Best LLMs for Coding
Models with strong code-generation capabilities for autocompletion, refactoring, and agentic coding.
114 models
Muse Spark 1.1
Meta Superintelligence Labs' updated flagship, building on Muse Spark with stronger agentic reasoning, more reliable multi-agent orchestration, and improved multimodal understanding across voice, text, and image. Extends the context window and reduces latency and reasoning token usage while raising coding and tool-use accuracy. Powers Meta AI across its product ecosystem.
Gemini 3.5 Pro
Google DeepMind's flagship Gemini model, rebuilt on a new foundation with a 2M-token context window and a Deep Think reasoning mode for the hardest math, coding, and multimodal tasks. Natively multimodal across text, image, audio, and video with streaming function calling and strong long-context grounding.
Gemini 3.5 Flash
Google DeepMind's balanced Gemini 3.5 model that pairs Pro-line reasoning quality with Flash-line latency and cost. Natively multimodal across text, image, audio, and video with a 1M-token context window, configurable thinking levels, and streaming function calling, tuned for high-throughput production workloads.
Grok 4.5
xAI's strongest model to date, built to excel at coding, agentic tasks, and knowledge work and co-developed alongside coding tools for real-world software engineering. Features real-time information access, extended reasoning, and large-context tool use with an OpenAI-compatible API.
Claude Sonnet 5
Anthropic's most capable Sonnet-class model, bringing frontier coding, agentic, and professional-work performance to the midsize tier while closing the gap with Opus 4.8 at a lower price. Supports adaptive thinking with selectable reasoning effort levels, a 1M-token context window, and text, image, and file inputs. Codenamed Fennec.
GPT-5.6 Luna
The fast, low-cost tier of OpenAI's GPT-5.6 series, optimized for high-volume, latency-sensitive tasks such as classification, extraction, routing, and lightweight agentic steps. Approaches the larger GPT-5.6 tiers on many benchmarks while running several times faster at a fraction of the price.
GPT-5.6 Sol
OpenAI's flagship model in the GPT-5.6 series, advancing coding, scientific reasoning, long-horizon planning, and agentic workflows while improving reliability and efficiency on demanding real-world tasks. Adds a max reasoning-effort setting and an ultra mode that spawns subagents for complex, multi-step work.
GPT-5.6 Terra
The balanced tier of OpenAI's GPT-5.6 series, trading a small amount of peak quality for markedly lower latency and cost. Retains strong reasoning, coding, and agentic tool use with configurable reasoning effort, making it a default choice for production workloads that need frontier capability at scale.
Sakana Fugu Ultra
The higher-quality tier of Sakana AI's Fugu multi-agent orchestration system, tuned for the hardest coding, reasoning, science, and agentic tasks. Coordinates a swappable pool of frontier LLMs through one OpenAI-compatible endpoint, delegating sub-tasks, verifying intermediate work, and synthesizing a single answer. Sakana reports strong vendor benchmarks including 93.2 on LiveCodeBench, 73.7 on SWE-Bench Pro, and 82.1 on TerminalBench.
Sakana Fugu
Sakana AI's multi-agent orchestration model from Tokyo, delivered as a single OpenAI-compatible API. Fugu is itself a language model trained to call a pool of specialist LLMs (and recursive instances of itself), handling model selection, delegation, verification, and synthesis behind one endpoint. Built on Sakana AI's TRINITY and Conductor research, its routing intelligence is learned in model weights rather than hand-configured.
Sarvam-30B
Sarvam AI's 30B-parameter Mixture-of-Experts reasoning model trained from scratch with only 2.4B active parameters per token. Optimized for real-time deployment and Indian languages, delivering strong reasoning, coding, and conversational performance while remaining efficient to serve. Open-weights.
GLM-5.2
Z.ai's (formerly Zhipu AI) flagship open-weight coding model with a 1M-token context window. Mixture-of-Experts architecture with 753B total parameters and ~40B active per request, featuring two cost-balancing reasoning modes. Tops several coding benchmarks while remaining a fraction of the cost of comparable proprietary frontier models. MIT-licensed weights.
