Claude family · videopoker · Chat Off
ante-index-v1
59.5/ 100
95% interval 58.1–60.9
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 | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 8 wins / 0 ties / 2 lossesev loss per hand: −0.9126 (95% interval −1.0909 to −0.7533; 10 scored units) | 0 missing · 0 void |
| Claude Mythos 5.1 | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 3 wins / 1 ties / 6 lossesev loss per hand: +0.2641 (95% interval +0.2198 to +0.3053; 10 scored units) | 0 missing · 0 void |
| Claude Opus 5.5 | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 3 wins / 3 ties / 4 lossesev loss per hand: +0.2649 (95% interval +0.2271 to +0.3055; 10 scored units) | 0 missing · 0 void |
| Claude Sonnet 5.5 | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 4 wins / 0 ties / 6 losses |
These are observed frequencies under this ruleset and opponent panel, not personality traits or evidence of inner state.
Commentary · Recorded net: 120 chips.
decision_deadline_ms: 90000 → 180000
New participant: claude-haiku-5-5-blackjack-off-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-haiku-5-5-blackjack-on-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-haiku-5-5-team-on-s3
prompt_version: v2 → v3
New participant: claude-haiku-5-5-craps-off-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-haiku-5-5-craps-off-s3
prompt_version: v2 → v3
New participant: claude-haiku-5-5-craps-on-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-haiku-5-5-craps-on-s3
| Condition | Follow control | Follow pressure | Susceptibility | Pairs |
|---|---|---|---|---|
| craps social | 34.0% | 33.5% | 0.0 pp | 200 |
| roulette fallacy | 2.6% | 1.0% | 0.0 pp | 192 |
Loss against the covered reference, compared with a random player. Lower loss is better.
Excluded from Edge: Roulette (exhibition).
| 0 missing · 0 void |
| Claude Sonnet 5 | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 2 wins / 1 ties / 7 lossesev loss per hand: +0.0702 (95% interval +0.0098 to +0.1241; 10 scored units) | 0 missing · 0 void |
|---|
| DeepSeek V4.1 Flash | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 9 wins / 0 ties / 1 lossesev loss per hand: −0.4528 (95% interval −0.6202 to −0.2939; 10 scored units) | 0 missing · 0 void |
|---|
| DeepSeek V4 Pro | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 6 wins / 2 ties / 2 lossesev loss per hand: −0.4526 (95% interval −0.6152 to −0.3072; 10 scored units) | 0 missing · 0 void |
|---|
| Gemini 3.8 Flash | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 3 wins / 1 ties / 6 lossesev loss per hand: +0.2823 (95% interval +0.2387 to +0.3183; 10 scored units) | 0 missing · 0 void |
|---|
| GLM 5.3 Flash | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 6 wins / 0 ties / 4 lossesev loss per hand: −0.3021 (95% interval −0.5066 to −0.1222; 10 scored units) | 0 missing · 0 void |
|---|
| GPT-5.6 Terra | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 4 wins / 1 ties / 5 lossesev loss per hand: +0.1122 (95% interval +0.0416 to +0.1765; 10 scored units) | 0 missing · 0 void |
|---|
| GPT-6.1 Sol | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 3 wins / 1 ties / 6 lossesev loss per hand: +0.2868 (95% interval +0.2446 to +0.3222; 10 scored units) | 0 missing · 0 void |
|---|
| GPT-6 Astra | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 3 wins / 1 ties / 6 lossesev loss per hand: +0.2864 (95% interval +0.2439 to +0.3222; 10 scored units) | 0 missing · 0 void |
|---|
| GPT-6 Luna | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 4 wins / 1 ties / 5 lossesev loss per hand: −0.0686 (95% interval −0.2192 to +0.0865; 10 scored units) | 0 missing · 0 void |
|---|
| GPT-6 Sol | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 4 wins / 1 ties / 5 lossesev loss per hand: +0.1543 (95% interval +0.0355 to +0.2558; 10 scored units) | 0 missing · 0 void |
|---|
| Grok 4.7 | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 7 wins / 0 ties / 3 lossesev loss per hand: −0.3501 (95% interval −0.4729 to −0.2473; 10 scored units) | 0 missing · 0 void |
|---|
| Muse Wonder | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 3 wins / 1 ties / 6 lossesev loss per hand: +0.2632 (95% interval +0.2167 to +0.303; 10 scored units) | 0 missing · 0 void |
|---|
| Solar Pro 4 | 10 sessions | You: seat 1 10 Opponent: seat 1 10 | net chips: 6 wins / 1 ties / 3 lossesev loss per hand: −0.8469 (95% interval −1.0135 to −0.687; 10 scored units) | 0 missing · 0 void |
|---|
prompt_version: v2 → v3
New participant: claude-haiku-5-5-craps-social-on-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-haiku-5-5-craps-social-on-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-haiku-5-5-showdown-off-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-haiku-5-5-videopoker-off-s3
Identical frozen decisions, separate from the Ante Index. Each game, split and stratum is shown with 95% intervals. Season 3 settings · participant IDs ending in -s3.
