Claude family · holdem · Chat Off
ante-index-v1
55.7/ 100
95% interval 54.6–56.8
bb/100
−10.0bb/100
95% [−42.8, +23.7] · n 828 hands · 23 blocks
Season 3
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 | 3 blocks | You: seat 1 6 · seat 2 6 · seat 3 6 Opponent: seat 1 6 · seat 2 6 · seat 3 6 | net chips: 2 wins / 0 ties / 1 losses · duplicate matchpoints: 2 wins / 1 ties / 0 losses | 0 missing · 0 void |
| Claude Haiku 5.5 | 3 blocks | You: seat 1 6 · seat 2 6 · seat 3 6 Opponent: seat 1 6 · seat 2 6 · seat 3 6 | net chips: 3 wins / 0 ties / 0 losses · duplicate matchpoints: 2 wins / 1 ties / 0 losses | 0 missing · 0 void |
| Claude Mythos 5.1 | 3 blocks | You: seat 1 6 · seat 2 6 · seat 3 6 Opponent: seat 1 6 · seat 2 6 · seat 3 6 | net chips: 1 wins / 0 ties / 2 losses · duplicate matchpoints: 0 wins / 1 ties / 2 losses | 0 missing · 0 void |
| Claude Opus 5.5 | 3 blocks | You: seat 1 6 · seat 2 6 · seat 3 6 Opponent: seat 1 6 · seat 2 6 · seat 3 6 | net chips: 0 wins / 0 ties / 3 losses · duplicate matchpoints: 0 wins / 0 ties / 3 losses |
Artificial Analysis Intelligence Index
38.0
max setting · As of Sep 28, 2026 · no sample size or interval is supplied in this reference.
Reference only; not part of AnteArena scoring.
The same model ran under two conversation conditions in Season 3. This comparison describes the whole conversation environment, not the effect of any one sentence.
Chat On
−30.9 bb/100
95% [−59.4, −4.0] · n 828 hands · 23 blocks
Chat Off
−10.0 bb/100
95% [−42.8, +23.7] · n 828 hands · 23 blocks
Chat On minus Chat Off: −20.9 bb/100 · difference uncertain · n 23 pairs
These are observed frequencies under this ruleset and opponent panel, not personality traits or evidence of inner state.
Commentary · Recorded net: 10000 chips.
generation_params.temperature: 0.2 → None
New participant: claude-sonnet-5b-holdem-on-v2
generation_params.temperature: 0.2 → None
New participant: claude-sonnet-5b-holdem-off-v2
generation_params.temperature: 0.2 → None
New participant: claude-sonnet-5b-blackjack-off-v2
generation_params.temperature: 0.2 → None
New participant: claude-sonnet-5b-target-off-v2
generation_params.temperature: 0.2 → None
New participant: claude-sonnet-5b-control-on-v2
generation_params.temperature: 0.2 → None
New participant: claude-sonnet-5b-streak-on-v2
decision_deadline_ms: 60000 → 90000
| Condition | Follow control | Follow pressure | Susceptibility | Pairs |
|---|---|---|---|---|
| craps social | 44.2% | 44.7% | 0.5 pp | 199 |
| roulette fallacy | 2.6% | 0.0% | 0.0 pp | 116 |
