IOI

Problems from the International Olympiad in Informatics 2024-2026. Run by Vals AI.

CategoryCoding
MetricAccuracy (%)
SourceVals AI (evaluator)
LicenseNone stated
Benchmark pagewww.vals.ai
StatusScored
Weight1.0 within Coding
FitDiscrimination 2.22, noise 0.94

Results

#ModelProviderResultDate
1 Gemini 4 Argon High Google 100.0% 2026-10-29
2 GPT-6 Astra Max OpenAI 100.0% 2026-10-29
3 GPT-6.1 Sol Max OpenAI 96.9% 2026-10-29
4 Claude Opus 5.5 Max Anthropic 95.1% 2026-10-29
5 GPT-5.6 Sol Max OpenAI 91.2% 2026-10-29
6 Claude Fable 5.1 Max Anthropic 90.8% 2026-10-29
7 GPT-5.6 Terra Max OpenAI 87.6% 2026-10-29
8 Claude Opus 5 Max Anthropic 84.3% 2026-10-29
9 Claude Sonnet 5.5 Max Anthropic 83.1% 2026-10-29
10 GPT-6 Sol Max OpenAI 82.6% 2026-10-29
11 Kimi K3.1 Pro Max Moonshot AI 81.9% 2026-10-29
12 Muse Wonder Full Max Meta 79.8% 2026-10-29
13 Qwen3.8 Max Alibaba 68.9% 2026-10-29
14 GLM-5.3 Max Zhipu AI 68.4% 2026-10-29
15 Gemini 3.7 Flash High Google 67.8% 2026-10-29
16 Muse Wonder Max Meta 66.9% 2026-10-29
17 GPT-5.6 Luna Max OpenAI 61.8% 2026-10-29
18 Hy4 preview Tencent 59.3% 2026-10-29
19 Grok 4.7 Extra High xAI 57.7% 2026-10-29
20 Gemini 3.8 Flash High Google 56.9% 2026-10-29
21 Muse Spark 1.3 Max Meta 56.6% 2026-10-29
22 GPT-6 Luna Max OpenAI 55.6% 2026-10-29
23 GPT-5.3 Codex Extra High OpenAI 53.8% 2026-10-29
24 GLM-5.3-Flash Max Zhipu AI 52.5% 2026-10-29
25 Gemini 3.1 Pro Preview High Google 51.8% 2026-10-29
26 DeepSeek V4 Pro 0813 Max DeepSeek 51.6% 2026-10-29
27 Kimi K3 Max Moonshot AI 48.9% 2026-10-29
28 MiMo-V2.6-Flash Xiaomi 47.7% 2026-10-29
29 Grok 4.6 High xAI 47.6% 2026-10-29
30 Claude Haiku 5.5 Max Anthropic 47.3% 2026-10-29
31 Ember-1 Fireworks 46.3% 2026-10-29
32 Mistral Large 4 High Mistral 45.3% 2026-10-29
33 Claude Sonnet 5 Max Anthropic 45.0% 2026-10-29
34 Muse Spark 1.3 Extra High Meta 43.9% 2026-10-29
35 Grok 4.5 High xAI 40.6% 2026-10-29
36 DeepSeek V4.1 Flash Max DeepSeek 40.3% 2026-10-29
37 MiMo-V2.6-Pro Xiaomi 39.3% 2026-10-29
38 Qwen3.8 27B Extra High Alibaba 39.1% 2026-10-29
39 Step 5 Preview StepFun 38.1% 2026-10-29
40 Gemini 3.6 Flash High Google 35.1% 2026-10-29
41 DeepSeek V4 Flash 0731 High DeepSeek 32.7% 2026-10-29
42 Beam 1.0 Reflection 22.8% 2026-10-29
43 Muse Spark 1.2 Extra High Meta 21.8% 2026-10-29
44 Inkling Thinking Machines 14.9% 2026-10-29
45 Inkling Small Thinking Machines 9.3% 2026-10-29
46 Mercury 2.5 High Inception 2.4% 2026-10-29