Command A+
Cohere's enterprise flagship model building on Command A with stronger reasoning, agentic tool use, and multilingual performance across 23 languages. Optimized for secure, high-throughput RAG, retrieval, and long-horizon agent workflows in regulated environments, with private and on-premise deployment options.
Sarvam-105B
Sarvam AI's sovereign 105B-parameter Mixture-of-Experts model activating ~9B parameters per token, with a 128K-token context window. Trained on 12 trillion tokens across 22 Indian languages using 128 sparse experts with Multi-head Latent Attention and a custom low-fertility Indic tokenizer. Wins the majority of pairwise comparisons on Indian-language and STEM benchmarks.
Sarvam-M
Sarvam AI's 24B-parameter instruction-tuned model derived from Mistral-Small-3.1-24B, post-trained on English plus eleven major Indic languages (bn, hi, kn, gu, mr, ml, or, pa, ta, te). Delivers large relative gains on Indian-language, math, and programming benchmarks over its base model, with a hybrid reasoning mode for complex tasks.
Kimi K2.7 Code
Moonshot AI's latest open-source, coding-focused model in the Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. A 1-trillion-parameter model that cuts reasoning token usage by roughly 30% versus K2.6 while improving coding and agent performance — +21.8% on Kimi Code Bench v2, +11.0% on Program Bench, and +31.5% on MLS Bench Lite for multi-language support. Released under a Modified MIT License and available via Kimi APIs and Hugging Face.
DiffusionGemma
Google DeepMind's experimental diffusion-based member of the Gemma 4 open model family. Unlike autoregressive models that generate text one token at a time, DiffusionGemma denoises a canvas of placeholder tokens to produce up to 256 tokens in parallel, finalizing output in one block. A Mixture-of-Experts model with 26B total parameters and 3.8B active per inference, delivering roughly 4x the throughput of similarly sized autoregressive Gemma models on local hardware. Excels at non-linear tasks like in-line editing, molecular sequencing, mathematical graphing, and self-correcting puzzles.
Claude Mythos 5
Anthropic's frontier Mythos-class model — the same underlying model as Claude Fable 5 but with safeguards lifted in some areas. It has the strongest cybersecurity capabilities of any model in the world, alongside state-of-the-art performance in software engineering, knowledge work, vision, and scientific research. Access is restricted to a small group of trusted cyberdefenders and infrastructure providers through Project Glasswing.
Claude Fable 5
Anthropic's first publicly available Mythos-class model, exceeding the capabilities of any model the company has previously made generally available. State-of-the-art on nearly all tested benchmarks, with exceptional performance in software engineering, knowledge work, vision, and scientific research. Its lead grows on longer and more complex tasks. Ships with built-in safeguards that route sensitive cybersecurity, biology, chemistry, and distillation queries to Claude Opus 4.8.
Gemma 4 12B
Google's medium-size open-weight model with 12 billion parameters from the Gemma 4 family. Encoder-free unified multimodal architecture that natively processes text, image, audio, and video inputs without dedicated encoders. Features a 256K context window and supports 140+ languages. First medium-sized model capable of natively ingesting audio. Suitable for local deployment on GPUs with 16GB VRAM.
Nemotron 3 Ultra
NVIDIA's flagship open 550B-parameter Mixture-of-Experts model with 55B active parameters, built for frontier reasoning and orchestration in long-running agentic systems. Features hybrid Mamba-Transformer architecture, LatentMoE routing, multi-token prediction, and NVFP4 precision for 5x higher throughput. Achieves 30% lower cost-to-task-completion on agentic benchmarks. Supports 1M+ token context window with 95% accuracy on Ruler@1M.
MiniMax M3
MiniMax's frontier open-weight model with 1M-token context window, native multimodality (text, image, video), and strong coding capabilities. Built on MiniMax Sparse Attention (MSA) architecture, achieving 59% on SWE-Bench Pro with significantly improved efficiency at long context.