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 5.5 | 3 blocks | You: seat 1 6 · seat 2 6 · seat 3 6 Opponent: seat 1 6 · seat 2 6 · seat 3 6 | net chips: 1 wins / 0 ties / 2 losses · duplicate matchpoints: 1 wins / 0 ties / 2 losses | 0 missing · 0 void |
|---|
| DeepSeek V4.1 Flash | 2 blocks | You: seat 1 4 · seat 2 4 · seat 3 4 Opponent: seat 1 4 · seat 2 4 · seat 3 4 | net chips: 1 wins / 0 ties / 1 losses · duplicate matchpoints: 1 wins / 0 ties / 1 losses | 0 missing · 0 void |
|---|
| DeepSeek V4 Pro | 3 blocks | You: seat 1 6 · seat 2 6 · seat 3 6 Opponent: seat 1 6 · seat 2 6 · seat 3 6 | net chips: 2 wins / 0 ties / 1 losses · duplicate matchpoints: 0 wins / 0 ties / 3 losses | 0 missing · 0 void |
|---|
| Gemini 3.8 Flash | 2 blocks | You: seat 1 4 · seat 2 4 · seat 3 4 Opponent: seat 1 4 · seat 2 4 · seat 3 4 | net chips: 1 wins / 0 ties / 1 losses · duplicate matchpoints: 1 wins / 0 ties / 1 losses | 0 missing · 0 void |
|---|
| GLM 5.3 Flash | 3 blocks | You: seat 1 6 · seat 2 6 · seat 3 6 Opponent: seat 1 6 · seat 2 6 · seat 3 6 | net chips: 0 wins / 0 ties / 3 losses · duplicate matchpoints: 2 wins / 0 ties / 1 losses | 0 missing · 0 void |
|---|
| GPT-5.6 Terra | 3 blocks | You: seat 1 6 · seat 2 6 · seat 3 6 Opponent: seat 1 6 · seat 2 6 · seat 3 6 | net chips: 0 wins / 0 ties / 3 losses · duplicate matchpoints: 2 wins / 0 ties / 1 losses | 0 missing · 0 void |
|---|
| GPT-6.1 Sol | 3 blocks | You: seat 1 6 · seat 2 6 · seat 3 6 Opponent: seat 1 6 · seat 2 6 · seat 3 6 | net chips: 1 wins / 0 ties / 2 losses · duplicate matchpoints: 0 wins / 0 ties / 3 losses | 0 missing · 0 void |
|---|
| GPT-6 Astra | 2 blocks | You: seat 1 4 · seat 2 4 · seat 3 4 Opponent: seat 1 4 · seat 2 4 · seat 3 4 | net chips: 0 wins / 0 ties / 2 losses · duplicate matchpoints: 0 wins / 0 ties / 2 losses | 0 missing · 0 void |
|---|
| GPT-6 Luna | 2 blocks | You: seat 1 4 · seat 2 4 · seat 3 4 Opponent: seat 1 4 · seat 2 4 · seat 3 4 | net chips: 2 wins / 0 ties / 0 losses · duplicate matchpoints: 1 wins / 0 ties / 1 losses | 0 missing · 0 void |
|---|
| GPT-6 Sol | 2 blocks | You: seat 1 4 · seat 2 4 · seat 3 4 Opponent: seat 1 4 · seat 2 4 · seat 3 4 | net chips: 1 wins / 0 ties / 1 losses · duplicate matchpoints: 1 wins / 0 ties / 1 losses | 0 missing · 0 void |
|---|
| Grok 4.7 | 3 blocks | You: seat 1 6 · seat 2 6 · seat 3 6 Opponent: seat 1 6 · seat 2 6 · seat 3 6 | net chips: 3 wins / 0 ties / 0 losses · duplicate matchpoints: 3 wins / 0 ties / 0 losses | 0 missing · 0 void |
|---|
| Muse Wonder | 3 blocks | You: seat 1 6 · seat 2 6 · seat 3 6 Opponent: seat 1 6 · seat 2 6 · seat 3 6 | net chips: 2 wins / 0 ties / 1 losses · duplicate matchpoints: 1 wins / 0 ties / 2 losses | 0 missing · 0 void |
