THE ISLAND GAME / DECISION MODELS
← All modelsMicrosoft

Microsoft-Decision-1

microsoft/microsoft-decision-1 · openrouter

Model source ↗
Completed games21
Wins8
Average points6.67
Fallback rate0.00%
Median latency1.049 s
Cost per game · USD$0.01
CHOICE CONFIDENCE

How certain were its picks?

53.7%

Mean top probability across 2,558 recorded full-menu distributions.

The histogram counts the chosen option's probability. Bins include the lower bound; the last bin includes 100%. Forced moves, bots and split questions are excluded. These odds describe the model's choice, not its chance of winning.

Chosen-option probability

Games

GameStageWinnerTurnsResult
Framing A/B, v1: Decision-1 vs Random bot vs Random bot vs Random bot ↗AB-ms-d1-v1-1Framing A/BRandom bot250guarded
Framing A/B, v1: Decision-1 vs Random bot vs Random bot vs Random bot ↗AB-ms-d1-v1-2Framing A/BRandom bot123winner
Framing A/B, v1: Decision-1 vs Random bot vs Random bot vs Random bot ↗AB-ms-d1-v1-3Framing A/BRandom bot250guarded
Framing A/B, v2: Decision-1 vs Random bot vs Random bot vs Random bot ↗AB-ms-d1-v2-1Framing A/BDecision-1114winner
Framing A/B, v2: Decision-1 vs Random bot vs Random bot vs Random bot ↗AB-ms-d1-v2-2Framing A/BRandom bot84winner
Framing A/B, v2: Decision-1 vs Random bot vs Random bot vs Random bot ↗AB-ms-d1-v2-3Framing A/BDecision-1190winner
Qualifier, round 1: Decision-1 vs Random bot vs Random bot vs Random bot ↗S0-ms-d1-1QualifierRandom bot250guarded
Qualifier, round 2: Random bot vs Random bot vs Random bot vs Decision-1 ↗S0-ms-d1-4QualifierDecision-1185winner
League, round 1, table 1: Tev1 4B vs Decision-1 vs Kev 4B vs ScaleDown Classify-1 ↗S1-R1-T1LeagueDecision-1179winner
League, round 2, table 2: Mercury Decide vs Drex v2.0 vs Decision-1 vs Perplexity Decider ↗S1-R2-T2LeagueDecision-1124winner
League, round 3, table 1: Jev 1.14 vs Solar Decide vs Perplexity Decider vs Decision-1 ↗S1-R3-T1LeagueJev 1.1482winner
League, round 4, table 2: Drex v2.0 vs Decision-1 vs Liquid d1 vs Tev1 4B ↗S1-R4-T2LeagueDrex v2.0170winner
League, round 5, table 2: Decision-1 vs Luna vs Solar Decide vs Liquid d1 ↗S1-R5-T2LeagueLiquid d1101winner
League, round 6, table 3: Decision-1 vs Clef-omni vs Tev1 4B vs Jev 1.14 ↗S1-R6-T3LeagueDecision-1166winner
Playoffs, final, round 1: Mercury Decide vs Decision-1 vs Luna vs Perplexity Decider ↗S2-F-G1PlayoffsLuna120winner
Playoffs, final, round 2: Decision-1 vs Luna vs Perplexity Decider vs Mercury Decide ↗S2-F-G2PlayoffsPerplexity Decider100winner
Playoffs, final, round 3: Luna vs Perplexity Decider vs Mercury Decide vs Decision-1 ↗S2-F-G3PlayoffsDecision-1169winner
Playoffs, semifinal, round 1, table 1: Decision-1 vs Mercury Decide vs Liquid d1 vs Drex v2.0 ↗S2-SF1-G1PlayoffsMercury Decide143winner
Playoffs, semifinal, round 2, table 1: Mercury Decide vs Liquid d1 vs Drex v2.0 vs Decision-1 ↗S2-SF1-G2PlayoffsMercury Decide102winner
Boss ladder, level 1: Decision-1 vs Greedy bot vs Greedy bot vs Greedy bot ↗S3-ms-d1-L1Boss ladderDecision-1162winner
Boss ladder, level 2: Decision-1 vs Value bot vs Value bot vs Value bot ↗S3-ms-d1-L2Boss ladderValue bot79winner

Games, wins and average points use completed games, including A/B. Fallback rate uses non-forced model decisions, including incomplete games. Median latency includes retries. Cost per game uses completed appearances only.