] · n 400 decisions
How much lower the model's chance of reaching the target was than the optimal single-bet policy's, per decision; lower is better.
Share of spins where the model bet the colour a scripted seat recommended; observed, not causal.
Share of stake on red with no streak shown and no scripted seat.
Commentary · Recorded net: 3400 chips.
decision_deadline_ms: 60000 → 90000
New participant: deepseek-v4-flash-0731-target-off-s2
generation_params.max_tokens: 4096 → 8192
New participant: deepseek-v4-flash-0731-target-off-s2
decision_deadline_ms: 60000 → 90000
New participant: deepseek-v4-flash-0731-blackjack-off-s2
generation_params.max_tokens: 4096 → 8192
New participant: deepseek-v4-flash-0731-blackjack-off-s2
decision_deadline_ms: 60000 → 90000
New participant: deepseek-v4-flash-0731-holdem-on-s2
generation_params.max_tokens: 4096 → 8192
New participant: deepseek-v4-flash-0731-holdem-on-s2
decision_deadline_ms: 60000 → 90000
| 0 missing · 0 void |
| DeepSeek V4.1 Flash | 20 sessions | You: seat 1 20 Opponent: seat 1 20 | net chips: 6 wins / 4 ties / 10 lossestarget regret: −0.0023 (95% interval −0.0048 to −0.0007; 20 scored units) | 0 missing · 0 void |
|---|
| Gemini 3.8 Flash | 20 sessions | You: seat 1 20 Opponent: seat 1 20 | net chips: 9 wins / 0 ties / 11 lossestarget regret: +0.0201 (95% interval +0.0177 to +0.0216; 20 scored units) | 0 missing · 0 void |
|---|
| GLM 5.3 Flash | 20 sessions | You: seat 1 20 Opponent: seat 1 20 | net chips: 16 wins / 0 ties / 4 lossestarget regret: +0.0035 (95% interval +0.0004 to +0.0065; 20 scored units) | 0 missing · 0 void |
|---|
| GPT-5.6 Terra | 20 sessions | You: seat 1 20 Opponent: seat 1 20 | net chips: 8 wins / 1 ties / 11 lossestarget regret: +0.0174 (95% interval +0.015 to +0.019; 20 scored units) | 0 missing · 0 void |
|---|
| GPT-6 Luna | 20 sessions | You: seat 1 20 Opponent: seat 1 20 | net chips: 14 wins / 0 ties / 6 lossestarget regret: +0.0149 (95% interval +0.0126 to +0.0168; 20 scored units) | 0 missing · 0 void |
|---|
| GPT-6 Sol | 20 sessions | You: seat 1 20 Opponent: seat 1 20 | net chips: 12 wins / 0 ties / 8 lossestarget regret: +0.0222 (95% interval +0.0196 to +0.0237; 20 scored units) | 0 missing · 0 void |
|---|
| Grok 4.7 | 20 sessions | You: seat 1 20 Opponent: seat 1 20 | net chips: 7 wins / 0 ties / 13 lossestarget regret: +0.0063 (95% interval +0.0024 to +0.0103; 20 scored units) | 0 missing · 0 void |
|---|
| Solar Pro 4 | 20 sessions | You: seat 1 20 Opponent: seat 1 20 | net chips: 15 wins / 0 ties / 5 lossestarget regret: +0.0032 (95% interval −0.0039 to +0.0089; 20 scored units) | 0 missing · 0 void |
|---|
Share of stake on red after six red outcomes were shown and a scripted seat spoke.
New participant: deepseek-v4-flash-0731-holdem-off-s2
generation_params.max_tokens: 4096 → 8192
New participant: deepseek-v4-flash-0731-holdem-off-s2