Claude Opus 4.8
Anthropic's most advanced model, building on Opus 4.7 with improvements across benchmarks in coding, agentic skills, reasoning, and knowledge work. Features enhanced honesty, better tool use efficiency, dynamic workflows support, and improved alignment.
Jamba Large 1.7
AI21's latest hybrid SSM-Transformer model with Mixture-of-Experts architecture. Features a 256K context window, improved grounding and instruction-following. 94B total parameters with 398B active, optimized for enterprise long-context tasks.
Palmyra X5
Writer's most advanced adaptive reasoning model with a 1 million token context window. Processes full million-token prompts in approximately 22 seconds with multi-turn function calls in 300ms. Optimized for enterprise agentic AI workflows at 3-4x lower cost than GPT-4.1.
Snowflake Arctic
Snowflake's enterprise-focused open LLM with 480B total parameters using a fine-grained MoE architecture with only 17B active parameters per input. Apache 2.0 licensed, excels at SQL generation, coding, and enterprise intelligence tasks with breakthrough training efficiency.
Falcon-H1
TII's hybrid Mamba-Transformer model that outperforms comparable offerings from Meta's Llama and Alibaba's Qwen in the 30-70B parameter range. Designed for real-world AI on everyday devices and resource-limited settings with state-of-the-art efficiency.
Falcon 3 10B
TII's open-source 10B parameter model from the Falcon 3 family. Achieved number one position on Hugging Face's LLM leaderboard in its size category, outperforming Meta's Llama variants and other models under 13B parameters.
Yi-Lightning
01.AI's flagship large language model with enhanced Mixture-of-Experts architecture. Ranked 6th on Chatbot Arena with particularly strong results in Chinese, Math, Coding, and Hard Prompts categories. Features advanced expert segmentation and optimized KV-caching.
DBRX
Databricks' open-source 132B parameter Mixture-of-Experts transformer model with 36B active parameters per input. Released under Databricks Open Model License, optimized for enterprise workloads including SQL generation and coding tasks.
StableLM 2 12B
Stability AI's 12.1 billion parameter decoder-only language model pre-trained on 2 trillion tokens of diverse multilingual and code datasets. Supports multiple languages and offers strong performance for its compact size with instruction-tuned chat variant available.
Ring-2.6-1T
InclusionAI's (Ant Group) trillion-parameter open-weights reasoning model with 63B active parameters per token. Built for real-world agent workflows with adaptive reasoning-effort modes. Features hybrid linear and MLA attention architecture with MIT license.
Solar Pro 3
Upstage's powerful Mixture-of-Experts language model with 102B total parameters and 12B active parameters per forward pass. Optimized for Korean with strong English and Japanese support. Excels at complex reasoning, structured output generation, and agentic workflows.
K2 Think
A 32 billion parameter open-weights reasoning model by LLM360/MBZUAI, built on Qwen2.5-32B. Trained with reinforcement learning and verifiable rewards for long chain-of-thought reasoning, agentic planning, and complex problem solving in math, science, and code.
Qwen 3.7 Max
Alibaba's flagship proprietary model engineered for advanced agentic coding, complex reasoning, and long-horizon task execution. Ranked
Qwen 3.7 Plus
Alibaba's multimodal variant in the Qwen 3.7 family, optimized for vision understanding and multimodal tasks. Ranked
Gemini 3 Flash
Google's balanced model combining Gemini 3 Pro's reasoning capabilities with the Flash line's latency, efficiency, and cost. Features configurable thinking levels, multimodal function responses, and streaming function calling for complex agentic workflows.
Gemini 3.1 Flash-Lite
Google's most cost-efficient Gemini model optimized for high-volume, low-latency use cases. Delivers 2.5x faster time to first token versus Gemini 2.5 Flash with full multimodal support. Ideal for agentic tasks, data extraction, translation, and classification.