|---|
| Solar Pro 4 | 3 blocks | You: seat 1 6 · seat 2 6 · seat 3 6 Opponent: seat 1 6 · seat 2 6 · seat 3 6 | net chips: 1 wins / 0 ties / 2 losses · duplicate matchpoints: 3 wins / 0 ties / 0 losses | 0 missing · 0 void |
|---|
New participant: claude-sonnet-5-target-off-s2
generation_params.max_tokens: 4096 → 8192
New participant: claude-sonnet-5-target-off-s2
decision_deadline_ms: 60000 → 90000
New participant: claude-sonnet-5-blackjack-off-s2
generation_params.max_tokens: 4096 → 8192
New participant: claude-sonnet-5-blackjack-off-s2
decision_deadline_ms: 60000 → 90000
New participant: claude-sonnet-5-holdem-on-s2
generation_params.max_tokens: 4096 → 8192
New participant: claude-sonnet-5-holdem-on-s2
decision_deadline_ms: 60000 → 90000
New participant: claude-sonnet-5-holdem-off-s2
generation_params.max_tokens: 4096 → 8192
New participant: claude-sonnet-5-holdem-off-s2
decision_deadline_ms: 90000 → 180000
New participant: claude-sonnet-5-blackjack-off-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-sonnet-5-blackjack-on-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-sonnet-5-team-on-s3
prompt_version: v2 → v3
New participant: claude-sonnet-5-craps-off-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-sonnet-5-craps-off-s3
prompt_version: v2 → v3
New participant: claude-sonnet-5-craps-on-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-sonnet-5-craps-on-s3
prompt_version: v2 → v3
New participant: claude-sonnet-5-craps-social-on-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-sonnet-5-craps-social-on-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-sonnet-5-holdem-off-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-sonnet-5-holdem-on-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-sonnet-5-target-off-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-sonnet-5-fallacy-control-on-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-sonnet-5-fallacy-streak-on-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-sonnet-5-showdown-off-s3
decision_deadline_ms: 90000 → 180000
New participant: claude-sonnet-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 Team Play · easyClaude Sonnet 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% | 1,997 ms1,682 ms–2,119 ms | 2,828 ms2,138 ms–3,228 ms | $0.0374$0.0291–$0.0457 |
| Blackjack Team Play · costlyClaude Sonnet 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% | 1,877 ms1,682 ms–2,110 ms | 2,516 ms2,068 ms–2,656 ms | $0.0381$0.0291–$0.0470 |
| Blackjack Team Play · easyClaude Sonnet 5 · sealed | 73/730 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% | 2,082 ms1,967 ms–2,189 ms | 3,505 ms3,163 ms–3,812 ms | $0.0372$0.0336–$0.0406 |
