math benchmark
CodeForces
A competitive programming benchmark using problems from the CodeForces platform. The benchmark evaluates code generation capabilities of LLMs on algorithmic problems with difficulty ratings ranging from 800 to 2400. Problems cover diverse algorithmic categories including dynamic programming, graph algorithms, data structures, and mathematical problems with standardized evaluation through direct platform submission.
Updated Aug 7, 2026
Published models16
Registry coverage16
MetricScore
EvidenceB
CodeForces leaderboard
Sorted by the source-provided rank. Higher score is better according to the registry.
| 1 | DE | 1 points | 100.0% | 16 | C | |
| 2 | DE | 1 points | 93.3% | 16 | C | |
| 3 | DE | 0.9 points | 86.7% | 16 | C | |
| 4 | AC | 0.851 points | 80.0% | 16 | C | |
| 5 | AC | 0.822 points | 73.3% | 16 | C | |
| 6 | OP | 0.821 points | 66.7% | 16 | C | |
| 7 | AC | 0.807 points | 60.0% | 16 | C | |
| 8 | DE | 0.795 points | 53.3% | 16 | C | |
| 9 | DE | 0.795 points | 46.7% | 16 | C | |
| 10 | OP | 0.743 points | 40.0% | 16 | C | |
| 11 | DE | 0.707 points | 33.3% | 16 | C | |
| 12 | DE | 0.697 points | 26.7% | 16 | C | |
| 13 | AC | 0.659 points | 20.0% | 16 | C | |
| 14 | DE | 0.643 points | 13.3% | 16 | C | |
| 15 | GO | 0.553 points | 6.7% | 16 | C | |
| 16 | GO | 0.476 points | 0.0% | 16 | C |
Score distribution
Top published rows on the benchmark's original scale.
CodeForces highlights
The top published results on this benchmark's own scale.
What is CodeForces?
Definition and scoring fields from the benchmark registry.
A competitive programming benchmark using problems from the CodeForces platform. The benchmark evaluates code generation capabilities of LLMs on algorithmic problems with difficulty ratings ranging from 800 to 2400. Problems cover diverse algorithmic categories including dynamic programming, graph algorithms, data structures, and mathematical problems with standardized evaluation through direct platform submission.
Scores are shown in points. The current registry marks this benchmark as not independently verified with evidence level B.
- Family
- CodeForces
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- codeforces|llm-stats-current
Source-native results are preserved. Eligibility for the overall LLMBoard score is a separate policy decision.
FAQ
Common questions about CodeForces.
Which model scores highest on CodeForces?
DeepSeek-V4-Flash-Max is currently ranked first with 1 points.
What does CodeForces measure?
A competitive programming benchmark using problems from the CodeForces platform. The benchmark evaluates code generation capabilities of LLMs on algorithmic problems with difficulty ratings ranging from 800 to 2400. Problems cover diverse algorithmic categories including dynamic programming, graph algorithms, data structures, and mathematical problems with standardized evaluation through direct platform submission.
Is a higher score better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
16 unique published model results are currently shown.
Does this benchmark affect the overall score?
This benchmark is marked as eligible for the current LLMBoard capability methodology.