Granite 4.1 8B
IBM's dense decoder-only 8B parameter language model from the Granite 4.1 family. Supports 131K-token context, tool calling, RAG, code generation with fill-in-the-middle, text summarization, classification, and extraction across 12 languages. Released under Apache 2.0.
Granite 4.1 30B
IBM's largest dense decoder-only 30B parameter language model from the Granite 4.1 family. Trained on approximately 15T tokens with long-context extension up to 512K tokens. Supports tool calling, RAG, code generation, multilingual tasks across 12 languages. Released under Apache 2.0.
Laguna M.1
Poolside AI's flagship agentic coding model with 225B total parameters and 23B active (MoE). Trained from scratch in-house on 30T tokens across 6,144 NVIDIA Hopper GPUs. Optimized for complex multi-step software engineering tasks including codebase exploration, file editing, test running, and iterative debugging.
GPT-5.5
OpenAI's most capable model designed for complex real-world work including coding, online research, information analysis, and document creation. Features advanced agentic capabilities with tool search and multi-step task execution.
DeepSeek V4 Pro
DeepSeek's flagship V4 model with 1.6T total parameters (49B activated). MoE architecture supporting 1M token context. Closes the gap with frontier proprietary models on reasoning and coding benchmarks.
DeepSeek V4 Flash
DeepSeek's efficient V4 model with 284B total parameters (13B activated). Optimized for speed and cost-efficiency while maintaining strong performance. Supports 1M token context window.
MiMo-V2.5-Pro
Xiaomi's flagship 1.02T-parameter Mixture-of-Experts model with 42B active parameters, built on a hybrid-attention architecture with 3-layer Multi-Token Prediction. Designed for complex agentic tasks, software engineering, and long-horizon instruction following with a 1M-token context window.
Qwen 3.6 27B
Alibaba's dense 27B parameter model that outperforms its own 397B MoE predecessor on agentic coding benchmarks. Strong multilingual and reasoning capabilities released under Apache 2.0.
Hy3 Preview
Tencent's flagship open-weight Mixture-of-Experts model from the Hunyuan family with 295B total parameters and 21B active. Integrates fast and slow thinking modes with configurable reasoning effort. Designed for agentic workflows, cross-file code refactoring, long-document analysis, and multi-step tool use.
Qwen 3.6 35B-A3B
Alibaba's efficient Mixture-of-Experts model with 35B total parameters and 3B active per token. Frontier-level agentic coding performance with 73.4% on SWE-bench Verified and 92.7 on AIME 2026. Released under Apache 2.0.
GPT-5.4 Mini
OpenAI's compact reasoning model optimized for coding, computer use, and subagent tasks. Approaches GPT-5.4 performance on several benchmarks while running more than 2x faster.
Muse Spark
Meta Superintelligence Labs' first model, featuring advanced reasoning, multimodal understanding, and agentic capabilities. Processes voice, text, and image inputs with tool use and multi-agent orchestration. Powers Meta AI across its product ecosystem.
Qwen 3.6 Plus
Alibaba's proprietary flagship model in the Qwen 3.6 family, targeting enterprise AI workflows with stronger agentic coding capability, visual coding support, and end-to-end enterprise engineering features.
Gemma 4 26B
Google's high-performance open-weight dense model with 26 billion parameters from the Gemma 4 family. Supports multimodal inputs including text and images with a 256K extended context window. Strong reasoning and code generation capabilities with all parameters active per forward pass.
Gemma 4 31B
Google's flagship open-weight dense model with 31 billion parameters from the Gemma 4 family. All parameters active per forward pass with top-tier performance on reasoning benchmarks including AIME 2026 and MMLU Pro. Supports vision and extended 256K context window.
Gemma 4 31B
Google's flagship open-weight dense model with 31B parameters. All parameters active per forward pass. Ranks among top open models with strong performance on AIME 2026 (89.2%) and MMLU Pro (85.2%). Supports vision and extended context.
