Ring-1T Report - CodeForces (rating): leaderboard
Expected Codeforces rating, computed by the report from problems of 14 Div. 2 contests with expert-designed test cases; the report notes the highest attainable rating is 2209, and the number is a rating, not a percentage. From Table 1 of inclusionAI's Ring-1T technical report, comparing Ring-1T with DeepSeek-V3.1-Terminus (Thinking), Qwen3-235B-A22B-Thinking-2507, Gemini 2.5 Pro and GPT-5 Thinking (High), evaluated with a 128K context window, extended with YaRN for models whose native context is shorter. Baselines use official hyperparameters for open models and vendor-recommended settings for APIs, and where an official score exists the report keeps the higher of its reproduction and the official figure.
Metric: CodeForces (rating). Source: arxiv.org. Saturation forecast: Estimated already saturated. 5 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Ring-1T | 2088 | #628 |
| 2 | DeepSeek V3.1 Terminus (Thinking) | 2073 | #442 (DeepSeek V3.1 Terminus) |
| 3 | Qwen 3 235B A22B 2507 (Thinking) | 2055 | #460 |
| 4 | GPT-5 (High) | 1918 | #163 (GPT-5) |
| 5 | Gemini 2.5 Pro | 1837 | #262 |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=ring-1t-report-codeforces-rating · How It Works · Data refreshed daily, snapshot 2026-11-12.