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.
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.
The UEFA Europa League Round of 32 featured 8 matches, with AI models making 152 total predictions. Accurate forecasting is critical in this knockout stage due to high-stakes progression implications. This audit evaluates model performance using strictly statistical data.
Top 10 Models
| # | Model | Matches | Total Points | Avg Pts/Match | Tendency % | Exact % |
|---|---|---|---|---|---|---|
| 1 | Mistral Small 3.2 24B (OpenRouter) | 8 | 27 | 3.38 | 62.5% | 25.0% |
| 2 | Phi-4 (OpenRouter) | 8 | 23 | 2.88 | 62.5% | 25.0% |
| 3 | Llama 4 Scout (OpenRouter) | 8 | 22 | 2.75 | 50.0% | 25.0% |
| 4 | GLM-4.7 (OpenRouter) | 8 | 22 | 2.75 | 62.5% | 25.0% |
| 5 | Trinity Large Preview (OpenRouter) | 8 | 20 | 2.50 | 50.0% | 25.0% |
| 6 | Gemma 3 27B (OpenRouter) | 8 | 17 | 2.13 | 37.5% | 25.0% |
| 7 | Step 3.5 Flash (OpenRouter) | 8 | 15 | 1.88 | 37.5% | 12.5% |
| 8 | Kimi K2.5 (OpenRouter) | 8 | 14 | 1.75 | 37.5% | 12.5% |
| 9 | Gemma 3 12B (OpenRouter) | 8 | 14 | 1.75 | 37.5% | 12.5% |
| 10 | MiniMax M2.1 (OpenRouter) | 8 | 14 | 1.75 | 37.5% | 12.5% |
Match-by-Match Audit
- Bologna vs Brann: Result 1-0. Correct tendency 57.9%, exact score hits 5.3%. Consensus H (57.9%) correct.
- Genk vs Dinamo Zagreb: Result 3-3. Correct tendency 31.6%, exact score hits 0.0%. Consensus H (42.1%) incorrect.
- Celta Vigo vs PAOK: Result 1-0. Correct tendency 26.3%, exact score hits 0.0%. Consensus D (42.1%) incorrect.
- Nottingham Forest vs Fenerbahçe: Result 1-2. Correct tendency 31.6%, exact score hits 31.6%. Consensus D (36.8%) incorrect.
- Ferencvarosi TC vs Ludogorets: Result 2-0. Correct tendency 52.6%, exact score hits 0.0%. Consensus H (52.6%) correct.
- VfB Stuttgart vs Celtic: Result 0-1. Correct tendency 10.5%, exact score hits 0.0%. Consensus H (84.2%) incorrect.
- Plzen vs Panathinaikos: Result 1-1. Correct tendency 89.5%, exact score hits 89.5%. Consensus D (89.5%) correct.
- FK Crvena Zvezda vs Lille: Result 0-2. Correct tendency 10.5%, exact score hits 0.0%. Consensus D (68.4%) incorrect.
Biggest Consensus Misses
- VfB Stuttgart vs Celtic (0-1) | Consensus: H (84.2%) | Counts H/D/A: 16/1/2
- FK Crvena Zvezda vs Lille (0-2) | Consensus: D (68.4%) | Counts H/D/A: 4/13/2
- Genk vs Dinamo Zagreb (3-3) | Consensus: H (42.1%) | Counts H/D/A: 8/6/5
- Celta Vigo vs PAOK (1-0) | Consensus: D (42.1%) | Counts H/D/A: 5/8/6
- Nottingham Forest vs Fenerbahçe (1-2) | Consensus: D (36.8%) | Counts H/D/A: 6/7/6
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 UEFA Europa League Round of 32? A: Mistral Small 3.2 24B (OpenRouter) performed best with 3.38 average points per match.
Q: How accurate were AI predictions for UEFA Europa League this round? A: Models achieved 38.82% correct tendency and 15.79% exact score hit rate across 8 matches.
Q: What was the biggest upset in UEFA Europa League Round of 32? A: VfB Stuttgart's 0-1 loss to Celtic was the biggest consensus miss, with 84.2% of models predicting a home win.
Q: How does kroam.xyz score AI football predictions? A: kroam.xyz uses a quota-based system awarding 2-6 points for correct tendency, +1 for correct goal difference, and +3 for exact score, with a maximum of 10 points per prediction.
Generation cost: $0.0020
Tokens: 4,561 input + 1,767 output
Frequently Asked Questions
What is this article about?
Which AI model performed best in UEFA Europa League Round of 32?**?
Q: Which AI model performed best in UEFA Europa League Round of 32?
Q: How accurate were AI predictions for UEFA Europa League this round?
You might also like
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 Champions League Round of 32 AI Model Accuracy Audit
Llama 4 Scout and GLM-4.7 led UEFA Champions League Round of 32 predictions with 2.50 points per match, followed by Gemma 3 27B and GLM-5 (2.25). Models achieved a 34.87% correct tendency overall, with the 2-2 draw between Paris Saint Germain and Monaco being the biggest consensus miss.
Mar 2, 2026
Serie A Week 27 AI Model Predictions & Accuracy Report
Gemma 3 12B and GLM-5 led with 3.13 avg points per match, followed by MiniMax M2.1 and DeepSeek V3.2 at 2.88. Models achieved 63.16% correct tendency overall. Torino's 2-0 win over Lazio was the biggest consensus miss.