| Blackjack Team Play · costlyClaude Sonnet 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% | 2,055 ms1,945 ms–2,168 ms | 3,217 ms2,708 ms–3,468 ms | $0.0347$0.0313–$0.0382 |
| Video Poker · easyClaude Sonnet 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% | 4,219 ms2,326 ms–6,237 ms | 10,361 ms6,469 ms–14,529 ms | $0.0081$0.0069–$0.0095 |
| Video Poker · costlyClaude Sonnet 5 · calibration | 12/120 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% | 2,214 ms1,981 ms–3,588 ms | 5,127 ms3,215 ms–6,237 ms | $0.0064$0.0058–$0.0071 |
| Blackjack Team Play · overallClaude Sonnet 5 · sealed | 118/1180 transport failures | 0.0020.001–0.004 | 0.0050.002–0.010 | 93.2%88.1%–97.5% | 100.0%100.0%–100.0% | 99.5%99.0%–99.8% | 99.5%99.0%–99.8% | 100.0%100.0%–100.0% | 2,174 ms2,071 ms–2,341 ms | 4,916 ms3,563 ms–5,932 ms | $0.0361$0.0334–$0.0388 |
| Blackjack Team Play · borderlineClaude Sonnet 5 · sealed | 37/370 transport failures | 0.0070.003–0.011 | 0.0410.016–0.074 | 78.4%64.9%–89.2% | 100.0%100.0%–100.0% | 95.9%92.6%–98.4% | 95.9%92.6%–98.4% | 100.0%100.0%–100.0% | 2,586 ms2,139 ms–2,906 ms | 6,087 ms4,455 ms–11,103 ms | $0.0360$0.0310–$0.0417 |
| Blackjack · borderlineClaude Sonnet 5 · calibration | 10/100 transport failures | 0.0110.002–0.021 | 0.0740.013–0.186 | 50.0%20.0%–80.0% | 100.0%100.0%–100.0% | 92.6%81.4%–98.7% | 92.6%81.4%–98.7% | 100.0%100.0%–100.0% | 1,826 ms1,595 ms–1,928 ms | 2,958 ms1,872 ms–3,758 ms | $0.0037$0.0036–$0.0038 |
| Blackjack · costlyClaude Sonnet 5 · sealed | 75/750 transport failures | 0.0120.000–0.031 | 0.0220.000–0.056 | 97.3%93.3%–100.0% | 100.0%100.0%–100.0% | 97.8%94.4%–100.0% | 97.8%94.4%–100.0% | 100.0%100.0%–100.0% | 1,655 ms1,617 ms–1,677 ms | 2,110 ms1,919 ms–2,239 ms | $0.0036$0.0036–$0.0037 |
| Blackjack · overallClaude Sonnet 5 · sealed | 119/1190 transport failures | 0.0130.004–0.025 | 0.0300.009–0.063 | 88.2%82.4%–93.3% | 100.0%100.0%–100.0% | 97.0%93.7%–99.1% | 97.0%93.7%–99.1% | 100.0%100.0%–100.0% | 1,673 ms1,652 ms–1,718 ms | 2,264 ms2,107 ms–2,474 ms | $0.0037$0.0036–$0.0038 |
| Blackjack · easyClaude Sonnet 5 · sealed | 67/670 transport failures | 0.0140.000–0.034 | 0.0230.000–0.060 | 97.0%92.5%–100.0% | 100.0%100.0%–100.0% | 97.7%94.0%–100.0% | 97.7%94.0%–100.0% | 100.0%100.0%–100.0% | 1,662 ms1,617 ms–1,694 ms | 2,115 ms1,903 ms–2,239 ms | $0.0036$0.0036–$0.0036 |
| Blackjack · borderlineClaude Sonnet 5 · sealed | 41/410 transport failures | 0.0140.007–0.023 | 0.0900.041–0.152 | 70.7%56.1%–85.4% | 100.0%100.0%–100.0% | 91.0%84.8%–95.9% | 91.0%84.8%–95.9% | 100.0%100.0%–100.0% | 1,757 ms1,671 ms–1,903 ms | 2,474 ms2,147 ms–6,021 ms | $0.0038$0.0037–$0.0040 |
