Ligue 1 AI Predictions Audit - Regular Season Week 24 Analysis
MiniMax M2.1 led with 2.78 avg points/match, followed by GLM-5 (2.44) and GPT-OSS 20B (2.22). Models achieved 50.19% correct tendency overall. The Paris FC vs Nice upset (1-0 result vs 78.9% consensus draw) was the biggest surprise.
MiniMax M2.1 led Ligue 1 predictions this week with 2.78 average points per match, followed by GLM-5 (2.44) and GPT-OSS 20B (2.22). AI models achieved 50.19% correct tendency across 9 matches. The Paris FC vs Nice result (1-0) was the biggest upset, with 78.9% consensus predicting a draw.
This audit covers Regular Season - 24 with 9 Ligue 1 matches. Accurate AI predictions are crucial for benchmarking model performance in competitive football analysis.
Top 10 Models
| Rank | Model | Matches | Avg Pts/Match | Tendency % | Exact % |
|---|---|---|---|---|---|
| 1 | MiniMax M2.1 (OpenRouter) | 9 | 2.78 | 66.7% | 22.2% |
| 2 | GLM-5 (OpenRouter) | 9 | 2.44 | 66.7% | 22.2% |
| 3 | GPT-OSS 20B (OpenRouter) | 9 | 2.22 | 66.7% | 11.1% |
| 4 | MiniMax M2.5 (OpenRouter) | 9 | 2.11 | 55.6% | 22.2% |
| 5 | Kimi K2.5 (OpenRouter) | 9 | 2.00 | 66.7% | 0.0% |
| 6 | Mistral Small 3.2 24B (OpenRouter) | 9 | 2.00 | 55.6% | 0.0% |
| 7 | Devstral 2 (OpenRouter) | 9 | 1.78 | 55.6% | 11.1% |
| 8 | Gemma 3 12B (OpenRouter) | 9 | 1.67 | 55.6% | 0.0% |
| 9 | Llama 3.3 70B Instruct (OpenRouter) | 9 | 1.67 | 44.4% | 11.1% |
| 10 | DeepSeek R1-0528 (OpenRouter) | 9 | 1.56 | 55.6% | 0.0% |
Match-by-Match Audit
- Marseille vs Lyon (3-2): 16.7% correct tendency, consensus away win (50.0%) incorrect
- Lorient vs Auxerre (2-2): 47.4% correct tendency, consensus home win (47.4%) incorrect
- Metz vs Stade Brestois 29 (0-1): 66.7% correct tendency, consensus away win (66.7%) correct
- Lille vs Nantes (1-0): 73.7% correct tendency, consensus home win (73.7%) correct
- Paris FC vs Nice (1-0): 0.0% correct tendency, consensus draw (78.9%) incorrect
- Le Havre vs Paris Saint Germain (0-1): 89.5% correct tendency, consensus away win (89.5%) correct
- Monaco vs Angers (2-0): 68.4% correct tendency, consensus home win (68.4%) correct
- Rennes vs Toulouse (1-0): 31.6% correct tendency, consensus draw (68.4%) incorrect
- Strasbourg vs Lens (1-1): 57.9% correct tendency, consensus draw (57.9%) correct
Biggest Consensus Misses
- Paris FC vs Nice (1-0): Consensus draw (78.9%) incorrect
- Rennes vs Toulouse (1-0): Consensus draw (68.4%) incorrect
- Marseille vs Lyon (3-2): Consensus away win (50.0%) incorrect
- Lorient vs Auxerre (2-2): Consensus home win (47.4%) incorrect
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 Ligue 1 Regular Season - 24? A: MiniMax M2.1 performed best with 2.78 average points per match across 9 matches.
Q: How accurate were AI predictions for Ligue 1 this round? A: AI models achieved 50.19% correct tendency and 7.02% exact score hit rate across 169 total predictions.
Q: What was the biggest upset in Ligue 1 Regular Season - 24? A: Paris FC vs Nice (1-0) was the biggest upset, with 78.9% consensus predicting a draw.
Q: How does kroam.xyz score AI football predictions? A: kroam.xyz uses a quota-based system rewarding correct tendency (2-6 points), goal difference bonus (+1 point), and exact score bonus (+3 points), with maximum 10 points per match.
Generation cost: $0.0019
Tokens: 4,855 input + 1,613 output
Frequently Asked Questions
What is this article about?
Which AI model performed best in Ligue 1 Regular Season - 24?**?
Q: Which AI model performed best in Ligue 1 Regular Season - 24?
Q: How accurate were AI predictions for Ligue 1 this round?
You might also like
Ligue 1 Week 23 AI Model Performance Audit
GLM-4.7 led Ligue 1 predictions with 3.22 points per match, followed by Qwen3 30B A3B (2.67) and MiniMax M2.5 (1.89). Models achieved 34.50% correct tendency overall, with Nantes' 2-0 win over Le Havre being the biggest consensus miss.
Feb 23, 2026
UEFA Conference League Round of 32 AI Prediction Audit
GPT-OSS 20B led UEFA Conference League predictions with 2.88 points per match, followed by Trinity Large Preview (2.63) and GLM-5 (2.25). Models achieved 38.16% correct tendency overall, with Fiorentina vs Jagiellonia (2-4) as the biggest upset.
Mar 2, 2026
UEFA Europa League Round of 32 AI Model Performance Audit
Mistral Small 3.2 24B led predictions with 3.38 avg points/match, followed by Phi-4 (2.88) and Llama 4 Scout (2.75). Models achieved 38.82% correct tendency. VfB Stuttgart's 0-1 loss to Celtic was the biggest consensus miss.
Mar 2, 2026