Evaluates models on competitive programming problems from the Codeforces platform.

Codeforces

A smaller model optimized for fast, cost-efficient reasoning. Achieves remarkable performance for its size and cost, particularly in math, coding, and visual tasks. It is the best-performing benchmarked model on AIME 2024 and 2025, with significantly higher usage limits than o3.

o4-mini

OpenAI's most powerful reasoning model that pushes the frontier across coding, math, science, visual perception, and more. Sets new state-of-the-art on benchmarks including Codeforces, SWE-bench, and MMMU. Features full tool access and can agentically use and combine every tool within ChatGPT.

Third-generation Qwen model featuring hybrid reasoning capabilities that can switch between thinking and non-thinking modes. Trained on 36 trillion tokens (double that of Qwen2.5), with support for 119 languages and dialects. Available in 6 dense models (0.6B to 32B parameters) and 2 MoE models (30B/3B active and 235B/22B active).

Qwen-3

DeepSeek-R1 is a first-generation reasoning model trained via large-scale reinforcement learning. Built on DeepSeek-V3-Base, it incorporates cold-start data before RL to address challenges like endless repetition and poor readability found in DeepSeek-R1-Zero. Achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks through advanced chain-of-thought reasoning capabilities.

DeepSeek-R1

The o1 model series is trained with large-scale reinforcement learning to reason using chain-of-thought. OpenAI o1 is the next model in this series (previously OpenAI o1-preview), with advanced reasoning capabilities that provide new avenues for improving safety and robustness. The model can reason about safety policies in context when responding to potentially unsafe prompts, through deliberative alignment.

Faster, cost-efficient reasoning model optimized for coding and agentic applications. 80% cheaper than o1-preview with strong capabilities for complex problem-solving in tasks where context is provided within the prompt.

o1-mini

Large reasoning model with strong capabilities for solving hard problems through extended thinking. Designed to spend more time reasoning before responding, with enhanced performance in science, coding, and math.

o1-preview

GPT-4o ('o' for 'omni') is a multimodal model that accepts any combination of text, audio, image, and video inputs and generates text, audio, and image outputs. It matches GPT-4 Turbo performance on English text and code, with significant improvements for non-English languages. It responds to audio inputs in as little as 232 milliseconds (avg. 320ms), similar to human conversation response time. GPT-4o is 50% cheaper in the API than previous models and features superior vision and audio understanding capabilities.

GPT-4o

A powerful Mixture-of-Experts (MoE) language model with 671B total parameters and 37B activated for each token. Features Multi-head Latent Attention (MLA) and DeepSeekMoE architectures with innovative auxiliary-loss-free load balancing and multi-token prediction training. Pre-trained on 14.8T high-quality tokens with only 2.788M H800 GPU hours.

Rank	Model	Provider	Score	Parameters	Released	Type
1	o4-mini	OpenAI	2,719		2025-04-16	Multimodal
2	o3	OpenAI	2,706		2025-04-16	Multimodal
3	Qwen-3	Alibaba	2,056	235B (22B active)	2025-04-29	Text
4	DeepSeek-R1	DeepSeek	2,029	671B (37B activated)	2025-01-20	Text
5	o1	OpenAI	1,673		2024-09-12	Multimodal
6	o1-mini	OpenAI	1,650		2024-09-12	Text
7	o1-preview	OpenAI	1,258		2024-09-12	Text
8	GPT-4o	OpenAI	900		2024-05-13	Multimodal
9	DeepSeek-V3	DeepSeek	51.6	671B total, 37B activated	2024-12-26	Text

Codeforces

Codeforces Leaderboard

About Codeforces

Description

Methodology

Publication

Related Benchmarks

Aider-Polyglot

Berkeley Function-Calling Leaderboard

HumanEval