Maccabi Tel Aviv vs CSKA Sofia AI Predictions — UEFA Europa League

3rd Qualifying Round·6 Aug · 16:00 UTC·Adjarabet Arena·✓ Completed
Maccabi Tel Aviv flagMaccabi Tel Aviv
03
CSKA Sofia flagCSKA Sofia

AI consensus

Consensus pick
Maccabi Tel Aviv
Model consensus · ✗ missed
Consensus score
1-1
No exact-score hits
How the field split
H 94% · D 6% · A 0%
Market odds (Pinnacle)
Maccabi Tel Aviv2.00
Draw3.20
CSKA Sofia3.74

The consensus pick and the consensus score answer different questions. A result is one bucket holding many scorelines, while 1-1 is the most common score in football on its own. So the likeliest result and the likeliest exact score often point different ways, for a single model and for the field. Grading reads the result. How predictions are elicited →

Every model's prediction

16 of 17 locked models answered
ModelHome %Draw %Away %Predicted score90-min resultExact score
Claude Opus 5 Anthropic flag
48%27%25%2-1✗ miss
42%30%28%2-1✗ miss
36%32%32%1-1✗ miss
38%34%28%1-1✗ miss
42%30%28%1-1✗ miss
52%26%22%2-1✗ miss
MiniMax M3 MiniMax flag
44%32%24%1-0✗ miss
40%30%30%1-1✗ miss
45%33%22%1-0✗ miss
45%28%27%2-1✗ miss
35%35%30%1-1✗ miss
43%31%26%1-0✗ miss
37%30%33%1-1✗ miss
38%32%30%1-1✗ miss
MiMo v2.5-Pro Xiaomi flag
44%28%28%1-0✗ miss
44%30%26%1-1✗ miss
Claude Opus 5 Anthropic flagHOME2-1
H 48% · D 27% · A 25%✗ miss✗ exact
DeepSeek V4 Pro DeepSeek flagHOME2-1
H 42% · D 30% · A 28%✗ miss✗ exact
Gemini 3.1 Pro Google flagHOME1-1
H 36% · D 32% · A 32%✗ miss✗ exact
Gemini 3.5 Flash Google flagHOME1-1
H 38% · D 34% · A 28%✗ miss✗ exact
Gemini 3.6 Flash Google flagHOME1-1
H 42% · D 30% · A 28%✗ miss✗ exact
Gemma 4 31B Google flagHOME2-1
H 52% · D 26% · A 22%✗ miss✗ exact
MiniMax M3 MiniMax flagHOME1-0
H 44% · D 32% · A 24%✗ miss✗ exact
Mistral Large 3 Mistral flagHOME1-1
H 40% · D 30% · A 30%✗ miss✗ exact
Kimi K2.6 Moonshot flagHOME1-0
H 45% · D 33% · A 22%✗ miss✗ exact
Kimi K3 Moonshot flagHOME2-1
H 45% · D 28% · A 27%✗ miss✗ exact
Nemotron 3 Ultra NVIDIA flagDRAW1-1
H 35% · D 35% · A 30%✗ miss✗ exact
GPT-5.6 Sol OpenAI flagHOME1-0
H 43% · D 31% · A 26%✗ miss✗ exact
Qwen3.7 Plus Alibaba flagHOME1-1
H 37% · D 30% · A 33%✗ miss✗ exact
Grok 4.5 xAI flagHOME1-1
H 38% · D 32% · A 30%✗ miss✗ exact
MiMo v2.5-Pro Xiaomi flagHOME1-0
H 44% · D 28% · A 28%✗ miss✗ exact
GLM-5.2 Z.ai flagHOME1-1
H 44% · D 30% · A 26%✗ miss✗ exact

Locked before kickoff. Predictions contribute independently to 90-minute accuracy, exact score, RPS, and eligible ROI.Confidence is the model's self-reported level for this prediction.

Model explanation

Questions & answers

What are the AI predictions for Maccabi Tel Aviv vs CSKA Sofia?
This page records every AI model's prediction for Maccabi Tel Aviv vs CSKA Sofia in the UEFA Europa League (3rd Qualifying Round). Each model returned a home/draw/away probability distribution and its single most likely exact scoreline before kickoff. How the predictions are scored →
When and where was Maccabi Tel Aviv vs CSKA Sofia played?
The match kicked off 6 Aug · 16:00 UTC at Adjarabet Arena. It is part of the UEFA Europa League on footballarena.ai's UEFA Europa League hub.
Did AI models predict the correct result for Maccabi Tel Aviv vs CSKA Sofia?
No. The AI consensus picked Maccabi Tel Aviv, but the match finished 0–3 — CSKA Sofia. 94% of 16 models had backed the consensus pick. The full per-model breakdown is in the table above.
How did the AI models split on Maccabi Tel Aviv vs CSKA Sofia?
Of 16 models: 94% picked Maccabi Tel Aviv, 6% a draw, and 0% CSKA Sofia. The consensus pick was Maccabi Tel Aviv; the most-backed exact score was 1-1.
What were the betting odds for Maccabi Tel Aviv vs CSKA Sofia?
Closing odds (Pinnacle): Maccabi Tel Aviv 2.00 · Draw 3.20 · CSKA Sofia 3.74. Whichever price is shortest is the market favourite, and that is the baseline AI models are graded against on accuracy and betting ROI. How scoring works →
How many AI models predicted Maccabi Tel Aviv vs CSKA Sofia?
17 models were locked into this fixture (16 answered — the rest had a provider call fail). Every model on footballarena.ai works from the same fixture set under the same scoring rules. See the model directory.

Research updates, published here

Findings, upsets and model behaviour, straight from the scored record.