| Participant | Cases | Mean loss | Loss / random | Optimal | Valid | Quality · all | Quality · valid | Coverage | Latency p50 | Latency p95 | Mean cost |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Blackjack · easyClaude Haiku 5.5 · calibration | 15/150 transport failures | 0.0000.000–0.000 | 0.0000.000–0.000 | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 1,672 ms1,290 ms–1,795 ms | 3,291 ms1,759 ms–6,334 ms | $0.0002$0.0002–$0.0002 |
| Blackjack · costlyClaude Haiku 5.5 · calibration | 17/170 transport failures | 0.0000.000–0.000 | 0.0000.000–0.000 | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 1,591 ms1,381 ms–1,795 ms | 2,856 ms1,809 ms–6,334 ms | $0.0002$0.0002–$0.0002 |
| Blackjack Team Play · easyClaude Haiku 5.5 · calibration | 15/150 transport failures | 0.0000.000–0.000 | 0.0000.000–0.000 | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 2,333 ms1,894 ms–2,775 ms | 3,037 ms2,794 ms–3,054 ms | $0.0019$0.0015–$0.0023 |
| Blackjack Team Play · costlyClaude Haiku 5.5 · calibration | 13/130 transport failures | 0.0000.000–0.000 | 0.0000.000–0.000 | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 2,332 ms1,894 ms–2,619 ms | 3,016 ms2,543 ms–3,030 ms | $0.0020$0.0015–$0.0024 |
| Blackjack Team Play · costlyClaude Haiku 5.5 · sealed | 71/710 transport failures | 0.0000.000–0.000 | 0.0000.000–0.000 | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 2,334 ms2,219 ms–2,440 ms | 3,451 ms2,835 ms–3,824 ms | $0.0018$0.0016–$0.0020 |
| Blackjack · overallClaude Haiku 5.5 · calibration | 29/290 transport failures | 0.0010.000–0.003 | 0.0030.000–0.009 | 93.1%82.8%–100.0% | 100.0%100.0%–100.0% | 99.7%99.1%–100.0% | 99.7%99.1%–100.0% | 100.0%100.0%–100.0% | 1,606 ms1,507 ms–1,795 ms | 2,675 ms1,966 ms–6,334 ms | $0.0002$0.0002–$0.0002 |
| Blackjack · borderlineClaude Haiku 5.5 · calibration | 10/100 transport failures | 0.0030.000–0.008 | 0.0240.000–0.063 | 80.0%50.0%–100.0% | 100.0%100.0%–100.0% | 97.6%93.7%–100.0% | 97.6%93.7%–100.0% | 100.0%100.0%–100.0% | 1,771 ms1,547 ms–2,170 ms | 2,653 ms1,954 ms–2,856 ms | $0.0002$0.0002–$0.0002 |
| Blackjack · borderlineClaude Haiku 5.5 · sealed | 41/410 transport failures | 0.0050.000–0.012 | 0.0330.003–0.079 | 87.8%78.0%–97.6% | 100.0%100.0%–100.0% | 96.7%92.1%–99.7% | 96.7%92.1%–99.7% | 100.0%100.0%–100.0% | 1,786 ms1,630 ms–1,865 ms | 2,734 ms2,263 ms–4,642 ms | $0.0002$0.0002–$0.0002 |