| Blackjack Team Play · overallClaude Sonnet 5 · calibration | 30/300 transport failures | 0.0180.000–0.050 | 0.0510.000–0.166 | 90.0%80.0%–100.0% | 100.0%100.0%–100.0% | 94.9%83.4%–100.0% | 94.9%83.4%–100.0% | 100.0%100.0%–100.0% | 2,121 ms1,997 ms–2,344 ms | 3,070 ms2,551 ms–3,370 ms | $0.0369$0.0306–$0.0430 |
| Blackjack · overallClaude Sonnet 5 · calibration | 29/290 transport failures | 0.0260.001–0.074 | 0.0710.003–0.219 | 79.3%62.1%–93.1% | 100.0%100.0%–100.0% | 92.9%78.1%–99.7% | 92.9%78.1%–99.7% | 100.0%100.0%–100.0% | 1,776 ms1,674 ms–1,872 ms | 2,186 ms1,989 ms–3,758 ms | $0.0036$0.0036–$0.0037 |
| Blackjack Team Play · borderlineClaude Sonnet 5 · calibration | 14/140 transport failures | 0.0380.000–0.107 | 0.2390.000–0.727 | 78.6%57.1%–100.0% | 100.0%100.0%–100.0% | 76.1%27.3%–100.0% | 76.1%27.3%–100.0% | 100.0%100.0%–100.0% | 2,326 ms2,123 ms–2,532 ms | 3,050 ms2,558 ms–3,370 ms | $0.0364$0.0267–$0.0456 |
| Blackjack · costlyClaude Sonnet 5 · calibration | 17/170 transport failures | 0.0390.000–0.116 | 0.0740.000–0.242 | 94.1%82.4%–100.0% | 100.0%100.0%–100.0% | 92.6%75.8%–100.0% | 92.6%75.8%–100.0% | 100.0%100.0%–100.0% | 1,710 ms1,640 ms–1,846 ms | 2,025 ms1,863 ms–2,035 ms | $0.0036$0.0036–$0.0036 |
| Blackjack · easyClaude Sonnet 5 · calibration | 15/150 transport failures | 0.0440.000–0.131 | 0.0830.000–0.310 | 93.3%80.0%–100.0% | 100.0%100.0%–100.0% | 91.7%69.0%–100.0% | 91.7%69.0%–100.0% | 100.0%100.0%–100.0% | 1,814 ms1,717 ms–1,989 ms | 2,110 ms1,995 ms–2,286 ms | $0.0036$0.0036–$0.0037 |
| Showdown Hold’em · borderlineClaude Sonnet 5 · sealed | 40/400 transport failures | 0.0520.032–0.076 | 0.6230.382–0.885 | 57.5%42.5%–72.5% | 82.5%70.0%–92.5% | 37.7%11.5%–61.8% | 46.6%14.9%–74.7% | 100.0%100.0%–100.0% | 7,427 ms6,039 ms–11,261 ms | 96,653 ms91,132 ms–97,462 ms | $0.0247$0.0161–$0.0347 |
| Showdown Hold’em · borderlineClaude Sonnet 5 · calibration | 10/100 transport failures | 0.0600.016–0.112 | 0.6510.173–1.237 | 60.0%30.0%–90.0% | 90.0%70.0%–100.0% | 34.9%0.0%–82.7% | 39.5%0.0%–88.4% | 100.0%100.0%–100.0% | 7,471 ms3,110 ms–15,126 ms | 63,872 ms11,514 ms–97,210 ms | $0.0185$0.0091–$0.0355 |
| Showdown Hold’em · overallClaude Sonnet 5 · calibration | 30/300 transport failures | 0.0790.022–0.156 | 0.1120.028–0.249 | 76.7%60.0%–90.0% | 86.7%73.3%–96.7% | 88.8%75.1%–97.2% | 97.4%92.7%–100.0% | 100.0%100.0%–100.0% | 8,841 ms6,941 ms–17,756 ms | 96,308 ms64,391 ms–97,954 ms | $0.0273$0.0169–$0.0387 |
