Taplio - Build a growth routine on LinkedIn
Mini toolsCodeForces ELO
CodeForces Live Contest ELO
Live competitive-programming ELO inferred from a model's performance on recent Codeforces rounds. Reported as a Codeforces rating.
Coding
Text
elo
Max 4,000.0rating
Released Sep 2024
12
Results
12
Models scored
3,206.0rating
Top: Deepseek V4 Pro
2,103.0rating
Median
Best results
Top primary scores; one row per model.
Frontier over time
Each dot is one model result; the line traces the running best score.
All results
Showing one canonical row per model. Show all configurations
| # | Model | Score | Conditions | Eval date | Source | Flags |
|---|---|---|---|---|---|---|
| 1 | Deepseek V4 Pro | 3,206.0rating | 0-shot · CoT · Think High/Max mode | Apr 24, 2026 | self reported | primary |
| 2 | o4 mini | 2,719.0rating | — | Apr 16, 2025 | self reported | primary |
| 3 | o3 | 2,706.0rating | — | Apr 16, 2025 | self reported | primary |
| 4 | DeepSeek 3.2 Speciale | 2,701.0rating | — | Dec 1, 2025 | paper | primary verified |
| 5 | Deepseek 3.2 | 2,386.0rating | — | Dec 1, 2025 | self reported | primary |
| 6 | Gemma 4 | 2,150.0rating | CoT · thinking mode | Apr 3, 2026 | self reported | primary |
| 7 | Qwen3 235B A22B | 2,056.0rating | — | Apr 28, 2025 | self reported | primary |
| 8 | DeepSeek V3.1 Terminus | 2,046.0rating | — | Sep 22, 2025 | self reported | primary |
| 9 | Qwen3 30B A3B | 1,974.0rating | — | Apr 28, 2025 | self reported | primary |
| 10 | o1 | 1,891.0rating | — | Apr 16, 2025 | self reported | primary |
| 11 | Phi 4 reasoning plus | 1,723.0rating | — | Jul 8, 0005 | self reported | primary |
| 12 | DeepSeek V3 | 51.6rating | — | Dec 26, 2024 | paper | primary |