Gemma 4 E4B
Google's efficient 4 billion parameter variant from the Gemma 4 family. Designed for resource-constrained environments while maintaining strong text generation quality. Text-only model with a 32K context window, balancing performance and efficiency.
Claude Opus 4.7
Anthropic's latest and most advanced model with state-of-the-art reasoning, coding, and analysis capabilities. Features improved tool use, extended thinking, and enhanced safety alignment.
GPT-OSS 20B
OpenAI's compact open-weight model with 20 billion parameters. Released under Apache 2.0 license, designed for efficient deployment on consumer hardware while maintaining strong coding and reasoning capabilities.
GPT-OSS 120B
OpenAI's first open-weight large model with 120 billion parameters. Released under Apache 2.0 license, offering strong performance on reasoning and coding tasks while being fully self-hostable.
Grok 4.3
xAI's latest and most intelligent model with strong agentic tool calling, minimal hallucinations, and configurable reasoning. Supports 1M token context window with competitive pricing.
Nemotron 3 Super 120B
NVIDIA's open hybrid Mamba-Transformer MoE model with 120B total parameters (12B active). Features 1M token context window and excels at agentic reasoning, coding, planning, and tool calling.
GPT-5.4
OpenAI's frontier reasoning model combining advances in coding, reasoning, and agentic workflows. Features 1.1M token context window and strong performance on complex multi-step problems.
GLM-5.1
Zhipu AI's latest bilingual model with strong Chinese and English capabilities. Features improved reasoning, coding, and tool use with competitive performance on academic benchmarks.
Kimi K2.6
Moonshot AI's latest model with ultra-long context window support, strong reasoning capabilities, and excellent performance on complex multi-step tasks. Known for reliable long-document understanding.
Gemini 3.1 Pro
Google's latest flagship multimodal model with state-of-the-art performance on reasoning, coding, and multimodal understanding. Features native tool use, grounding, and million-token context window.
Mistral Small 4
Mistral AI's efficient hybrid model unifying instruct, reasoning, and coding in a single model. Open-weight under Apache 2.0 with strong performance for its size class.
GPT-5.5 Pro
OpenAI's premium tier model with extended reasoning capabilities, higher accuracy on complex tasks, and priority access. Optimized for professional and enterprise workloads requiring maximum quality.
Qwen 3.6
Alibaba's latest Qwen model with enhanced reasoning, multilingual capabilities, and improved instruction following. Features strong performance on coding, math, and general knowledge benchmarks.
MiniMax M2.7
MiniMax's latest large language model with strong multilingual and multimodal capabilities. Competitive pricing with high-quality text generation and improved reasoning performance.
Grok 4.20
xAI's multi-agent capable model with 2M token context window. Available in reasoning, non-reasoning, and multi-agent variants for diverse enterprise workloads.
Mistral Medium 3.5
Mistral AI's balanced model offering strong multilingual performance with excellent price-performance ratio. Optimized for production workloads requiring reliable quality across European and global languages.
Grok 4
xAI's latest model with real-time information access, strong reasoning capabilities, and competitive performance on coding and analysis tasks. Features improved tool use and multimodal understanding.
DeepSeek V4
DeepSeek's fourth-generation model with improved mixture-of-experts architecture, enhanced reasoning and coding capabilities, and stronger multilingual performance. Competitive with frontier proprietary models.
Claude Sonnet 4.6
Anthropic's balanced model offering strong performance at lower cost and latency than Opus. Excellent for everyday coding, analysis, and content generation tasks with good reasoning capabilities.
Claude Opus 4.6
Anthropic's most capable model in the Claude 4 family, excelling at complex analysis, extended reasoning, scientific research, and advanced code generation. Features significantly improved accuracy and reduced hallucinations.
Devstral 2
Mistral AI's frontier code agents model designed for solving software engineering tasks. Open-weight model optimized for agentic coding workflows and complex development tasks.
Mistral Large 3
Mistral AI's largest open-weight model with 41B active parameters (675B total MoE). State-of-the-art general-purpose multimodal model with 256K context window and powerful agentic capabilities. Released under Apache 2.0.