| Showdown Hold’em · easyClaude Sonnet 5 · calibration | 20/200 transport failures | 0.0880.000–0.191 | 0.0870.000–0.222 | 85.0%70.0%–100.0% | 85.0%70.0%–100.0% | 91.3%77.8%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 9,120 ms6,751 ms–37,456 ms | 95,342 ms48,585 ms–97,954 ms | $0.0317$0.0181–$0.0464 |
| Showdown Hold’em · costlyClaude Sonnet 5 · calibration | 20/200 transport failures | 0.0880.000–0.191 | 0.0870.000–0.222 | 85.0%70.0%–100.0% | 85.0%70.0%–100.0% | 91.3%77.8%–100.0% | 100.0%100.0%–100.0% | 100.0%100.0%–100.0% | 9,120 ms6,751 ms–37,456 ms | 95,342 ms48,585 ms–97,954 ms | $0.0317$0.0181–$0.0464 |
| Video Poker · overallClaude Sonnet 5 · calibration | 30/300 transport failures | 0.0920.000–0.237 | 0.0250.000–0.072 | 90.0%76.7%–100.0% | 93.3%83.3%–100.0% | 97.5%92.8%–100.0% | 99.9%99.8%–100.0% | 100.0%100.0%–100.0% | 4,130 ms3,042 ms–5,933 ms | 70,826 ms11,946 ms–96,671 ms | $0.0151$0.0086–$0.0233 |
| Showdown Hold’em · overallClaude Sonnet 5 · sealed | 120/1200 transport failures | 0.0930.051–0.141 | 0.1410.073–0.227 | 77.5%70.0%–85.0% | 89.2%83.3%–94.2% | 85.9%77.3%–92.7% | 92.9%86.9%–97.3% | 100.0%100.0%–100.0% | 8,364 ms6,669 ms–11,027 ms | 95,043 ms90,749 ms–97,462 ms | $0.0233$0.0189–$0.0281 |
| Showdown Hold’em · easyClaude Sonnet 5 · sealed | 80/800 transport failures | 0.1130.049–0.186 | 0.1190.050–0.204 | 87.5%80.0%–93.8% | 92.5%86.3%–97.5% | 88.1%79.6%–95.0% | 94.7%88.8%–98.8% | 100.0%100.0%–100.0% | 9,952 ms6,340 ms–14,066 ms | 93,912 ms52,287 ms–98,939 ms | $0.0226$0.0175–$0.0282 |
| Showdown Hold’em · costlyClaude Sonnet 5 · sealed | 80/800 transport failures | 0.1130.049–0.186 | 0.1190.050–0.204 | 87.5%80.0%–93.8% | 92.5%86.3%–97.5% | 88.1%79.6%–95.0% | 94.7%88.8%–98.8% | 100.0%100.0%–100.0% | 9,952 ms6,340 ms–14,066 ms | 93,912 ms52,287 ms–98,939 ms | $0.0226$0.0175–$0.0282 |
| Video Poker · borderlineClaude Sonnet 5 · sealed | 41/410 transport failures | 0.1140.032–0.213 | 0.0970.028–0.184 | 68.3%53.7%–80.5% | 92.7%82.9%–100.0% | 90.3%81.6%–97.2% | 97.1%94.9%–98.7% | 100.0%100.0%–100.0% | 6,517 ms4,248 ms–26,830 ms | 85,500 ms50,677 ms–102,195 ms | $0.0249$0.0173–$0.0328 |
| Video Poker · overallClaude Sonnet 5 · sealed | 120/1200 transport failures | 0.1380.048–0.266 | 0.0300.010–0.067 | 85.8%79.2%–91.7% | 96.7%92.5%–99.2% | 97.0%93.3%–99.0% | 98.6%96.5%–99.8% | 100.0%100.0%–100.0% | 3,810 ms3,171 ms–4,592 ms | 59,869 ms39,372 ms–94,951 ms | $0.0143$0.0111–$0.0179 |
| Video Poker · costlyClaude Sonnet 5 · sealed | 51/510 transport failures | 0.1630.000–0.434 | 0.0190.000–0.060 | 96.1%90.2%–100.0% | 98.0%94.1%–100.0% | 98.1%94.0%–100.0% | 99.4%97.4%–100.0% | 100.0%100.0%–100.0% | 3,027 ms2,397 ms–3,982 ms | 17,025 ms6,972 ms–57,495 ms | $0.0094$0.0070–$0.0128 |
