Skip to main content

Benchmark profile

Codeforces Rating (Codeforces)

Competitive-programming rating reported for DeepSeek-V4 thinking-mode evaluations.

Data verified

Benchmark score on Codeforces — July 23, 2026

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.

4 modelsCodingCurrentDisplay onlyUpdated July 23, 2026

Benchmark score table (4 models)

Score
1
DeepSeek V4 Pro (Max)DeepSeek · Open weight
3206.0
2
DeepSeek V4 Flash (Max)DeepSeek · Open weight
3052.0
3
DeepSeek V4 Pro (High)DeepSeek · Open weight
2919.0
4
DeepSeek V4 Flash (High)DeepSeek · Open weight
2816.0

The published Codeforces snapshot places DeepSeek V4 Pro (Max) first at 3206.0. The third row is 287.0 score units behind. The broader top-10 range is 390.0 score units, so the table still separates the published systems.

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.

About Codeforces

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.

BenchLM freshness & provenance

Version

Codeforces 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

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.

FAQ

What does Codeforces measure?

Competitive-programming rating reported for DeepSeek-V4 thinking-mode evaluations.

Which model scores highest on Codeforces?

DeepSeek V4 Pro (Max) by DeepSeek currently leads with a score of 3206.0 on Codeforces.

How many models are evaluated on Codeforces?

4 AI models have been evaluated on Codeforces on BenchLM.

Last updated: July 23, 2026 · BenchLM version Codeforces 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.