# Vals IOI (IOI)

> Based on the International Olympiad in Informatics

Canonical page: https://benchlm.ai/benchmarks/valsioi

- Category: [Coding](/coding)
- Last updated: September 27, 2026

## About IOI

- Year: 2026
- Tasks: International Olympiad in Informatics-style programming tasks
- Format: Accuracy score
- Difficulty: Olympiad programming
- Paper: [IOI](https://www.vals.ai/benchmarks/ioi)

BenchLM mirrors the public Vals AI IOI leaderboard as display-only external evidence. The captured snapshot preserves overall scores, task-level scores where Vals publishes them, uncertainty, latency, and cost-per-test metadata. It is excluded from BenchLM weighted rankings.

IOI is currently displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.

## Leaderboard (36 models)

| Rank | Model | Configuration | Creator | Score |
|------|-------|---------------|---------|-------|
| 1 | [GPT-6 Astra](/models/gpt-6-astra) | max reasoning | OpenAI | 100.00% |
| 2 | [Claude Opus 5.5](/models/claude-opus-5-5) | — | Anthropic | 95.06% |
| 3 | [GPT-5.6 Sol](/models/gpt-5-6-sol) | max reasoning | OpenAI | 91.17% |
| 4 | [Claude Fable 5.1](/models/claude-fable-5-1) | — | Anthropic | 90.78% |
| 5 | [GPT-5.6 Terra](/models/gpt-5-6-terra) | max reasoning | OpenAI | 87.61% |
| 6 | [Claude Opus 5](/models/claude-opus-5) | — | Anthropic | 84.33% |
| 7 | [Claude Sonnet 5.5](/models/claude-sonnet-5-5) | — | Anthropic | 83.06% |
| 8 | [GPT-6 Sol](/models/gpt-6-sol) | max reasoning | OpenAI | 82.61% |
| 9 | [Qwen3.8 Max](/models/qwen3-8-max) | — | Alibaba | 68.89% |
| 10 | [GLM-5.3](/models/glm-5-3) | max reasoning | Z.AI | 68.44% |
| 11 | [Gemini 3.7 Flash](/models/gemini-3-7-flash) | high reasoning | Google | 67.83% |
| 12 | [GPT-5.6 Luna](/models/gpt-5-6-luna) | max reasoning | OpenAI | 61.78% |
| 13 | [Hy4 preview](/models/hy4-preview) | — | Tencent | 59.33% |
| 14 | [Grok 4.7](/models/grok-4-7) | xhigh reasoning | xAI | 57.72% |
| 15 | [Gemini 3.8 Flash](/models/gemini-3-8-flash) | high reasoning | Google | 56.94% |
| 16 | [Muse Spark 1.3 Max](https://www.vals.ai/models/meta_muse_spark_1_3_max) | max reasoning | Meta | 56.56% |
| 17 | [GPT-6 Luna](/models/gpt-6-luna) | max reasoning | OpenAI | 55.56% |
| 18 | [GPT-5.3 Codex](/models/gpt-5-3-codex) | xhigh reasoning | OpenAI | 53.83% |
| 19 | [GLM-5.3-Flash](/models/glm-5-3-flash) | max reasoning | Z.AI | 52.50% |
| 20 | [Gemini 3.1 Pro Preview](https://www.vals.ai/models/google_gemini-3.1-pro-preview) | high reasoning | Google | 51.83% |
| 21 | [DeepSeek V4 Pro 0813](/models/deepseek-v4-pro-0813) | max reasoning | DeepSeek | 51.61% |
| 22 | [Kimi K3](/models/kimi-k3) | max reasoning | Moonshot AI | 48.94% |
| 23 | [MiMo-V2.6-Flash](/models/mimo-v2-6-flash) | — | Xiaomi | 47.67% |
| 24 | [Grok 4.6](/models/grok-4-6) | high reasoning | xAI | 47.61% |
| 25 | [Claude Sonnet 5](/models/claude-sonnet-5) | — | Anthropic | 45.00% |
| 26 | [Muse Spark 1.3](/models/muse-spark-1-3) | xhigh reasoning | Meta | 43.94% |
| 27 | [Grok 4.5](/models/grok-4-5) | high reasoning | xAI | 40.56% |
| 28 | [DeepSeek V4.1 Flash](/models/deepseek-v4-1-flash) | high reasoning | DeepSeek | 40.28% |
| 29 | [MiMo-V2.6-Pro](/models/mimo-v2-6-pro) | — | Xiaomi | 39.33% |
| 30 | [Qwen3.8-27B](/models/qwen3-8-27b) | xhigh reasoning | Alibaba | 39.06% |
| 31 | [Gemini 3.6 Flash](/models/gemini-3-6-flash) | high reasoning | Google | 35.06% |
| 32 | [DeepSeek V4 Flash 0731](/models/deepseek-v4-flash-0731) | high reasoning | DeepSeek | 32.72% |
| 33 | [Muse Spark 1.2](/models/muse-spark-1-2) | xhigh reasoning | Meta | 21.78% |
| 34 | [Inkling](/models/inkling) | 0.99 reasoning | Thinking Machines Lab | 14.94% |
| 35 | [Inkling-Small](/models/inkling-small) | 0.99 reasoning | Thinking Machines Lab | 9.33% |
| 36 | [Mercury 2.5](/models/mercury-2-5) | high reasoning | Inception | 2.44% |

## FAQ

### What does IOI measure?

Based on the International Olympiad in Informatics

### Which model leads the published IOI snapshot?

GPT-6 Astra currently leads the published IOI snapshot with a score of 100.00%.

### How many models are evaluated on IOI?

The September 27, 2026 contains 36 AI models.

### Does IOI affect BenchLM's overall score?

Not directly. IOI is still displayed on BenchLM for reference, but it is excluded from the weighted scoring formula.