math benchmark
CodeForces Leaderboard
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 17, 2026
Models17
Model coverage17
MetricNormalized rating
EvidenceB
CodeForces Ranking
Higher normalized rating ranks better on this benchmark.
Sort by
Rank | Model | Normalized rating | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelDE | Normalized rating100.0% | Percentile100.0% | Participants17 | EvidenceC | Evaluated |
| Rank02 | ModelDE | Normalized rating100.0% | Percentile93.8% | Participants17 | EvidenceC | Evaluated |
| Rank03 | ModelDE | Normalized rating93.9% | Percentile87.5% | Participants17 | EvidenceC | Evaluated |
| Rank04 | ModelDE | Normalized rating90.0% | Percentile81.3% | Participants17 | EvidenceC | Evaluated |
| Rank05 | ModelAC | Normalized rating85.1% | Percentile75.0% | Participants17 | EvidenceC | Evaluated |
| Rank06 | ModelAC | Normalized rating82.2% | Percentile68.8% | Participants17 | EvidenceC | Evaluated |
| Rank07 | ModelOP | Normalized rating82.1% | Percentile62.5% | Participants17 | EvidenceC | Evaluated |
| Rank08 | ModelAC | Normalized rating80.7% | Percentile56.3% | Participants17 | EvidenceC | Evaluated |
| Rank09 | ModelDE | Normalized rating79.5% | Percentile50.0% | Participants17 | EvidenceC | Evaluated |
| Rank10 | ModelDE | Normalized rating79.5% | Percentile43.8% | Participants17 | EvidenceC | Evaluated |
| Rank11 | ModelOP | Normalized rating74.3% | Percentile37.5% | Participants17 | EvidenceC | Evaluated |
| Rank12 | ModelDE | Normalized rating70.7% | Percentile31.3% | Participants17 | EvidenceC | Evaluated |
| Rank13 | ModelDE | Normalized rating69.7% | Percentile25.0% | Participants17 | EvidenceC | Evaluated |
| Rank14 | ModelAC | Normalized rating65.9% | Percentile18.8% | Participants17 | EvidenceC | Evaluated |
| Rank15 | ModelDE | Normalized rating64.3% | Percentile12.5% | Participants17 | EvidenceC | Evaluated |
| Rank16 | ModelGO | Normalized rating55.3% | Percentile6.3% | Participants17 | EvidenceC | Evaluated |
| Rank17 | ModelGO | Normalized rating47.6% | Percentile0.0% | Participants17 | EvidenceC | Evaluated |
CodeForces Highlights
The leading models and scores on this benchmark.
CodeForces Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for CodeForces
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
Ranking basisThis codeforces AI model leaderboard uses descending normalized rating in the benchmark's original unit. The leaderboard ranking keeps matched price and speed data separate from benchmark evidence.
- 01DEDeepSeek-V4-Flash-MaxDeepSeek
- Normalized rating
- 100.0%
- Price
- $0.14 input / $0.28 output per 1M tokens
- Speed
- Up to 19 tok/s via Novita
Strengths
- Ranks #1 of 17 compared models
- 100th percentile on this benchmark
- C evidence result
Considerations
- This result measures CodeForces, not total model capability
- 02DEDeepSeek-V4-Pro-MaxDeepSeek
- Normalized rating
- 100.0%
- Price
- $0.43 input / $0.87 output per 1M tokens
- Speed
- Up to 18 tok/s via Fireworks
Strengths
- Ranks #2 of 17 compared models
- 94th percentile on this benchmark
- C evidence result
Considerations
- This result measures CodeForces, not total model capability
- 03DEDeepSeek-V4-Flash-0423DeepSeek
- Normalized rating
- 93.9%
- Price
- $0.14 input / $0.28 output per 1M tokens
- Speed
- Up to 19 tok/s via Novita
Strengths
- Ranks #3 of 17 compared models
- 88th percentile on this benchmark
- C evidence result
Considerations
- This result measures CodeForces, not total model capability
- 04DEDeepSeek-V3.2-SpecialeDeepSeek
- Normalized rating
- 90.0%
- Price
- $0.14 input / $0.28 output per 1M tokens
- Speed
- Up to 30 tok/s via DeepSeek
Strengths
- Ranks #4 of 17 compared models
- 81th percentile on this benchmark
- C evidence result
Considerations
- This result measures CodeForces, not total model capability
- 05ACQwen3.5-122B-A10BAlibaba Cloud / Qwen Team
- Normalized rating
- 85.1%
- Price
- $0.40 input / $3.2 output per 1M tokens
Strengths
- Ranks #5 of 17 compared models
- 75th percentile on this benchmark
- C evidence result
Considerations
- This result measures CodeForces, not total model capability
Selection summary
Best AI Models for CodeForces
DeepSeek-V4-Flash-Max currently leads CodeForces with 100.0%. It is the top model on this specific benchmark, while the best LLM for the broader task should also be checked against other benchmarks, price and runtime.
Use this leaderboard with the supporting benchmark results and coverage details above. A leaderboard position summarizes the selected ranking signal; it does not replace workload-specific testing.
What is CodeForces?
What CodeForces measures and how its scores work.
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 ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- CodeForces
- Modality
- text
- Primary category
- math
- Score direction
- higher
- LLMBoard eligible
- Yes
- Evaluation key
- codeforces|llm-stats-current
Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about CodeForces.
Which model scores highest on CodeForces?
DeepSeek-V4-Flash-Max is currently ranked first with 100.0%.
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 normalized rating better?
Yes. Higher values rank better for this benchmark.
How many models are compared?
17 model results are currently shown.
Does this benchmark affect the overall score?
Yes. This benchmark can contribute to the current LLMBoard capability score.