Code on Best of AI

AlphaCode 2

Thu, 16 Jul 2026 00:00:00 +0000

AlphaCode 2 is Google DeepMind’s competitive-programming system, published as a technical report in December 2023 as a follow-up to the original AlphaCode. Instead of a single model, it is a pipeline built on fine-tuned Gemini models: it samples up to a million candidate C++ solutions per problem, then filters them down through test-based checks, behavioral clustering, and a learned scoring model to pick roughly ten final submissions. On a set of recent Codeforces contests, it solved 43 percent of problems within ten attempts, nearly double the original AlphaCode’s 25 percent.

Code Llama

Thu, 16 Jul 2026 00:00:00 +0000

Code Llama is Meta’s code-focused version of Llama 2, released in August 2023. It was trained further on code-heavy data on top of the base Llama 2 weights and shipped in three foundation sizes (7B, 13B, and 34B parameters), each with a base version, a Python-specialized version, and an instruction-tuned version for chat-style coding help. Meta later added a 70B variant. A key change from the base Llama 2 model was extending the context window from 4,096 tokens up to 100,000 tokens, achieved by adjusting the RoPE positional embeddings, which made the model far more useful for reading and editing long files or entire codebases in one pass.

CodeGen2

Thu, 16 Jul 2026 00:00:00 +0000

CodeGen2 is Salesforce Research’s second-generation family of open code models, released in May 2023 as a follow-up to the original CodeGen. It comes in four sizes: 1B, 3.7B, 7B, and 16B parameters. The main improvement over the first CodeGen is infilling support, meaning the model can fill in a missing chunk of code given the surrounding context on both sides, rather than only generating text left to right. This makes it better suited to real editor workflows like autocomplete and code repair, where the model needs to write code in the middle of an existing file.

Codestral

Thu, 16 Jul 2026 00:00:00 +0000

Codestral is Mistral AI’s dedicated code generation model, first released in May 2024 with 22 billion parameters. It’s built for fill-in-the-middle completion and multi-language code generation, and it launched with an 81.1 percent pass@1 score on HumanEval, ahead of larger code models like Code Llama 70B and DeepSeek Coder 33B at the time. The original release used a 32,000-token context window and shipped under the Mistral AI Non-Production License, which limited free use to research and testing and required a separate commercial license for production deployment.

Codestral Mamba

Thu, 16 Jul 2026 00:00:00 +0000

Codestral Mamba is a code generation model Mistral AI released in July 2024, notable mainly for its architecture: instead of the transformer design used by nearly every other code model, it’s built on Mamba, a state-space model architecture. State-space models process sequences with linear rather than quadratic scaling in sequence length, which means inference speed does not degrade as sharply as context grows. Mistral sized it at roughly 7 billion parameters and gave it a 256,000-token context window, with the company reporting reliable in-context retrieval performance even at that length.

CodeT5+

Thu, 16 Jul 2026 00:00:00 +0000

CodeT5+ is a family of open-weight code models built by Salesforce Research, released in May 2023 as a follow-up to the original CodeT5 encoder-decoder model. It comes in several sizes from 220 million up to 16 billion parameters and can run in encoder-only, decoder-only, or full encoder-decoder mode, which lets one architecture cover code understanding tasks like defect detection alongside generation tasks like code completion and text-to-code synthesis. Training combines span denoising, causal language modeling, contrastive learning, and text-code matching objectives, an approach Salesforce says gives it an edge over decoder-only code models of similar size on retrieval-augmented generation tasks. The 16B variant scores around 30.9% pass@1 on HumanEval, and an instruction-tuned version of the same checkpoint pushes past 35%, beating OpenAI’s older code-cushman-001 model on the same benchmark. Weights are hosted on Hugging Face under a BSD-3-Clause license, making CodeT5+ one of the earlier fully open alternatives to Codex-era proprietary code models.

Codex

Thu, 16 Jul 2026 00:00:00 +0000

Codex is OpenAI’s first dedicated code-generation model, announced in August 2021 as a GPT-3 descendant fine-tuned on billions of lines of public source code from GitHub. The largest published version had 12 billion parameters and a 4,096-token context window, and it solved 28.8% of problems on OpenAI’s HumanEval benchmark on the first try, rising to 77.5% when allowed 100 sampled attempts per problem. Codex is what powered the original GitHub Copilot when Copilot launched in technical preview in 2021, marking one of the first large-scale deployments of an LLM as a coding assistant rather than a chat or completion demo. OpenAI made it available through a private beta API for a few years before retiring the standalone Codex API in March 2023, folding its capabilities into successor GPT-3.5 and GPT-4 family models. The name lives on today as the brand for OpenAI’s newer agentic coding products, but the original Codex model itself is no longer accessible through the API.

DeepSeek Coder V2

Thu, 16 Jul 2026 00:00:00 +0000

DeepSeek-Coder-V2 is DeepSeek’s second-generation code model, released in June 2024 as a mixture-of-experts model with 236 billion total parameters and 21 billion active per token. It extended the context window to 128,000 tokens, up sharply from the 16,000-token window of the original DeepSeek-Coder, and expanded language coverage from 86 to 338 programming languages. On HumanEval it scored 90.2%, a result DeepSeek billed at the time as closing the gap with closed models like GPT-4 Turbo on coding tasks, and it also improved on general reasoning and math benchmarks compared to its predecessor. Unlike the original DeepSeek-Coder’s more restrictive license, DeepSeek-Coder-V2 is released under the MIT license, making it freely usable for commercial projects, and weights are available on Hugging Face alongside API access through DeepSeek’s own platform.

DeepSeek-Coder-33B

Thu, 16 Jul 2026 00:00:00 +0000

DeepSeek-Coder-33B is a code-focused language model that DeepSeek released in November 2023, before the company became widely known for its later reasoning models. It was trained from scratch on 2 trillion tokens split mostly between code and natural language, with a 16,000-token context window and project-level training that lets it reason across multiple files rather than isolated snippets. The instruction-tuned version scored 79.3% pass@1 on HumanEval at release, putting it ahead of most open code models of the time and within striking distance of GPT-3.5 on coding benchmarks. It supports fill-in-the-middle completion for use in code editors and covers a wide range of programming languages. DeepSeek has since superseded it with DeepSeek-Coder-V2, a larger mixture-of-experts model with a longer context window, but the 33B model is still available on Hugging Face for self-hosting.

Devstral

Thu, 16 Jul 2026 00:00:00 +0000

GLM-4.6

Thu, 16 Jul 2026 00:00:00 +0000

Granite Code

Thu, 16 Jul 2026 00:00:00 +0000

Kimi K2.7 Code

Thu, 16 Jul 2026 00:00:00 +0000

Qwen2.5-Coder

Thu, 16 Jul 2026 00:00:00 +0000

Qwen3-Coder

Thu, 16 Jul 2026 00:00:00 +0000

replit-code-v1.5

Thu, 16 Jul 2026 00:00:00 +0000

SantaCoder

Thu, 16 Jul 2026 00:00:00 +0000

StarCoder

Thu, 16 Jul 2026 00:00:00 +0000

StarCoder2

Thu, 16 Jul 2026 00:00:00 +0000

Voyage-Code-2

Thu, 16 Jul 2026 00:00:00 +0000

WizardCoder

Thu, 16 Jul 2026 00:00:00 +0000

Yi-Coder

Thu, 16 Jul 2026 00:00:00 +0000