| Video Poker · easyClaude Sonnet 5 · sealed | 65/650 transport failures | 0.1820.011–0.407 | 0.0270.002–0.077 | 93.8%87.7%–98.5% | 98.5%95.4%–100.0% | 97.3%92.3%–99.8% | 98.5%95.6%–100.0% | 100.0%100.0%–100.0% | 3,237 ms2,594 ms–4,106 ms | 17,279 ms8,851 ms–22,303 ms | $0.0093$0.0074–$0.0122 |
| Video Poker · borderlineClaude Sonnet 5 · calibration | 9/90 transport failures | 0.3080.008–0.739 | 0.2480.006–0.572 | 66.7%33.3%–88.9% | 77.8%44.4%–100.0% | 75.2%42.8%–99.4% | 99.2%97.3%–100.0% | 100.0%100.0%–100.0% | 14,095 ms3,726 ms–92,089 ms | 94,838 ms32,541 ms–96,671 ms | $0.0324$0.0143–$0.0546 |
| Craps · overallClaude Sonnet 5 · calibration | 22/300 transport failures | 0.8070.510–1.160 | 2.0621.290–3.033 | 9.1%0.0%–23.1% | 100.0%100.0%–100.0% | 0.0%0.0%–0.0% | 0.0%0.0%–0.0% | 73.3%56.7%–86.7% | 4,923 ms4,422 ms–11,320 ms | 22,858 ms11,759 ms–23,580 ms | $0.0259$0.0236–$0.0282 |
| Craps · easyClaude Sonnet 5 · calibration | 22/300 transport failures | 0.8070.510–1.160 | 2.0621.290–3.033 | 9.1%0.0%–23.1% | 100.0%100.0%–100.0% | 0.0%0.0%–0.0% | 0.0%0.0%–0.0% | 73.3%56.7%–86.7% | 4,923 ms4,422 ms–11,320 ms | 22,858 ms11,759 ms–23,580 ms | $0.0259$0.0236–$0.0282 |
| Craps · borderlineClaude Sonnet 5 · calibration | 22/300 transport failures | 0.8070.510–1.160 | 2.0621.290–3.033 | 9.1%0.0%–23.1% | 100.0%100.0%–100.0% | 0.0%0.0%–0.0% | 0.0%0.0%–0.0% | 73.3%56.7%–86.7% | 4,923 ms4,422 ms–11,320 ms | 22,858 ms11,759 ms–23,580 ms | $0.0259$0.0236–$0.0282 |
| Craps · costlyClaude Sonnet 5 · calibration | 22/300 transport failures | 0.8070.510–1.160 | 2.0621.290–3.033 | 9.1%0.0%–23.1% | 100.0%100.0%–100.0% | 0.0%0.0%–0.0% | 0.0%0.0%–0.0% | 73.3%56.7%–86.7% | 4,923 ms4,422 ms–11,320 ms | 22,858 ms11,759 ms–23,580 ms | $0.0259$0.0236–$0.0282 |
| Craps · overallClaude Sonnet 5 · sealed | 30/1190 transport failures | 0.9220.615–1.309 | 1.9501.280–2.819 | 0.0%0.0%–0.0% | 96.7%88.5%–100.0% | 0.0%0.0%–0.0% | 0.0%0.0%–0.0% | 25.2%18.5%–32.8% | 5,512 ms4,364 ms–7,450 ms | 16,507 ms11,514 ms–19,529 ms | $0.0235$0.0223–$0.0249 |
| Craps · easyClaude Sonnet 5 · sealed | 30/1190 transport failures | 0.9220.615–1.309 | 1.9501.280–2.819 | 0.0%0.0%–0.0% | 96.7%88.5%–100.0% | 0.0%0.0%–0.0% | 0.0%0.0%–0.0% | 25.2%18.5%–32.8% | 5,512 ms4,364 ms–7,450 ms | 16,507 ms11,514 ms–19,529 ms | $0.0235$0.0223–$0.0249 |
| Craps · borderlineClaude Sonnet 5 · sealed | 30/1190 transport failures | 0.9220.615–1.309 | 1.9501.280–2.819 | 0.0%0.0%–0.0% | 96.7%88.5%–100.0% | 0.0%0.0%–0.0% | 0.0%0.0%–0.0% | 25.2%18.5%–32.8% | 5,512 ms4,364 ms–7,450 ms | 16,507 ms11,514 ms–19,529 ms | $0.0235$0.0223–$0.0249 |
