CS2PREDCT.gg
Match Prediction Engine
Top models accuracy · top-tier TRIBUNAL 87.1%    STRONGHOLD 86.4%    VANGUARD 86.1%    SENTINEL 85.2%    NEXUS 84.1%    TIER3ELO 82.8%    TIERELO 81.1%    TIER2ELO 77.9%    HIGHORACLE 77.3%    ELOHQ 76.6%   
Last refresh: 2026-05-19 00:00 UTC · Next: 5 min

Model Leaderboard

Prediction accuracy across major tier matches

Top Major All
Calibrating — less than 20 predictions. Ranking available after more data is collected.
APEXPro
ELO + Form + Streak + SOS (optimized)
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
EAGLEFree
Rank + ELO + ELOHQ + Form + WinRate
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
ELOFree
Team ELO rating
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
ELOFACEBasic
ELO + training activity
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
ELOHQPro
High-confidence ELO
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
FORMFree
Win rate last 10 matches
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
HIGH-ORACLEPro
Oracle filtered to high confidence only (>67%)
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
MAJORBasic
Rank + H2H + Form for major events
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
MINDBasic
Psychology + tilt + H2H
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
NEXUSPro
APEX + ORACLE both >65% same direction
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
OPENBasic
Rank + form + head-to-head
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
ORACLEPro
ELO + ELOHQ + Form + Tilt + SOS
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
PHANTOMPro
ELO + TierELO + WinRate + Tilt (max accuracy)
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
XGPROBasic
Rank + H2H for top matches
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
SENTINELPro
Anti-signal: SOS >60% confirmed by Mind anti-prediction
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
SOSBasic
Rank + form + opponent strength
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
SQUADFree
Player ratings
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
STREAKPro
Rank + H2H + win/loss streak
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
STRONGHOLDPro
ELO + SOS both >60% same direction
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
TIER2Pro
Top-teams ELO v2
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
TIER3Pro
Top-teams ELO v3
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
TIERPro
ELO for top-30 teams
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
TRIBUNALPro
OPEN + PRO + ORACLE all >55% same direction
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
VANGUARDPro
Sharp consensus: ELO + WR10 both >65% same direction
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
WR10Pro
Rank + H2H + win rate vs top-10
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
WR10CFree
Win rate top-10 + ELO + form
calibrating (0/20)
Calibrating — less than 20 predictions. Ranking available after more data is collected.
WR10PFree
Pure win rate vs top-10
calibrating (0/20)
CS2PREDICT v2.0 · statistical analysis & AI predictions for informational and entertainment purposes only. 18+ · About · FAQ · Guides · Embed · Terms · Privacy · NCPG · BeGambleAware · © 2026 cs2predict.gg