| Blackjack Team Play · easyClaude Haiku 5.5 · sealed | 73/730 transport failures | 0.0060.000–0.018 | 0.0110.000–0.035 | 98.6%95.9%–100.0% | 100.0%100.0%–100.0% | 98.9%96.5%–100.0% | 98.9%96.5%–100.0% | 100.0%100.0%–100.0% | 2,398 ms2,273 ms–2,468 ms | 3,677 ms3,091 ms–4,203 ms | $0.0019$0.0017–$0.0021 |
| Blackjack Team Play · overallClaude Haiku 5.5 · sealed | 118/1180 transport failures | 0.0060.001–0.015 | 0.0160.002–0.037 | 92.4%87.3%–96.6% | 100.0%100.0%–100.0% | 98.4%96.3%–99.8% | 98.4%96.3%–99.8% | 100.0%100.0%–100.0% | 2,425 ms2,325 ms–2,527 ms | 3,800 ms3,516 ms–4,278 ms | $0.0019$0.0017–$0.0020 |
| Blackjack Team Play · overallClaude Haiku 5.5 · calibration | 30/300 transport failures | 0.0070.001–0.015 | 0.0190.002–0.049 | 86.7%73.3%–96.7% | 100.0%100.0%–100.0% | 98.1%95.1%–99.8% | 98.1%95.1%–99.8% | 100.0%100.0%–100.0% | 2,333 ms2,102 ms–2,574 ms | 3,043 ms2,838 ms–3,074 ms | $0.0019$0.0016–$0.0022 |
| Blackjack · easyClaude Haiku 5.5 · sealed | 67/670 transport failures | 0.0070.000–0.021 | 0.0120.000–0.039 | 98.5%95.5%–100.0% | 100.0%100.0%–100.0% | 98.8%96.1%–100.0% | 98.8%96.1%–100.0% | 100.0%100.0%–100.0% | 1,546 ms1,439 ms–1,688 ms | 2,378 ms2,041 ms–4,050 ms | $0.0002$0.0002–$0.0002 |
| Blackjack · overallClaude Haiku 5.5 · sealed | 119/1190 transport failures | 0.0080.001–0.018 | 0.0190.002–0.045 | 94.1%89.9%–97.5% | 100.0%100.0%–100.0% | 98.1%95.5%–99.8% | 98.1%95.5%–99.8% | 100.0%100.0%–100.0% | 1,666 ms1,585 ms–1,778 ms | 2,458 ms2,249 ms–4,050 ms | $0.0002$0.0002–$0.0002 |
| Blackjack Team Play · borderlineClaude Haiku 5.5 · sealed | 37/370 transport failures | 0.0080.003–0.016 | 0.0530.018–0.105 | 78.4%64.9%–89.2% | 100.0%100.0%–100.0% | 94.7%89.5%–98.2% | 94.7%89.5%–98.2% | 100.0%100.0%–100.0% | 2,650 ms2,314 ms–2,871 ms | 4,016 ms3,318 ms–5,909 ms | $0.0019$0.0016–$0.0021 |
| Blackjack · costlyClaude Haiku 5.5 · sealed | 75/750 transport failures | 0.0100.000–0.025 | 0.0170.000–0.044 | 97.3%93.3%–100.0% | 100.0%100.0%–100.0% | 98.3%95.6%–100.0% | 98.3%95.6%–100.0% | 100.0%100.0%–100.0% | 1,586 ms1,458 ms–1,732 ms | 2,243 ms2,041 ms–2,760 ms | $0.0002$0.0002–$0.0002 |
| Blackjack Team Play · borderlineClaude Haiku 5.5 · calibration | 14/140 transport failures | 0.0140.001–0.031 | 0.0890.013–0.197 | 71.4%50.0%–92.9% | 100.0%100.0%–100.0% | 91.1%80.3%–98.7% | 91.1%80.3%–98.7% | 100.0%100.0%–100.0% | 2,257 ms2,023 ms–2,759 ms | 3,024 ms2,624 ms–3,074 ms | $0.0019$0.0014–$0.0023 |
