La Liga Round 25 AI Model Performance: Top Predictors & Accuracy
MiniMax M2.5 led La Liga predictions with 3.22 points per match, followed by Gemma 3 12B (3.00) and DeepSeek R1-0528 (2.56). Models achieved 38.60% correct tendency overall, with Real Sociedad vs Oviedo (3-3) being the biggest consensus miss.
MiniMax M2.5 led La Liga predictions with 3.22 points per match, followed by Gemma 3 12B (3.00) and DeepSeek R1-0528 (2.56). Models achieved 38.60% correct tendency overall, with Real Sociedad vs Oviedo (3-3) being the biggest consensus miss. La Liga Regular Season - 25 featured 9 matches, including notable fixtures involving top teams. Accurate AI predictions are critical for benchmarking model reliability in competitive scenarios. The data reveals key performance metrics across all matches.
Top 10 Models
| # | Model | Matches | Total Points | Avg Pts/Match | Tendency % | Exact % |
|---|---|---|---|---|---|---|
| 1 | MiniMax M2.5 (OpenRouter) | 9 | 29 | 3.22 | 55.6% | 33.3% |
| 2 | Gemma 3 12B (OpenRouter) | 9 | 27 | 3.00 | 55.6% | 33.3% |
| 3 | DeepSeek R1-0528 (OpenRouter) | 9 | 23 | 2.56 | 55.6% | 11.1% |
| 4 | Trinity Large Preview (OpenRouter) | 9 | 23 | 2.56 | 55.6% | 22.2% |
| 5 | GLM-5 (OpenRouter) | 9 | 20 | 2.22 | 44.4% | 22.2% |
| 6 | GPT-OSS 20B (OpenRouter) | 9 | 19 | 2.11 | 44.4% | 22.2% |
| 7 | Gemma 3 27B (OpenRouter) | 9 | 18 | 2.00 | 44.4% | 22.2% |
| 8 | Llama 4 Scout (OpenRouter) | 9 | 16 | 1.78 | 44.4% | 11.1% |
| 9 | GLM-4.7 (OpenRouter) | 9 | 16 | 1.78 | 44.4% | 11.1% |
| 10 | Kimi K2.5 (OpenRouter) | 9 | 15 | 1.67 | 33.3% | 22.2% |
Match-by-Match Audit
- Villarreal vs Valencia (2-1): Correct tendency: 31.6%, exact score hits: 31.6%, consensus: D (57.9%) incorrect.
- Celta Vigo vs Mallorca (2-0): Correct tendency: 42.1%, exact score hits: 5.3%, consensus: D (57.9%) incorrect.
- Barcelona vs Levante (3-0): Correct tendency: 100.0%, exact score hits: 26.3%, consensus: H (100.0%) correct.
- Getafe vs Sevilla (0-1): Correct tendency: 36.8%, exact score hits: 5.3%, consensus: D (52.6%) incorrect.
- Atletico Madrid vs Espanyol (4-2): Correct tendency: 31.6%, exact score hits: 0.0%, consensus: D (63.2%) incorrect.
- Osasuna vs Real Madrid (2-1): Correct tendency: 0.0%, exact score hits: 0.0%, consensus: A (84.2%) incorrect.
- Real Betis vs Rayo Vallecano (1-1): Correct tendency: 73.7%, exact score hits: 73.7%, consensus: D (73.7%) correct.
- Real Sociedad vs Oviedo (3-3): Correct tendency: 10.5%, exact score hits: 0.0%, consensus: H (89.5%) incorrect.
- Athletic Club vs Elche (2-1): Correct tendency: 21.1%, exact score hits: 10.5%, consensus: D (73.7%) incorrect.
Biggest Consensus Misses
- Real Sociedad vs Oviedo (3-3) | Consensus: H (89.5%) | Counts H/D/A: 17/2/0
- Osasuna vs Real Madrid (2-1) | Consensus: A (84.2%) | Counts H/D/A: 0/3/16
- Athletic Club vs Elche (2-1) | Consensus: D (73.7%) | Counts H/D/A: 4/14/1
- Atletico Madrid vs Espanyol (4-2) | Consensus: D (63.2%) | Counts H/D/A: 6/12/1
- Villarreal vs Valencia (2-1) | Consensus: D (57.9%) | Counts H/D/A: 6/11/2
Methodology
kroam.xyz uses a quota-based scoring system that rewards both accuracy and boldness:
Tendency Points (2-6 points): Models earn points for correctly predicting the match outcome (home win, draw, or away win). The points awarded depend on prediction rarity—if most models predicted a home win but the away team won, models who correctly predicted the away win earn more points (up to 6). Common predictions earn fewer points (minimum 2).
Goal Difference Bonus (+1 point): If the model predicts the correct goal difference (e.g., predicted 2-1 and result was 3-2, both +1 difference), they earn a bonus point.
Exact Score Bonus (+3 points): Predicting the exact final score earns 3 additional points.
Maximum: 10 points per prediction (6 tendency + 1 goal diff + 3 exact).
This system ensures that models taking calculated risks on unlikely outcomes are rewarded when correct, while also recognizing precision in exact score predictions. Learn more about our methodology.
Frequently Asked Questions
Q: Which AI model performed best in La Liga Regular Season - 25? A: MiniMax M2.5 (OpenRouter) performed best with an average of 3.22 points per match.
Q: How accurate were AI predictions for La Liga this round? A: The average correct tendency was 38.60%, and the exact score hit rate was 16.96%.
Q: What was the biggest upset in La Liga Regular Season - 25? A: Real Sociedad vs Oviedo (3-3) was the biggest consensus miss, with 89.5% of models incorrectly predicting a home win.
Q: How does kroam.xyz score AI football predictions? A: kroam.xyz uses a quota-based system awarding up to 10 points per prediction for tendency, goal difference, and exact score accuracy.
Generation cost: $0.0021
Tokens: 4,845 input + 1,804 output
Frequently Asked Questions
What is this article about?
Which AI model performed best in La Liga Regular Season - 25?**?
Q: Which AI model performed best in La Liga Regular Season - 25?
Q: How accurate were AI predictions for La Liga this round?
You might also like
La Liga Week 24 AI Model Audit: Top Performers & Accuracy
Phi-4 led La Liga predictions with 3.50 points per match, followed by Trinity Large Preview and Gemma 3 12B (both 3.25). Models achieved 39.99% correct tendency overall, with the Getafe vs Villarreal (2-1) result catching all models off guard.
Feb 16, 2026
UEFA Europa League Round of 32 AI Model Performance Audit
GLM-5 (OpenRouter) led UEFA Europa League predictions this week with 3.25 points per match, followed by Llama 4 Scout (OpenRouter) at 2.88 and Mistral Small 3.2 24B (OpenRouter) at 2.25. Models achieved 52.63% correct tendency overall, though Ludogorets vs Ferencvarosi TC (2-1) caught most models off guard.
Feb 23, 2026
UEFA Conference League Round of 32 AI Prediction Audit
Trinity Large Preview led with 3.13 points per match, followed by Phi-4 (2.38) and Kimi K2.5 (2.13). Models achieved 33.19% correct tendency overall, with FC Noah's 1-0 win over AZ Alkmaar being the biggest surprise.