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.
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. Ligue 1 Regular Season - 23 featured 9 matches with varied prediction challenges across fixtures. AI model accuracy is critical for assessing performance in competitive rounds with unexpected outcomes, transitioning to detailed statistical review.
Top 10 Models
| # | Model | Matches | Total Points | Avg Pts/Match | Tendency % | Exact % |
|---|---|---|---|---|---|---|
| 1 | GLM-4.7 (OpenRouter) | 9 | 29 | 3.22 | 66.7% | 11.1% |
| 2 | Qwen3 30B A3B (OpenRouter) | 9 | 24 | 2.67 | 55.6% | 22.2% |
| 3 | MiniMax M2.5 (OpenRouter) | 9 | 17 | 1.89 | 33.3% | 22.2% |
| 4 | Step 3.5 Flash (OpenRouter) | 9 | 17 | 1.89 | 33.3% | 0.0% |
| 5 | Gemma 3 12B (OpenRouter) | 9 | 17 | 1.89 | 44.4% | 11.1% |
| 6 | GLM-5 (OpenRouter) | 9 | 16 | 1.78 | 33.3% | 22.2% |
| 7 | GPT-OSS 20B (OpenRouter) | 9 | 16 | 1.78 | 44.4% | 11.1% |
| 8 | Llama 4 Scout (OpenRouter) | 9 | 15 | 1.67 | 44.4% | 0.0% |
| 9 | Llama 3.3 70B Instruct (OpenRouter) | 9 | 13 | 1.44 | 33.3% | 11.1% |
| 10 | Trinity Large Preview (OpenRouter) | 9 | 13 | 1.44 | 44.4% | 0.0% |
Match-by-Match Audit
- Strasbourg vs Lyon: Result 3-1, 15.8% correct tendency, 0.0% exact score hits, consensus A (47.4%) incorrect.
- Nice vs Lorient: Result 3-3, 47.4% correct tendency, 0.0% exact score hits, consensus D (47.4%) correct.
- Angers vs Lille: Result 0-1, 36.8% correct tendency, 5.3% exact score hits, consensus D (42.1%) incorrect.
- Nantes vs Le Havre: Result 2-0, 0.0% correct tendency, 0.0% exact score hits, consensus D (78.9%) incorrect.
- Auxerre vs Rennes: Result 0-3, 47.4% correct tendency, 0.0% exact score hits, consensus A (47.4%) correct.
- Paris Saint Germain vs Metz: Result 3-0, 94.7% correct tendency, 42.1% exact score hits, consensus H (94.7%) correct.
- Toulouse vs Paris FC: Result 1-1, 42.1% correct tendency, 42.1% exact score hits, consensus D (42.1%) correct.
- Lens vs Monaco: Result 2-3, 15.8% correct tendency, 0.0% exact score hits, consensus H (52.6%) incorrect.
- Stade Brestois 29 vs Marseille: Result 2-0, 10.5% correct tendency, 0.0% exact score hits, consensus D (47.4%) incorrect.
Biggest Consensus Misses
- Nantes vs Le Havre (2-0) | Consensus: D (78.9%) | Counts H/D/A: 0/15/4
- Lens vs Monaco (2-3) | Consensus: H (52.6%) | Counts H/D/A: 10/6/3
- Strasbourg vs Lyon (3-1) | Consensus: A (47.4%) | Counts H/D/A: 3/7/9
- Stade Brestois 29 vs Marseille (2-0) | Consensus: D (47.4%) | Counts H/D/A: 2/9/8
- Angers vs Lille (0-1) | Consensus: D (42.1%) | Counts H/D/A: 4/8/7
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 - 23? A: GLM-4.7 (OpenRouter) performed best with 3.22 average points per match.
Q: How accurate were AI predictions for Ligue 1 this round? A: Models achieved 34.50% correct tendency and 9.94% exact score hit rate across 9 matches.
Q: What was the biggest upset in Ligue 1 Regular Season - 23? A: Nantes' 2-0 win over Le Havre was the biggest consensus miss, with 0% of models predicting the correct tendency.
Q: How does kroam.xyz score AI football predictions? A: kroam.xyz uses a quota-based system awarding up to 10 points per prediction based on tendency accuracy, goal difference, and exact score.
Generation cost: $0.0021
Tokens: 4,897 input + 1,799 output
Frequently Asked Questions
What is this article about?
Which AI model performed best in Ligue 1 Regular Season - 23?**?
Q: Which AI model performed best in Ligue 1 Regular Season - 23?
Q: How accurate were AI predictions for Ligue 1 this round?
You might also like
Ligue 1 AI Predictions Audit: Regular Season Week 22 Performance
Devstral Small and Llama 3.2 3B led Ligue 1 predictions this week with 3.00 points per match, followed by Phi-4 (2.75). Models achieved 40.68% correct tendency overall, though the Rennes 3-1 victory over Paris Saint Germain, predicted correctly by only 3.3% of models, was the biggest surprise.
Feb 16, 2026
Ligue 1 AI Predictions Audit - Regular Season 21
Llama 3.2 3B Turbo led Ligue 1 predictions with 2.89 avg points/match, followed by GPT-OSS 120B (2.17) and DeepSeek V3.1 Terminus (2.00). Models achieved 36.83% correct tendency overall. Biggest upset: Le Havre vs Strasbourg (2-1) with 66.7% consensus on draw.
Feb 9, 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.