| Showdown Hold’em · borderlineClaude Haiku 5.5 · sealed | 40/400 transport failures | 0.0460.024–0.074 | 0.5530.294–0.886 | 65.0%50.0%–77.5% | 100.0%100.0%–100.0% | 44.7%11.4%–70.6% | 44.7%11.4%–70.6% | 100.0%100.0%–100.0% | 6,014 ms4,843 ms–10,782 ms | 20,273 ms16,451 ms–27,346 ms | $0.0010$0.0009–$0.0012 |
| Showdown Hold’em · borderlineClaude Haiku 5.5 · calibration | 10/100 transport failures | 0.0560.013–0.118 | 0.5990.118–1.299 | 70.0%40.0%–90.2% | 100.0%100.0%–100.0% | 40.1%0.0%–88.2% | 40.1%0.0%–88.2% | 100.0%100.0%–100.0% | 6,750 ms4,150 ms–13,721 ms | 14,790 ms7,419 ms–15,574 ms | $0.0009$0.0006–$0.0012 |
| Showdown Hold’em · overallClaude Haiku 5.5 · sealed | 120/1200 transport failures | 0.0740.031–0.127 | 0.1120.047–0.199 | 83.3%76.7%–90.0% | 99.2%97.5%–100.0% | 88.8%80.1%–95.3% | 90.5%82.9%–96.2% | 100.0%100.0%–100.0% | 10,686 ms8,179 ms–12,148 ms | 23,292 ms19,297 ms–31,574 ms | $0.0012$0.0011–$0.0013 |
| Showdown Hold’em · overallClaude Haiku 5.5 · calibration | 30/300 transport failures | 0.0780.012–0.168 | 0.1100.015–0.257 | 83.3%70.0%–93.4% | 100.0%100.0%–100.0% | 89.0%74.3%–98.5% | 89.0%74.3%–98.5% | 100.0%100.0%–100.0% | 11,095 ms6,194 ms–15,465 ms | 20,704 ms18,344 ms–23,643 ms | $0.0012$0.0010–$0.0014 |
| Showdown Hold’em · easyClaude Haiku 5.5 · sealed | 80/800 transport failures | 0.0880.023–0.161 | 0.0930.024–0.174 | 92.5%86.3%–97.5% | 98.8%96.3%–100.0% | 90.7%82.6%–97.6% | 92.6%85.0%–98.6% | 100.0%100.0%–100.0% | 11,989 ms9,900 ms–13,105 ms | 23,344 ms19,281 ms–35,015 ms | $0.0013$0.0012–$0.0015 |
| Showdown Hold’em · costlyClaude Haiku 5.5 · sealed | 80/800 transport failures | 0.0880.023–0.161 | 0.0930.024–0.174 | 92.5%86.3%–97.5% | 98.8%96.3%–100.0% | 90.7%82.6%–97.6% | 92.6%85.0%–98.6% | 100.0%100.0%–100.0% | 11,989 ms9,900 ms–13,105 ms | 23,344 ms19,281 ms–35,015 ms | $0.0013$0.0012–$0.0015 |
| Showdown Hold’em · easyClaude Haiku 5.5 · calibration | 20/200 transport failures | 0.0890.000–0.223 | 0.0880.000–0.264 | 90.0%75.0%–100.0% | 100.0%100.0%–100.0% | 91.2%73.6%–100.0% | 91.2%73.6%–100.0% | 100.0%100.0%–100.0% | 14,693 ms6,078 ms–18,060 ms | 21,730 ms18,634 ms–23,643 ms | $0.0014$0.0011–$0.0016 |
| Showdown Hold’em · costlyClaude Haiku 5.5 · calibration | 20/200 transport failures | 0.0890.000–0.223 | 0.0880.000–0.264 | 90.0%75.0%–100.0% | 100.0%100.0%–100.0% | 91.2%73.6%–100.0% | 91.2%73.6%–100.0% | 100.0%100.0%–100.0% | 14,693 ms6,078 ms–18,060 ms | 21,730 ms18,634 ms–23,643 ms | $0.0014$0.0011–$0.0016 |
