Skip to content
decisionbench
OverallSudokuRulebookConsistencyOdds

Independent benchmark. Not affiliated with or endorsed by OpenRouter or any model provider. Company and model names are trademarks of their respective owners.

How ranking worksPrivacyTermsContact

© 2026 editid0

← Odds leaderboard

Classify-1

ScaleDown · scaledown/classify-1 · added 20 Oct 2026

Classify-1 by ScaleDown ranks #15 of 17 AI decision models on the DecisionBench Odds benchmark (weighing risk), with score 33.5%. View on OpenRouter.

Overall#17Sudoku#16Rulebook#16Consistency#16Odds#15
Odds rank
#15 of 17
Score
33.5%
Value captured
55.3%
Odds within 2×
11.7%
Odds off by
×8.8
Leans
over ×7.4

60 cases · best action 40% of the time · acts on its own odds 43% of the time · $0.0556 per 1,000 cases · 449 ms per case

Every case

The probability the model gave and the right one (✓ when its odds are within 2×), the action it picked, and how much of the available expected payoff that action earns.

CaseSituationProbabilityActionValue
O-1000 · EasyOnline order #512643: $120 basket✕ 57% / 2%✓ ship the order100%
O-1001 · Rare outcomeSmall-business loan application: $10,000 over 3 years✕ 61% / 9%✕ decline the loan → approve the loan0%
O-1002 · Adds upBoiler feed pump on line 7, 6 years in service✕ 67% / 81%✓ replace the part now100%
O-1003 · Missing clueInbound demo request, $9,850 first-year deal✕ 56% / 9%✕ assign a sales rep → drop the lead0%
O-1004 · Red herringOnline order #428497: $170 basket✕ 68% / 11%✕ hold for manual review → ship the order35%
O-1005 · High stakesSmall-business loan application: $5,000 over 5 years✕ 62% / 8%✕ approve the loan → decline the loan53%
O-1006 · EasyInbound demo request, $8,450 first-year deal✕ 60% / 1%✕ assign a sales rep → drop the lead0%
O-1007 · Rare outcomeOnline order #527243: $100 basket✕ 68% / 25%✕ ship the order → hold for manual review60%
O-1008 · Adds upSmall-business loan application: $128,000 over 2 years✕ 70% / 44%✕ approve the loan → approve only against collateral0%
O-1009 · Missing clueConveyor gearbox on line 7, 4 years in service✕ 62% / 43%✕ replace the part now → stop it for an inspection95%
O-1010 · Red herringInbound demo request, $5,500 first-year deal✕ 66% / 34%✕ assign a sales rep → send the automated email sequence56%
O-1011 · High stakesOnline order #736444: $190 basket✕ 51% / 6%✓ hold for manual review100%
O-1012 · EasyPress motor on line 9, 12 years in service✕ 67% / 30%✕ keep it running → stop it for an inspection0%
O-1013 · Rare outcomeInbound demo request, $2,200 first-year deal✕ 64% / 5%✕ assign a sales rep → drop the lead71%
O-1014 · Adds upOnline order #735461: $310 basket✓ 58% / 68%✕ ship the order → cancel the order0%
O-1015 · Missing clueSmall-business loan application: $22,000 over 3 years✕ 64% / 6%✓ approve the loan100%
O-1016 · Red herringConveyor gearbox on line 2, 10 years in service✕ 71% / 10%✕ replace the part now → keep it running0%
O-1017 · High stakesInbound demo request, $3,450 first-year deal✕ 66% / 4%✓ assign a sales rep100%
O-1018 · EasySmall-business loan application: $6,000 over 5 years✕ 54% / 4%✓ approve the loan100%
O-1019 · Rare outcomeCoolant pump on line 4, 10 years in service✕ 60% / 8%✕ replace the part now → stop it for an inspection64%
O-1020 · Adds upInbound demo request, $5,800 first-year deal✕ 67% / 46%✕ assign a sales rep → send the automated email sequence64%
O-1021 · Missing clueOnline order #590697: $95 basket✕ 60% / 24%✕ ship the order → hold for manual review0%
O-1022 · Red herringSmall-business loan application: $21,000 over 3 years✕ 59% / 37%✓ approve only against collateral100%
O-1023 · High stakesCoolant pump on line 2, 15 years in service✕ 59% / 2%✓ stop it for an inspection100%
O-1024 · EasyOnline order #426231: $175 basket✓ 40% / 52%✕ ship the order → cancel the order0%
O-1025 · Rare outcomeSmall-business loan application: $77,000 over 2 years✕ 65% / 6%✕ decline the loan → approve the loan0%
