La Liga Week 23 AI Model Predictions Audit & Accuracy Stats
Qwen 2.5 7B Turbo led La Liga predictions this week with 2.25 avg points/match, followed by Llama 4 Maverick and Nemotron Nano 9B v2 at 2.13. Models achieved 35.52% correct tendency overall, with the 0-1 Atletico Madrid vs Real Betis result catching most models off guard.
Qwen 2.5 7B Turbo led La Liga predictions this week with 2.25 avg points/match, followed by Llama 4 Maverick and Nemotron Nano 9B v2 at 2.13. Models achieved 35.52% correct tendency overall, with the 0-1 Atletico Madrid vs Real Betis result catching most models off guard.
La Liga Regular Season - 23 featured 8 matches, including high-profile fixtures like Valencia vs Real Madrid and Barcelona vs Mallorca. AI prediction accuracy is critical for evaluating model reliability in competitive scenarios. This audit examines statistical performance across all predictions.
Top 10 Models
| # | Model | Matches | Total Points | Avg Pts/Match | Tendency % | Exact % |
|---|---|---|---|---|---|---|
| 1 | Qwen 2.5 7B Turbo (Alibaba) | 8 | 18 | 2.25 | 50.0% | 12.5% |
| 2 | Llama 4 Maverick (Meta) | 8 | 17 | 2.13 | 50.0% | 12.5% |
| 3 | Nemotron Nano 9B v2 (NVIDIA) | 8 | 17 | 2.13 | 50.0% | 12.5% |
| 4 | Gemma 3n E4B (Google) | 8 | 17 | 2.13 | 50.0% | 12.5% |
| 5 | Marin 8B Instruct (Marin Community) | 8 | 17 | 2.13 | 62.5% | 0.0% |
| 6 | Llama 3.3 70B Turbo (Meta) | 8 | 15 | 1.88 | 37.5% | 12.5% |
| 7 | Llama 3.2 3B Turbo (Meta) | 8 | 14 | 1.75 | 50.0% | 0.0% |
| 8 | Kimi K2 Thinking (Synthetic) | 8 | 14 | 1.75 | 50.0% | 12.5% |
| 9 | Qwen3 Coder 480B (Synthetic) | 3 | 5 | 1.67 | 66.7% | 0.0% |
| 10 | MiniMax M2 (Synthetic) | 8 | 12 | 1.50 | 50.0% | 0.0% |
Match-by-Match Audit
- Valencia vs Real Madrid (0-2): Correct tendency 88.9%, exact score hits 3.7%, consensus A (88.9%) correct.
- Atletico Madrid vs Real Betis (0-1): Correct tendency 3.8%, exact score hits 0.0%, consensus H (61.5%) incorrect.
- Athletic Club vs Levante (4-2): Correct tendency 32.0%, exact score hits 0.0%, consensus D (56.0%) incorrect.
- Alaves vs Getafe (0-2): Correct tendency 7.4%, exact score hits 0.0%, consensus D (77.8%) incorrect.
- Real Sociedad vs Elche (3-1): Correct tendency 51.9%, exact score hits 0.0%, consensus H (51.9%) correct.
- Sevilla vs Girona (1-1): Correct tendency 11.1%, exact score hits 7.4%, consensus A (81.5%) incorrect.
- Barcelona vs Mallorca (3-0): Correct tendency 73.1%, exact score hits 7.7%, consensus H (73.1%) correct.
- Celta Vigo vs Osasuna (1-2): Correct tendency 16.0%, exact score hits 16.0%, consensus D (52.0%) incorrect.
Biggest Consensus Misses
- Sevilla vs Girona (1-1) | Consensus: A (81.5%) | Counts H/D/A: 2/3/22
- Alaves vs Getafe (0-2) | Consensus: D (77.8%) | Counts H/D/A: 4/21/2
- Atletico Madrid vs Real Betis (0-1) | Consensus: H (61.5%) | Counts H/D/A: 16/9/1
- Athletic Club vs Levante (4-2) | Consensus: D (56.0%) | Counts H/D/A: 8/14/3
- Celta Vigo vs Osasuna (1-2) | Consensus: D (52.0%) | Counts H/D/A: 8/13/4
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 - 23? A: Qwen 2.5 7B Turbo (Alibaba) performed best with 2.25 average points per match.
Q: How accurate were AI predictions for La Liga this round? A: Models achieved 35.52% correct tendency and 4.35% exact score hit rate across 8 matches.
Q: What was the biggest upset in La Liga Regular Season - 23? A: Atletico Madrid vs Real Betis (0-1) was the biggest consensus miss, with 61.5% predicting a home win.
Q: How does kroam.xyz score AI football predictions? A: Points are awarded based on tendency accuracy (2-6 pts), goal difference bonus (+1 pt), and exact score bonus (+3 pts), with a maximum of 10 points per prediction.
Generation cost: $0.0058
Tokens: 4,600 input + 1,790 output
Frequently Asked Questions
What is this article about?
Which AI model performed best in La Liga Regular Season - 23?**?
Q: Which AI model performed best in La Liga Regular Season - 23?
Q: How accurate were AI predictions for La Liga this round?
You might also like
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.
Feb 23, 2026
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.