| Craps · overallClaude Haiku 5.5 · calibration | 22/300 transport failures | 0.1050.080–0.128 | 0.2690.208–0.330 | 22.7%5.6%–41.2% | 100.0%100.0%–100.0% | 73.1%67.0%–79.2% | 73.1%67.0%–79.2% | 73.3%56.7%–86.7% | 3,084 ms2,749 ms–3,571 ms | 4,835 ms3,885 ms–5,160 ms | $0.0012$0.0011–$0.0012 |
| Craps · easyClaude Haiku 5.5 · calibration | 22/300 transport failures | 0.1050.080–0.128 | 0.2690.208–0.330 | 22.7%5.6%–41.2% | 100.0%100.0%–100.0% | 73.1%67.0%–79.2% | 73.1%67.0%–79.2% | 73.3%56.7%–86.7% | 3,084 ms2,749 ms–3,571 ms | 4,835 ms3,885 ms–5,160 ms | $0.0012$0.0011–$0.0012 |
| Craps · borderlineClaude Haiku 5.5 · calibration | 22/300 transport failures | 0.1050.080–0.128 | 0.2690.208–0.330 | 22.7%5.6%–41.2% | 100.0%100.0%–100.0% | 73.1%67.0%–79.2% | 73.1%67.0%–79.2% | 73.3%56.7%–86.7% | 3,084 ms2,749 ms–3,571 ms | 4,835 ms3,885 ms–5,160 ms | $0.0012$0.0011–$0.0012 |
| Craps · costlyClaude Haiku 5.5 · calibration | 22/300 transport failures | 0.1050.080–0.128 | 0.2690.208–0.330 | 22.7%5.6%–41.2% | 100.0%100.0%–100.0% | 73.1%67.0%–79.2% | 73.1%67.0%–79.2% | 73.3%56.7%–86.7% | 3,084 ms2,749 ms–3,571 ms | 4,835 ms3,885 ms–5,160 ms | $0.0012$0.0011–$0.0012 |
| Craps · overallClaude Haiku 5.5 · calibration | 8/300 transport failures | 0.1140.071–0.140 | 0.2310.154–0.310 | 12.5%0.0%–40.0% | 100.0%100.0%–100.0% | 76.9%69.0%–84.6% | 76.9%69.0%–84.6% | 26.7%13.3%–43.3% | 3,114 ms3,000 ms–4,465 ms | 4,743 ms3,128 ms–4,892 ms | $0.0011$0.0011–$0.0012 |
| Craps · easyClaude Haiku 5.5 · calibration | 8/300 transport failures | 0.1140.071–0.140 | 0.2310.154–0.310 | 12.5%0.0%–40.0% | 100.0%100.0%–100.0% | 76.9%69.0%–84.6% | 76.9%69.0%–84.6% | 26.7%13.3%–43.3% | 3,114 ms3,000 ms–4,465 ms | 4,743 ms3,128 ms–4,892 ms | $0.0011$0.0011–$0.0012 |
| Craps · borderlineClaude Haiku 5.5 · calibration | 8/300 transport failures | 0.1140.071–0.140 | 0.2310.154–0.310 | 12.5%0.0%–40.0% | 100.0%100.0%–100.0% | 76.9%69.0%–84.6% | 76.9%69.0%–84.6% | 26.7%13.3%–43.3% | 3,114 ms3,000 ms–4,465 ms | 4,743 ms3,128 ms–4,892 ms | $0.0011$0.0011–$0.0012 |
| Craps · costlyClaude Haiku 5.5 · calibration | 8/300 transport failures | 0.1140.071–0.140 | 0.2310.154–0.310 | 12.5%0.0%–40.0% | 100.0%100.0%–100.0% | 76.9%69.0%–84.6% | 76.9%69.0%–84.6% | 26.7%13.3%–43.3% | 3,114 ms3,000 ms–4,465 ms | 4,743 ms3,128 ms–4,892 ms | $0.0011$0.0011–$0.0012 |
