AI model leaderboard
A summary per model across all prompts: how many outputs work, how many points they earned against the prompt requirements, what they cost and how long they took. Click a model to open its page.
| # | Model | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| 1. | GPT-6.1 Sol OpenAI |
29/09/2026 | – | 99 | 78 | 5/5 | $1.08 prices as of 15/10/2026 | 6 min 23 s | 869,355 | 39 kB |
| 2. | GPT-6 Astra OpenAI |
03/09/2026 | – | 99 | 79 | 5/5 | $7.65 prices as of 15/10/2026 | 7 min 56 s | 1,191,837 | 38 kB |
| 3. | Gemini 3.5 Flash-Lite |
21/07/2026 | – | 98 | 89 | 5/5 | $0.19 prices as of 17/10/2026 | 51 s | 79,398 | 45 kB |
| 4. | Claude Haiku 5.5 Anthropic |
07/10/2026 | – | 98 | 92 | 5/5 | ≈ $0.46 prices as of 06/10/2026 | 13 min 42 s | 1,005,674 | 47 kB |
| 5. | GPT-5.6 Sol OpenAI |
09/07/2026 | – | 98 | 78 | 5/5 | $1.69 prices as of 15/10/2026 | 2 min 30 s | 1,134,216 | 24 kB |
| 6. | GPT-6 Luna OpenAI |
22/09/2026 | – | 96 | 79 | 5/5 | $0.048 prices as of 15/10/2026 | 1 min 29 s | 1,187,622 | 25 kB |
| 7. | DeepSeek V4.1 Flash DeepSeek |
10/09/2026 | – | 96 | 92 | 5/5 | $0.24 prices as of 16/10/2026 | 5 min 54 s | 408,374 | 76 kB |
| 8. | GPT-6 Sol OpenAI |
22/09/2026 | – | 96 | 80 | 4/5 | $1.25 prices as of 15/10/2026 | 2 min 48 s | 1,319,789 | 35 kB |
| 9. | GPT-5.6 Terra OpenAI |
09/07/2026 | – | 95 | 85 | 4/5 | $0.52 prices as of 17/10/2026 | 1 min 09 s | 45,078 | 23 kB |
| 10. | GPT-5.4 mini OpenAI |
17/03/2026 | – | 95 | 84 | 4/5 | $2.16 prices as of 17/10/2026 | 6 min 04 s | 482,419 | 74 kB |
| 11. | Claude Sonnet 5.5 Anthropic |
28/09/2026 | – | 95 | 85 | 4/5 | ≈ $8.08 prices as of 06/10/2026 | 17 min 30 s | 877,582 | 72 kB |
| 12. | Gemini 3.1 Flash-Lite |
07/05/2026 | – | 94 | 84 | 5/5 | $0.021 prices as of 17/10/2026 | 8 s | 16,051 | 6 kB |
| 13. | GPT-5.5 OpenAI |
23/04/2026 | – | 94 | 82 | 4/5 | $2.06 prices as of 17/10/2026 | 2 min 19 s | 70,525 | 32 kB |
| 14. | Claude Opus 5.5 Anthropic |
22/09/2026 | – | 94 | 88 | 4/5 | ≈ $17.86 prices as of 06/10/2026 | 38 min 33 s | 970,297 | 93 kB |
| 15. | Mistral Large 4 Mistral |
06/10/2026 | – | 94 | 86 | 3/4 | $0.75 prices as of 17/10/2026 | 33 min 03 s | 360,488 | 69 kB |
| 16. | Mistral Medium 3.5 Mistral |
28/04/2026 | – | 93 | 93 | 5/5 | $1.49 prices as of 17/10/2026 | 4 min 09 s | 199,885 | 50 kB |
| 17. | Gemini 4 Argon |
30/09/2026 | – | 91 | 88 | 5/5 | $1.68 prices as of 17/10/2026 | 5 min 05 s | 169,955 | 89 kB |
| 18. | GLM 5.3 Z.ai |
15/09/2026 | – | 91 | 72 | 1/5 | $2.16 prices as of 17/10/2026 | 7 min 19 s | 492,105 | 57 kB |
| 19. | Gemini 3.1 Pro |
19/02/2026 | – | 90 | 86 | 5/5 | $1.12 prices as of 17/10/2026 | 1 min 57 s | 95,232 | 41 kB |
| 20. | Gemma 4 31B |
02/04/2026 | – | 90 | 90 | 4/5 | $0.00 prices as of 17/10/2026 | 4 min 55 s | 54,429 | 29 kB |
| 21. | DeepSeek V4 Pro DeepSeek |
13/08/2026 | – | 89 | 88 | 4/5 | $0.37 prices as of 16/10/2026 | 4 min 10 s | 190,929 | 63 kB |
| 22. | Codestral 25.08 Mistral |
30/07/2025 | – | 88 | 85 | 4/5 | $0.075 prices as of 17/10/2026 | 2 min 14 s | 84,769 | 70 kB |
| 23. | Gemini 3.8 Flash |
02/09/2026 | – | 87 | 85 | 4/5 | $0.57 prices as of 16/10/2026 | 3 min 21 s | 152,540 | 70 kB |
| 24. | Gemini 3.6 Flash |
21/07/2026 | – | 87 | 90 | 3/5 | $0.51 prices as of 17/10/2026 | 2 min 25 s | 137,040 | 57 kB |
| 25. | GPT-5.6 Luna OpenAI |
09/07/2026 | – | 78 | 76 | 2/5 | $0.034 prices as of 17/10/2026 | 41 s | 30,369 | 15 kB |
| 26. | Mistral Small 4 Mistral |
16/03/2026 | – | 73 | 91 | 2/5 | $0.072 prices as of 17/10/2026 | 2 min 01 s | 122,169 | 41 kB |
Cost = tokens priced with the API price list valid on the date shown next to the cost (prices change; actual subscriptions differ). ≈ = at least part is an estimate. Score = sum of checklist points (a broken output scores 0, the score after fix in brackets). Loads = outputs that open without errors. Tech. quality = automatic measurement 0–100.