BlogLLM Benchmark Scores as Published, Side by Side
IOI: Results as Published
Every result the catalog holds for IOI: 5 models from 5 developers, read from 1 page. Each number is as printed by the company named beside it; nothing is ranked or rescored. Models are listed by developer, newest first.
Area Code GenerationMaintainer International Olympiad in InformaticsIntroduced 2025Data version 2026103001, as of 2026-10-30
IOI tasks are the problems of the International Olympiad in Informatics, the secondary-school programming olympiad: six algorithmic problems over two contest days, each scored on partial subtasks up to 100 points, so a contest totals 600. Model cards print the total points on a stated year (IOI 2025).
Not checked against a maintainer's page.
IOI 2025 (total points)
| Model | Value | Printed by | Setup as printed |
|---|---|---|---|
| DeepSeek-V4-Pro (Preview)DeepSeek, released 2026-04-24 | 580.1 | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
| Qwen3.5-397B-A17BAlibaba, released 2026-02-16 | 441.3 | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
| Kimi K2.6Moonshot AI, released 2026-04-20 | 585 | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
| GLM-5.1Z.ai, released 2026-04-07 | 456.5 | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
| Nemotron 3 UltraNVIDIA, released 2026-06-04 | 570 | NVIDIA, NVIDIA Nemotron 3 Ultra 550B-A55B model cardchecked 2026-10-15 | - |
Every number here is read from the same catalog file as the benchmark table, data version 2026103001, and is the number the table shows for that model and test. Where one page printed a model under several setups, each value is listed. The catalog is public in armanobosyan/sugra-llm-benchmarks; a wrong number can be reported from the table, with Report an error under the value, or as an issue in that repository.