O-1026 · Adds upConveyor gearbox on line 9, 14 years in service✓ 68% / 80%✕ keep it running → replace the part now0%
O-1027 · Missing clueInbound demo request, $3,200 first-year deal✕ 63% / 22%✕ assign a sales rep → drop the lead0%
O-1028 · Red herringOnline order #599758: $73 basket✕ 46% / 16%✓ ship the order100%
O-1029 · High stakesSmall-business loan application: $112,000 over 3 years✕ 63% / 10%✓ decline the loan100%
O-1030 · EasyInbound demo request, $31,000 first-year deal✕ 56% / 5%✓ send the automated email sequence100%
O-1031 · Rare outcomeOnline order #973229: $545 basket✕ 63% / 23%✕ cancel the order → hold for manual review84%
O-1032 · Adds upSmall-business loan application: $21,000 over 2 years✓ 55% / 52%✓ approve only against collateral100%
O-1033 · Missing clueBoiler feed pump on line 2, 4 years in service✕ 60% / 31%✕ replace the part now → stop it for an inspection90%
O-1034 · Red herringInbound demo request, $2,400 first-year deal✕ 57% / 12%✕ assign a sales rep → send the automated email sequence0%
O-1035 · High stakesOnline order #380045: $700 basket✕ 54% / 8%✓ hold for manual review100%
O-1036 · EasyPress motor on line 2, 10 years in service✕ 71% / 1%✕ replace the part now → keep it running0%
O-1037 · Rare outcomeInbound demo request, $3,250 first-year deal✕ 64% / 9%✕ assign a sales rep → drop the lead0%
O-1038 · Adds upOnline order #820072: $71 basket✕ 53% / 87%✕ ship the order → cancel the order0%
O-1039 · Missing clueSmall-business loan application: $52,000 over 5 years✕ 54% / 6%✓ approve the loan100%
O-1040 · Red herringCoolant pump on line 1, 14 years in service✕ 64% / 20%✕ stop it for an inspection → keep it running80%
O-1041 · High stakesInbound demo request, $2,700 first-year deal✕ 53% / 4%✓ assign a sales rep100%
O-1042 · EasySmall-business loan application: $17,000 over 5 years✕ 69% / 43%✕ approve the loan → decline the loan0%
O-1043 · Rare outcomeBoiler feed pump on line 7, 14 years in service✕ 61% / 21%✕ keep it running → stop it for an inspection0%
O-1044 · Adds upInbound demo request, $2,650 first-year deal✕ 71% / 50%✕ assign a sales rep → send the automated email sequence70%
O-1045 · Missing clueOnline order #739291: $185 basket✓ 61% / 57%✓ hold for manual review100%
O-1046 · Red herringSmall-business loan application: $15,000 over 3 years✕ 62% / 12%✓ approve only against collateral100%
O-1047 · High stakesAir compressor on line 8, 14 years in service✕ 57% / 6%✕ replace the part now → stop it for an inspection0%
O-1048 · EasyOnline order #728467: $440 basket✓ 57% / 53%✓ hold for manual review100%
O-1049 · Rare outcomeSmall-business loan application: $11,000 over 2 years✕ 71% / 6%✕ approve only against collateral → approve the loan93%
O-1050 · Adds upAir compressor on line 7, 7 years in service✕ 64% / 84%✕ keep it running → replace the part now0%
O-1051 · Missing clueInbound demo request, $3,250 first-year deal✕ 69% / 11%✕ assign a sales rep → drop the lead0%
O-1052 · Red herringOnline order #552300: $43 basket✕ 53% / 22%✓ ship the order100%
O-1053 · High stakesSmall-business loan application: $13,000 over 5 years✕ 63% / 6%✕ approve only against collateral → decline the loan0%
O-1054 · EasyInbound demo request, $84,500 first-year deal✕ 64% / 39%✓ assign a sales rep100%
O-1055 · Rare outcomeOnline order #914426: $705 basket✕ 47% / 20%✓ hold for manual review100%
O-1056 · Adds upSmall-business loan application: $114,000 over 2 years✓ 55% / 44%✓ approve only against collateral100%
O-1057 · Missing clueBoiler feed pump on line 7, 14 years in service✕ 61% / 8%✓ stop it for an inspection100%
O-1058 · Red herringInbound demo request, $3,750 first-year deal✕ 57% / 19%✕ drop the lead → send the automated email sequence0%
O-1059 · High stakesOnline order #381274: $720 basket✕ 41% / 7%✓ hold for manual review100%

Probability: the model's answer / the right one. Value: 100% for the best action, 0% for the worst. A case is worked through on the Odds page.

Classify-1 across all benchmarks · How Odds works