GigaChat 3.1 Ultra
Sber's flagship large-scale Mixture-of-Experts model with 702B total parameters and 36B active. Designed for multilingual assistant workloads, reasoning, code generation, tool use, and large-cluster deployment. Open-weight release.
GigaChat 3.1 Lightning
Sber's compact Mixture-of-Experts model with 10B total parameters and 1.8B active. Designed for fast multilingual assistant workloads, reasoning, code, function calling, and product-style deployment on edge devices.
Grok 4.1 Fast
xAI's fast and cost-effective model with 2M token context window. Offers both reasoning and non-reasoning modes at significantly lower pricing than flagship models.
Claude Sonnet 4.5
Anthropic's previous-generation balanced model with strong coding and analysis capabilities. Offers excellent price-performance ratio for production workloads requiring reliable quality.
Claude Haiku 4.5
Anthropic's fastest model with near-frontier intelligence. Optimized for high-throughput, low-latency applications requiring quick responses at minimal cost. Supports extended thinking.
GLM-4.7
Zhipu AI's multilingual agentic coding model with strong reasoning, tool use, and UI generation capabilities. Predecessor to GLM-5.1 with competitive performance on coding benchmarks.
AlemLLM
Kazakhstan's flagship Mixture-of-Experts language model developed by Astana Hub with technical support from 01.AI. Features 247B total parameters with 22B active per token, achieving state-of-the-art results on Kazakh, Russian, and English benchmarks. Outperforms GPT-4o on Kazakh language tasks.
Trendyol LLM 8B T1
Turkish-optimized 8B chat model developed by Trendyol, Turkey's largest e-commerce platform. Built on Qwen3-8B and fine-tuned on large-scale Turkish e-commerce datasets. Features advanced chain-of-thought reasoning in Turkish with dual operation modes (/think and /no_think), strong instruction following, summarization, coding, and attribute extraction for catalogue enrichment. English reasoning capabilities are preserved alongside Turkish.
Gemini 2.5 Pro
Google's high-capability reasoning model with adaptive thinking for complex agentic and multimodal challenges. Features 1M token context window and strong performance on coding and scientific tasks.
Gemini 2.5 Flash
Google's cost-effective model optimized for high throughput tasks. Balances speed and intelligence with strong multimodal capabilities and 1M token context window.
GPT-5
OpenAI's fifth-generation flagship model with significant improvements in reasoning, multimodal understanding, and code generation. Features enhanced instruction following and expanded context window.
Nemotron Nano 9B v2
NVIDIA's compact 9B parameter model trained from scratch for both reasoning and non-reasoning tasks. Generates reasoning traces before final responses. Efficient for edge and on-device deployment.
YandexGPT 5 Lite
Yandex's compact 8B parameter language model trained on 15T tokens of primarily Russian and English text. Features 32K context window with strong performance on web, code, and mathematics tasks. Open-weight release.
Kumru 7B
Turkish large language model developed by VNGRS, pre-trained from scratch on 500 GB of Turkish corpora (300B tokens). Decoder-only architecture with a custom tokenizer optimized for Turkish, supporting code, math, and chat. Outperforms significantly larger multilingual models on the Cetvel Turkish benchmark. Available for on-premise enterprise deployment.
Llama 4 Scout
Meta's efficient MoE model with 17B active parameters (109B total, 16 experts). Supports up to 10M token context — the longest of any production model. Strong performance on reasoning and multilingual tasks.
Llama 4 Maverick
Meta's quality-focused MoE model with 17B active parameters (400B total, 128 experts). Targets quality-critical tasks with benchmark scores competitive with GPT-4o and Gemini 2.5 Pro.
Qwen3 32B
Alibaba's Qwen3 32B dense language model with strong reasoning and multilingual capabilities, supporting function calling and code generation across diverse tasks.
