Model Leaderboard
Prediction accuracy across premium tier matches · 397/624 settled
#1
73.3%
Nexus
META: 3-way consensus of Apex + Oracle + Eagle with avg confidence >55%.
33 ✓ / 45
12 wrong
#2
70.0%
Oracle
Conservative: Elo HQ dampened when streaks disagree.
14 ✓ / 20
6 wrong
#3
69.6%
Streak
Win/loss streak signal blended with Elo.
16 ✓ / 23
7 wrong
#4
66.1%
Roster Change
Penalty for unstable rosters — fresh lineups underperform Elo.
37 ✓ / 56
19 wrong
#5
65.5%
SOS
Strength of schedule: form weighted by opponent quality.
19 ✓ / 29
10 wrong
#6
65.0%
Consensus
META: triggers when ≥75% of base models converge on same side.
13 ✓ / 20
7 wrong
#7
63.8%
Fatigue
Dota-specific: penalty for back-to-back matches (<12h apart).
44 ✓ / 69
25 wrong
#8
63.2%
Elo H2H
Standard head-to-head Elo, scale=400.
43 ✓ / 68
25 wrong
#9
62.7%
Apex
Blend: Elo + form + streak — momentum-aware ensemble pick.
42 ✓ / 67
25 wrong
#10
62.7%
Eagle
Blend: Elo + WR10 + form — weighted toward top-tier record.
42 ✓ / 67
25 wrong
#11
60.0%
Form
Pure win-rate over last 10 matches.
15 ✓ / 25
10 wrong
#12
60.0%
Patch-Aware
Elo with patch-boundary decay — stale form loses weight after Valve patches.
12 ✓ / 20
8 wrong
◉
Calibrating — fewer than 20 settled predictions on this tier. Ranking appears once more matches complete.
63.2%
Elo HQ
High-confidence Elo: smaller K-factor, scale=2000 — slow learner.
calibrating (19/20)
◉
Calibrating — fewer than 20 settled predictions on this tier. Ranking appears once more matches complete.
57.9%
Tier Elo
Elo computed only from matches against top-30 teams.
calibrating (19/20)
◉
Calibrating — fewer than 20 settled predictions on this tier. Ranking appears once more matches complete.
66.7%
WR10
Win-rate vs top-10 opponents, blended with Elo.
calibrating (18/20)
◉
Calibrating — fewer than 20 settled predictions on this tier. Ranking appears once more matches complete.
53.8%
Phantom
High-conviction: only commits when Elo + WR10 strongly agree.
calibrating (13/20)
◉
Calibrating — fewer than 20 settled predictions on this tier. Ranking appears once more matches complete.
50.0%
Meta Strength
Team's recent hero pool weighted by current meta winrates.
calibrating (14/20)
◉
Calibrating — fewer than 20 settled predictions on this tier. Ranking appears once more matches complete.
57.9%
Synergy
Hero co-occurrence winrates within recent team lineups.
calibrating (19/20)
◉
Calibrating — fewer than 20 settled predictions on this tier. Ranking appears once more matches complete.
53.8%
Vanguard
META: fires only when Elo and WR10 strongly agree (>60% same side).
calibrating (13/20)
Accuracy is measured per tournament tier — Premium is the clean, high-signal subset (mirrors cs2predict's top tier). Models with fewer than 20 settled predictions on the selected tier are calibrating. Coin-flip predictions (48–52%) are excluded. Click a model for confidence buckets, Brier score, and recent picks.