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.
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.
The UEFA Conference League Round of 32 featured 8 matches, including fixtures like Jagiellonia vs Fiorentina and Zrinjski vs Crystal Palace. Accurate AI predictions are critical as the knockout stage intensifies competition stakes. This audit evaluates model performance using statistical data.
Top 10 Models
| # | Model | Matches | Total Points | Avg Pts/Match | Tendency % | Exact % |
|---|---|---|---|---|---|---|
| 1 | Trinity Large Preview (OpenRouter) | 8 | 25 | 3.13 | 75.0% | 12.5% |
| 2 | Phi-4 (OpenRouter) | 8 | 19 | 2.38 | 62.5% | 0.0% |
| 3 | Kimi K2.5 (OpenRouter) | 8 | 17 | 2.13 | 37.5% | 25.0% |
| 4 | MiniMax M2.1 (OpenRouter) | 8 | 17 | 2.13 | 37.5% | 25.0% |
| 5 | Mistral Small 3.2 24B (OpenRouter) | 8 | 16 | 2.00 | 50.0% | 12.5% |
| 6 | DeepSeek R1-0528 (OpenRouter) | 8 | 13 | 1.63 | 25.0% | 25.0% |
| 7 | Llama 3.3 70B Instruct (OpenRouter) | 8 | 13 | 1.63 | 25.0% | 25.0% |
| 8 | Gemma 3 12B (OpenRouter) | 8 | 13 | 1.63 | 50.0% | 0.0% |
| 9 | Step 3.5 Flash (OpenRouter) | 8 | 13 | 1.63 | 37.5% | 0.0% |
| 10 | Devstral 2 (OpenRouter) | 8 | 12 | 1.50 | 37.5% | 12.5% |
Match-by-Match Audit
- Shkendija vs Samsunspor (0-1): Correct tendency 55.0%, exact score 0.0%, consensus A (55.0%) correct.
- Omonia Nicosia vs HNK Rijeka (0-1): Correct tendency 21.1%, exact score 0.0%, consensus D (63.2%) incorrect.
- Drita vs Celje (2-3): Correct tendency 31.6%, exact score 0.0%, consensus D (68.4%) incorrect.
- Jagiellonia vs Fiorentina (0-3): Correct tendency 21.1%, exact score 0.0%, consensus D (63.2%) incorrect.
- KuPS vs Lech Poznan (0-2): Correct tendency 36.8%, exact score 0.0%, consensus D (57.9%) incorrect.
- Sigma Olomouc vs Lausanne (1-1): Correct tendency 57.9%, exact score 57.9%, consensus D (57.9%) correct.
- Zrinjski vs Crystal Palace (1-1): Correct tendency 36.8%, exact score 26.3%, consensus A (63.2%) incorrect.
- FC Noah vs AZ Alkmaar (1-0): Correct tendency 5.3%, exact score 0.0%, consensus A (63.2%) incorrect.
Biggest Consensus Misses
- Drita vs Celje (2-3): Consensus D (68.4%) incorrect.
- Omonia Nicosia vs HNK Rijeka (0-1): Consensus D (63.2%) incorrect.
- Jagiellonia vs Fiorentina (0-3): Consensus D (63.2%) incorrect.
- Zrinjski vs Crystal Palace (1-1): Consensus A (63.2%) incorrect.
- FC Noah vs AZ Alkmaar (1-0): Consensus A (63.2%) 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 rarityβif 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 Conference League Round of 32? A: Trinity Large Preview (OpenRouter) with 3.13 average points per match.
Q: How accurate were AI predictions for UEFA Conference League this round? A: 33.19% correct tendency and 10.53% exact score hit rate.
Q: What was the biggest upset in UEFA Conference League Round of 32? A: FC Noah's 1-0 win over AZ Alkmaar, with only 5.3% of models predicting the correct tendency.
Q: How does kroam.xyz score AI football predictions? A: Using a quota-based system awarding up to 10 points per match for tendency, goal difference, and exact score accuracy.
Generation cost: $0.0019
Tokens: 4,579 input + 1,659 output
Frequently Asked Questions
What is this article about?
Which AI model performed best in UEFA Conference League Round of 32?**?
Q: Which AI model performed best in UEFA Conference League Round of 32?
Q: How accurate were AI predictions for UEFA Conference League this round?
You might also like
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
Serie A Week 26 AI Predictions: DeepSeek Leads, 37.5% Tendency Accuracy
DeepSeek R1-0528 topped Serie A predictions with 2.38 avg points/match, followed by MiniMax M2.5 and GPT-OSS 20B at 1.88. Models achieved 37.50% correct tendency overall. The biggest upset was AC Milan's 0-1 home loss to Parma, missed by 89.5% of models.
Feb 23, 2026
Turkish Super Lig Week 23 AI Predictions Audit & Accuracy Stats
Kimi K2.5 led AI predictions with 2.63 avg points/match, followed by GLM-4.7 and Qwen3 30B A3B at 2.25. Models achieved 26.32% correct tendency. Biggest upset: Konyaspor's 2-0 win over Galatasaray fooled 84.2% consensus.