IOI 2025 (Vals v2)
Code
The six IOI 2025 problems under Vals' v2 OpenCode protocol without interactive grading feedback. Final solutions receive official subtask points, averaged across the problems.
Top models (higher is better)
| Model | Score |
|---|---|
| Gemini 4 Argon | 100.0 |
| GPT-6.1 Sol | 100.0 |
| GPT-6 Astra | 100.0 |
| Claude Sonnet 5.5 | 88.3 |
| GPT-5.6 Sol | 88.3 |
| Claude Opus 5 | 87.2 |
| Muse Wonder Full | 85.5 |
| GPT-6 Sol | 79.3 |
| GPT-5.6 Terra | 77.8 |
| GLM-5.3 | 75.5 |
| Kimi K3.1 Pro | 75.5 |
| Muse Wonder | 75.5 |
| Gemini 3.7 Flash | 69.8 |
| Hy4 Preview | 68.5 |
| Qwen3.8-Max | 68.3 |
| Gemini 3.8 Flash | 61.3 |
| Muse Spark 1.3 | 61.2 |
| GPT-5.3-Codex | 57.0 |
| GLM-5.3 Flash | 56.7 |
| Grok 4.7 | 56.2 |
| MiMo-V2.6-Flash | 54.2 |
| GPT-5.6 Luna | 49.8 |
| Step 5 Preview | 49.8 |
| Grok 4.6 | 49.0 |
| DeepSeek V4 Pro 0813 | 48.5 |
| Qwen3.8 27B | 48.5 |
| Gemini 3.1 Pro Preview | 46.8 |
| Sonnet 5 | 42.0 |
| Gemini 3.6 Flash | 40.8 |
| MiMo-V2.6-Pro | 39.3 |
| GPT-6 Luna | 39.0 |
| Mistral Large 4 Preview | 37.8 |
| DeepSeek V4.1 Flash | 35.2 |
| Ember-1 | 35.2 |
| Grok 4.5 | 33.5 |
| Claude Haiku 5.5 | 31.3 |
| Kimi K3 | 29.3 |
| DeepSeek-V4-Flash-0731 | 28.2 |
| Muse Spark 1.2 | 23.2 |
| Inkling | 21.0 |