Experiment · No History Variant
One final, ten tries. How much does each model disagree with itself?
25 AI models each simulated the WC26 Final ten times, this time with the tournament match history withheld from the prompt. Same match, ten independent runs — so we can measure the variance in each model's scorelines, scorers, assists and MVPs.
Real final
🇪🇸Spain1
🇦🇷Argentina0
Best model
Gemini 2.5 Pro
85.0%
Worst model
GPT-5 Mini
0.0%
Avg accuracy
45.6%
25 × 10 runs
Leaderboard
25 models · sorted by accuracy| # | Model | xG 🇪🇸 | xG 🇦🇷 | Modal score | W / D / L % | Top scorer | MVP | Accuracy |
|---|---|---|---|---|---|---|---|---|
| 1 |  Gemini 2.5 Pro Google | 1.10 | 0.20 | 1–080% | 90/10/0 | Mikel Oyarzabal (1.0/g) | Rodri 90% | 85.0% |
| 2 | Gemini 2.5 Flash Lite Google | 1.60 | 0.50 | 2–150% | 100/0/0 | Mikel Oyarzabal (1.0/g) | Rodri 100% | 70.0% |
| 3 |  Perplexity Sonar Perplexity | 1.60 | 0.10 | 2–050% | 100/0/0 | Mikel Oyarzabal (1.0/g) | Rodri 100% | 70.0% |
| 4 |  Mistral Large Mistral | 1.70 | 0.90 | 2–170% | 90/0/10 | Mikel Oyarzabal (1.0/g) | Rodri 90% | 55.0% |
| 5 |  Qwen 3.7 Max Alibaba | 1.90 | 0.40 | 2–050% | 100/0/0 | Mikel Oyarzabal (1.1/g) | Rodri 70% | 55.0% |
| 6 |  DeepSeek V4 Pro DeepSeek | 1.90 | 0.60 | 2–160% | 100/0/0 | Mikel Oyarzabal (0.9/g) | Rodri 100% | 55.0% |
| 7 |  GPT-5.6 Sol OpenAI | 1.70 | 0.80 | 2–170% | 90/10/0 | Lionel Messi (0.8/g) | Rodri 80% | 55.0% |
| 8 |  Claude Opus 4.8 Anthropic | 2.00 | 1.00 | 2–1100% | 100/0/0 | Mikel Oyarzabal (1.0/g) | Lamine Yamal 90% | 50.0% |
| 9 | Gemini 2.5 Flash Google | 1.80 | 0.50 | 2–050% | 90/0/10 | Mikel Oyarzabal (1.0/g) | Rodri 90% | 50.0% |
| 10 |  Moonshot Kimi K2 Moonshot | 2.00 | 0.20 | 2–080% | 100/0/0 | Mikel Oyarzabal (1.0/g) | Rodri 100% | 50.0% |
| 11 |  Llama 4 Maverick Meta | 2.00 | 0.40 | 2–060% | 100/0/0 | Lamine Yamal (1.0/g) | Lamine Yamal 100% | 50.0% |
| 12 | Mixtral 8x22B Mistral | 2.00 | 1.00 | 2–1100% | 100/0/0 | Lamine Yamal (1.0/g) | Rodri 100% | 50.0% |
| 13 | Qwen 3.7 Plus Alibaba | 2.00 | 0.30 | 2–070% | 100/0/0 | Mikel Oyarzabal (1.0/g) | Lamine Yamal 60% | 50.0% |
| 14 | Claude Fable 5 Anthropic | 2.00 | 1.00 | 2–1100% | 100/0/0 | Mikel Oyarzabal (1.0/g) | Mikel Oyarzabal 70% | 50.0% |
| 15 | DeepSeek R1 0528 DeepSeek | 1.10 | 0.50 | 1–030% | 60/40/0 | Mikel Oyarzabal (1.0/g) | Rodri 90% | 45.0% |
| 16 |  GLM 5.2 z.ai | 1.90 | 0.60 | 2–150% | 90/10/0 | Mikel Oyarzabal (1.0/g) | Rodri 70% | 45.0% |
| 17 | Claude Haiku 4.5 Anthropic | 1.80 | 0.60 | 2–060% | 80/0/20 | Mikel Oyarzabal (1.0/g) | Rodri 80% | 40.0% |
| 18 | GPT-5.5 OpenAI | 1.80 | 1.00 | 2–180% | 80/20/0 | Lionel Messi (0.9/g) | Rodri 70% | 40.0% |
| 19 | GPT-5.6 Luna OpenAI | 1.80 | 1.00 | 2–180% | 80/20/0 | Lionel Messi (1.0/g) | Lamine Yamal 90% | 40.0% |
| 20 | Claude Sonnet 4.6 Anthropic | 1.50 | 0.90 | 2–150% | 60/40/0 | Mikel Oyarzabal (1.0/g) | Rodri 60% | 35.0% |
| 21 | Llama 3.3 70B Meta | 1.50 | 0.80 | 2–050% | 60/0/40 | Mikel Oyarzabal (1.0/g) | Lamine Yamal 50% | 35.0% |
| 22 |  Grok 4.20 xAI | 1.50 | 1.40 | 2–150% | 50/10/40 | Lamine Yamal (1.0/g) | Lionel Messi 50% | 25.0% |
| 23 | GPT-5 Nano OpenAI | 1.30 | 0.90 | 0–040% | 40/60/0 | Lamine Yamal (0.9/g) | Lamine Yamal 80% | 20.0% |
| 24 | GPT-5.6 Terra OpenAI | 1.40 | 1.00 | 1–160% | 40/60/0 | Mikel Oyarzabal (0.8/g) | Rodri 50% | 20.0% |
| 25 | GPT-5 Mini OpenAI | 1.60 | 1.70 | 2–260% | 0/90/10 | Lionel Messi (0.9/g) | Lionel Messi 70% | 0.0% |