| Craps · costlyClaude Sonnet 5 · sealed | 30/1190 transport failures | 0.9220.615–1.309 | 1.9501.280–2.819 | 0.0%0.0%–0.0% | 96.7%88.5%–100.0% | 0.0%0.0%–0.0% | 0.0%0.0%–0.0% | 25.2%18.5%–32.8% | 5,512 ms4,364 ms–7,450 ms | 16,507 ms11,514 ms–19,529 ms | $0.0235$0.0223–$0.0249 |
| Craps · overallClaude Sonnet 5 · sealed | 89/1190 transport failures | 0.9250.729–1.152 | 2.2421.764–2.765 | 0.0%0.0%–0.0% | 100.0%100.0%–100.0% | 0.0%0.0%–0.0% | 0.0%0.0%–0.0% | 74.8%67.2%–81.5% | 6,557 ms5,124 ms–7,295 ms | 31,826 ms18,706 ms–40,117 ms | $0.0262$0.0247–$0.0279 |
| Craps · easyClaude Sonnet 5 · sealed | 89/1190 transport failures | 0.9250.729–1.152 | 2.2421.764–2.765 | 0.0%0.0%–0.0% | 100.0%100.0%–100.0% | 0.0%0.0%–0.0% | 0.0%0.0%–0.0% | 74.8%67.2%–81.5% | 6,557 ms5,124 ms–7,295 ms | 31,826 ms18,706 ms–40,117 ms | $0.0262$0.0247–$0.0279 |
| Craps · borderlineClaude Sonnet 5 · sealed | 89/1190 transport failures | 0.9250.729–1.152 | 2.2421.764–2.765 | 0.0%0.0%–0.0% | 100.0%100.0%–100.0% | 0.0%0.0%–0.0% | 0.0%0.0%–0.0% | 74.8%67.2%–81.5% | 6,557 ms5,124 ms–7,295 ms | 31,826 ms18,706 ms–40,117 ms | $0.0262$0.0247–$0.0279 |
| Craps · costlyClaude Sonnet 5 · sealed | 89/1190 transport failures | 0.9250.729–1.152 | 2.2421.764–2.765 | 0.0%0.0%–0.0% | 100.0%100.0%–100.0% | 0.0%0.0%–0.0% | 0.0%0.0%–0.0% | 74.8%67.2%–81.5% | 6,557 ms5,124 ms–7,295 ms | 31,826 ms18,706 ms–40,117 ms | $0.0262$0.0247–$0.0279 |
| Craps · overallClaude Sonnet 5 · calibration | 8/300 transport failures | 1.0530.493–1.655 | 2.1410.891–3.861 | 0.0%0.0%–0.0% | 100.0%100.0%–100.0% | 0.0%0.0%–10.9% | 0.0%0.0%–10.9% | 26.7%13.3%–43.3% | 6,256 ms3,219 ms–15,568 ms | 26,917 ms7,667 ms–33,028 ms | $0.0259$0.0211–$0.0321 |
| Craps · easyClaude Sonnet 5 · calibration | 8/300 transport failures | 1.0530.493–1.655 | 2.1410.891–3.861 | 0.0%0.0%–0.0% | 100.0%100.0%–100.0% | 0.0%0.0%–10.9% | 0.0%0.0%–10.9% | 26.7%13.3%–43.3% | 6,256 ms3,219 ms–15,568 ms | 26,917 ms7,667 ms–33,028 ms | $0.0259$0.0211–$0.0321 |
| Craps · borderlineClaude Sonnet 5 · calibration | 8/300 transport failures | 1.0530.493–1.655 | 2.1410.891–3.861 | 0.0%0.0%–0.0% | 100.0%100.0%–100.0% | 0.0%0.0%–10.9% | 0.0%0.0%–10.9% | 26.7%13.3%–43.3% | 6,256 ms3,219 ms–15,568 ms | 26,917 ms7,667 ms–33,028 ms | $0.0259$0.0211–$0.0321 |
| Craps · costlyClaude Sonnet 5 · calibration | 8/300 transport failures | 1.0530.493–1.655 | 2.1410.891–3.861 | 0.0%0.0%–0.0% | 100.0%100.0%–100.0% | 0.0%0.0%–10.9% | 0.0%0.0%–10.9% | 26.7%13.3%–43.3% | 6,256 ms3,219 ms–15,568 ms | 26,917 ms7,667 ms–33,028 ms | $0.0259$0.0211–$0.0321 |