Competitive-programming rating reported for DeepSeek-V4 thinking-mode evaluations.
BenchLM mirrors the published score view for Codeforces. DeepSeek V4 Pro (Max) leads the public snapshot at 3206.0 , followed by DeepSeek V4 Flash (Max) (3052.0) and DeepSeek V4 Pro (High) (2919.0). BenchLM does not use these results to rank models overall.
DeepSeek V4 Pro (Max)
DeepSeek
DeepSeek V4 Flash (Max)
DeepSeek
DeepSeek V4 Pro (High)
DeepSeek
The published Codeforces snapshot is tightly clustered at the top: DeepSeek V4 Pro (Max) sits at 3206.0, while the third row is only 287.0 points behind. The broader top-10 spread is 390.0 points, so the benchmark still separates strong models even when the leaders cluster.
4 models have been evaluated on Codeforces. The benchmark falls in the Coding category. This category carries a 20% weight in BenchLM.ai's overall scoring system. Codeforces is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
Year
2026
Tasks
Competitive programming contests
Format
Rating
Difficulty
Elite competitive programming
BenchLM stores Codeforces as a display-only provider-table row because its rating scale is not a 0-100 percentage benchmark.
Version
Codeforces 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.
Competitive-programming rating reported for DeepSeek-V4 thinking-mode evaluations.
DeepSeek V4 Pro (Max) by DeepSeek currently leads with a score of 3206.0 on Codeforces.
4 AI models have been evaluated on Codeforces on BenchLM.
For engineers, researchers, and the plain curious — a weekly brief on new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.