| Craps · overallClaude Haiku 5.5 · sealed | 89/1190 transport failures | 0.1290.115–0.142 | 0.3120.276–0.352 | 9.0%3.4%–15.6% | 100.0%100.0%–100.0% | 68.8%64.8%–72.4% | 68.8%64.8%–72.4% | 74.8%67.2%–81.5% | 3,253 ms3,064 ms–3,904 ms | 5,754 ms5,280 ms–7,169 ms | $0.0012$0.0012–$0.0012 |
| Craps · easyClaude Haiku 5.5 · sealed | 89/1190 transport failures | 0.1290.115–0.142 | 0.3120.276–0.352 | 9.0%3.4%–15.6% | 100.0%100.0%–100.0% | 68.8%64.8%–72.4% | 68.8%64.8%–72.4% | 74.8%67.2%–81.5% | 3,253 ms3,064 ms–3,904 ms | 5,754 ms5,280 ms–7,169 ms | $0.0012$0.0012–$0.0012 |
| Craps · borderlineClaude Haiku 5.5 · sealed | 89/1190 transport failures | 0.1290.115–0.142 | 0.3120.276–0.352 | 9.0%3.4%–15.6% | 100.0%100.0%–100.0% | 68.8%64.8%–72.4% | 68.8%64.8%–72.4% | 74.8%67.2%–81.5% | 3,253 ms3,064 ms–3,904 ms | 5,754 ms5,280 ms–7,169 ms | $0.0012$0.0012–$0.0012 |
| Craps · costlyClaude Haiku 5.5 · sealed | 89/1190 transport failures | 0.1290.115–0.142 | 0.3120.276–0.352 | 9.0%3.4%–15.6% | 100.0%100.0%–100.0% | 68.8%64.8%–72.4% | 68.8%64.8%–72.4% | 74.8%67.2%–81.5% | 3,253 ms3,064 ms–3,904 ms | 5,754 ms5,280 ms–7,169 ms | $0.0012$0.0012–$0.0012 |
| Craps · overallClaude Haiku 5.5 · sealed | 30/1190 transport failures | 0.1350.126–0.145 | 0.2860.256–0.322 | 0.0%0.0%–0.0% | 100.0%100.0%–100.0% | 71.4%67.8%–74.4% | 71.4%67.8%–74.4% | 25.2%18.5%–32.8% | 3,205 ms2,685 ms–3,340 ms | 4,567 ms3,606 ms–5,188 ms | $0.0011$0.0011–$0.0012 |
| Craps · easyClaude Haiku 5.5 · sealed | 30/1190 transport failures | 0.1350.126–0.145 | 0.2860.256–0.322 | 0.0%0.0%–0.0% | 100.0%100.0%–100.0% | 71.4%67.8%–74.4% | 71.4%67.8%–74.4% | 25.2%18.5%–32.8% | 3,205 ms2,685 ms–3,340 ms | 4,567 ms3,606 ms–5,188 ms | $0.0011$0.0011–$0.0012 |
| Craps · borderlineClaude Haiku 5.5 · sealed | 30/1190 transport failures | 0.1350.126–0.145 | 0.2860.256–0.322 | 0.0%0.0%–0.0% | 100.0%100.0%–100.0% | 71.4%67.8%–74.4% | 71.4%67.8%–74.4% | 25.2%18.5%–32.8% | 3,205 ms2,685 ms–3,340 ms | 4,567 ms3,606 ms–5,188 ms | $0.0011$0.0011–$0.0012 |
| Craps · costlyClaude Haiku 5.5 · sealed | 30/1190 transport failures | 0.1350.126–0.145 | 0.2860.256–0.322 | 0.0%0.0%–0.0% | 100.0%100.0%–100.0% | 71.4%67.8%–74.4% | 71.4%67.8%–74.4% | 25.2%18.5%–32.8% | 3,205 ms2,685 ms–3,340 ms | 4,567 ms3,606 ms–5,188 ms | $0.0011$0.0011–$0.0012 |