Qwen3 Coder
Alibaba's Qwen3 Coder model optimized for software development tasks including code generation, debugging, code review, and technical documentation with strong multilingual programming support.
Qwen3 235B
Alibaba's Qwen3 235B mixture-of-experts model delivering frontier-level performance with advanced reasoning, function calling, and code generation capabilities at massive scale.
Gemma 3 4B
Google's compact open-weight model with 4 billion parameters from the Gemma 3 family. Supports multimodal inputs including text and images with a 128K context window. Balances efficiency and capability for vision and language tasks.
Gemma 3 12B
Google's mid-size open-weight model with 12 billion parameters from the Gemma 3 family. Supports multimodal inputs including text and images with a 128K context window. Strong performance on reasoning and code generation tasks at moderate compute cost.
Gemma 3 27B
Google's largest open-weight model in the Gemma 3 family with 27 billion parameters. Supports multimodal inputs including text and images with a 128K context window. Delivers strong performance across reasoning, code generation, and vision tasks, competitive with larger proprietary models.
Mistral Small 3.1
Mistral AI's Small 3.1 model with 24B parameters offering efficient multimodal capabilities including vision, function calling, and code generation with a large 128K context window.
Command A
Cohere's flagship 111B parameter model optimized for demanding enterprises requiring fast, secure, and high-quality AI. Excels at RAG, tool use, and multilingual tasks with strong reasoning capabilities.
Phi-4 Mini
Microsoft's Phi-4 Mini model with 3.8B parameters providing lightweight yet capable language understanding and code generation, optimized for resource-constrained deployments with a large 128K context window.
DeepSeek R1
DeepSeek's reasoning-focused model trained with reinforcement learning for complex multi-step reasoning. Excels at math, science, and coding problems requiring chain-of-thought reasoning.
Codestral
Mistral AI's cutting-edge code generation model specializing in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code completion, correction, and test generation. Features efficient architecture with 2x faster generation than its predecessor.
ISSAI KazLLM 1.0 70B
Large language model developed by ISSAI (Nazarbayev University) customized from Llama 3.1 70B to improve helpfulness of responses in the Kazakh language. Part of Kazakhstan's initiative to ensure the country benefits from generative AI advancements.
Llama 3.3 70B Instruct
Meta's flagship open-weight model with 70 billion parameters. Strong multilingual capabilities with competitive performance on reasoning and coding benchmarks. Available for self-hosting and through various inference providers.
Command R7B
Cohere's compact 7B parameter model optimized for RAG, tool use, and code tasks. Delivers top-tier speed and efficiency on commodity GPUs and edge devices with 128K context window.
Phi-4
Microsoft's Phi-4 model with 14B parameters excelling at reasoning and code generation tasks, delivering strong performance relative to its compact size with efficient inference characteristics.
DeepSeek V3
DeepSeek's third-generation large language model featuring mixture-of-experts architecture, strong multilingual capabilities, and competitive performance on reasoning and coding benchmarks.
Llama 3.2 11B Vision Instruct
Meta's multimodal open-weight model with 11 billion parameters from the Llama 3.2 family. Supports both text and image inputs, enabling visual understanding tasks alongside standard text generation. Suitable for applications requiring vision capabilities at moderate scale.
Llama 3.2 3B Instruct
Meta's lightweight open-weight model with 3 billion parameters from the Llama 3.2 family. Designed for on-device and edge deployment with strong text generation capabilities relative to its size. Supports instruction following and general-purpose tasks.
Llama 3.2 90B Vision Instruct
Meta's largest multimodal open-weight model with 90 billion parameters from the Llama 3.2 family. Delivers strong performance on both text and image understanding tasks with competitive results on visual reasoning benchmarks. Designed for high-quality inference requiring vision capabilities.
Llama 3.1 8B Instruct
Meta's efficient open-weight model with 8 billion parameters from the Llama 3.1 family. Optimized for instruction following with strong performance on general tasks, coding, and multilingual benchmarks. Ideal for cost-effective deployment and edge inference scenarios.