| Video Poker · costlyClaude Haiku 5.5 · calibration | 12/120 transport failures | 0.2360.000–0.707 | 0.0370.000–0.159 | 91.7%75.0%–100.0% | 100.0%100.0%–100.0% | 96.3%84.1%–100.0% | 96.3%84.1%–100.0% | 100.0%100.0%–100.0% | 3,314 ms2,148 ms–4,477 ms | 7,938 ms4,254 ms–7,976 ms | $0.0005$0.0004–$0.0006 |
| Video Poker · borderlineClaude Haiku 5.5 · sealed | 41/410 transport failures | 0.3800.238–0.525 | 0.3250.202–0.453 | 36.6%22.0%–51.2% | 100.0%100.0%–100.0% | 67.5%54.7%–79.8% | 67.5%54.7%–79.8% | 100.0%100.0%–100.0% | 5,502 ms5,071 ms–6,367 ms | 8,348 ms7,622 ms–9,082 ms | $0.0007$0.0006–$0.0007 |
| Video Poker · overallClaude Haiku 5.5 · sealed | 120/1200 transport failures | 0.3860.231–0.561 | 0.0830.044–0.151 | 70.0%61.7%–78.3% | 100.0%100.0%–100.0% | 91.7%84.9%–95.6% | 91.7%84.9%–95.6% | 100.0%100.0%–100.0% | 4,579 ms4,269 ms–5,039 ms | 8,731 ms7,566 ms–10,325 ms | $0.0006$0.0006–$0.0006 |
| Video Poker · overallClaude Haiku 5.5 · calibration | 30/300 transport failures | 0.4040.163–0.685 | 0.1110.038–0.240 | 70.0%53.3%–86.7% | 100.0%100.0%–100.0% | 88.9%76.0%–96.2% | 88.9%76.0%–96.2% | 100.0%100.0%–100.0% | 4,523 ms3,721 ms–5,159 ms | 8,585 ms7,311 ms–9,202 ms | $0.0006$0.0005–$0.0006 |
| Video Poker · easyClaude Haiku 5.5 · calibration | 17/170 transport failures | 0.4190.000–0.887 | 0.0910.000–0.254 | 82.4%64.7%–100.0% | 100.0%100.0%–100.0% | 90.9%74.6%–100.0% | 90.9%74.6%–100.0% | 100.0%100.0%–100.0% | 4,030 ms2,979 ms–5,159 ms | 8,221 ms5,383 ms–9,202 ms | $0.0006$0.0005–$0.0007 |
| Video Poker · costlyClaude Haiku 5.5 · sealed | 51/510 transport failures | 0.4690.141–0.809 | 0.0540.016–0.128 | 86.3%76.5%–96.1% | 100.0%100.0%–100.0% | 94.6%87.2%–98.4% | 94.6%87.2%–98.4% | 100.0%100.0%–100.0% | 3,917 ms3,105 ms–4,581 ms | 10,086 ms5,552 ms–11,710 ms | $0.0005$0.0005–$0.0006 |
| Video Poker · easyClaude Haiku 5.5 · sealed | 65/650 transport failures | 0.4720.223–0.767 | 0.0700.026–0.156 | 84.6%75.4%–92.3% | 100.0%100.0%–100.0% | 93.0%84.4%–97.4% | 93.0%84.4%–97.4% | 100.0%100.0%–100.0% | 4,423 ms3,728 ms–4,708 ms | 8,831 ms6,203 ms–10,503 ms | $0.0006$0.0005–$0.0006 |
| Video Poker · borderlineClaude Haiku 5.5 · calibration | 9/90 transport failures | 0.5540.223–0.852 | 0.4460.179–0.693 | 33.3%0.0%–66.7% | 100.0%100.0%–100.0% | 55.4%30.7%–82.1% | 55.4%30.7%–82.1% | 100.0%100.0%–100.0% | 6,005 ms4,959 ms–7,576 ms | 8,481 ms6,948 ms–9,084 ms | $0.0007$0.0006–$0.0008 |