Noticias de IA

Nuestra fotografía anual de datos: quién lidera el Podium Score, qué tan amplia es la brecha de pesos abiertos, dónde quedaron los precios y qué benchmarks definieron el año.

¿Qué modelos de IA escriben el mejor código en 2026? Comparamos Claude Fable 5, Claude Mythos Preview, GPT-5.6 Sol y Kimi K3 en SWE-Bench Verified, LiveCodeBench y Terminal-Bench.

Kimi K3 logra 83.3 de Podium Score — más cerca de los modelos propietarios de frontera que nunca. Cuantificamos la brecha de pesos abiertos de 2026 con datos agregados de rankings.

Una brecha de 178×: los LLMs de frontera más baratos y más caros de 2026, análisis de precio por inteligencia y dónde está el punto óptimo de valor.

Anthropic's next-generation model family, top-ranked on BenchLM with highest composite score.

Gemini 3.5 Flash-Lite lidera con 389 tokens/segundo. Ranking completo de velocidad de modelos frontera y por qué la velocidad es el benchmark más subestimado.

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows.

Compact Inkling variant for fast, cheap inference.

Research preview of Anthropic’s next-generation model family.

Added Alibaba Qwen 3 235B MoE model with hybrid thinking mode to all leaderboards.

Updated LiveCodeBench scores for all models with latest contamination-free results.

Alibaba’s newest hosted flagship, a fast riser on human preference arenas.

Anthropic frontier model with adaptive reasoning effort levels, leading agentic coding benchmarks.

Added Meta Llama 4 Maverick 400B MoE model with 1M context window support.

Lowest-cost Gemini 3.5 tier for extremely high-throughput serving.

Newest Flash-class Gemini, near-pro intelligence at 200+ tokens/s.

Added full benchmark suite for Claude Opus 4 including SWE-Bench and AIME scores.

Moonshot’s frontier MoE with 1M context, top-tier agentic benchmark results.

Thinking Machines’ first frontier model.

Entendiendo las arenas LLM: evaluaciones en vivo que revelan qué modelos prefiere la gente realmente.

LLMPodium now available in 10 languages: EN, ZH, JA, KO, TH, RU, DE, ES, IT, FR.

Meta’s proprietary frontier model line, top-10 on blind human preference.

Fast, cheap GPT-5.6 variant built for high-volume production traffic.

Mid-tier GPT-5.6 model balancing intelligence with very high throughput.

Flagship of the GPT-5.6 series for complex reasoning, coding and multi-step agentic workflows.

xAI flagship with real-time knowledge and strong agentic results.

Added Google Gemini 2.5 Pro and 2.5 Flash with thinking capabilities.

Tencent’s latest Hunyuan generation model.

Cómo evitar la contaminación de datos y construir evaluaciones confiables.

Updated pricing data for all models from official API documentation.

Balanced Claude tier with adaptive reasoning, strong speed-to-intelligence ratio.

Updated SWE-Bench Verified scores for frontier models.

Added DeepSeek R1 reasoning model with chain-of-thought capabilities.

Cómo LLMPodium normaliza y pondera puntuaciones de múltiples clasificaciones.

New Arena page for side-by-side model comparison launched.

Z.ai flagship with strong agent tool use and 150+ tokens/s.

Code-specialized Kimi variant for repository-level engineering.

Anthropic flagship with adaptive reasoning and Opus-class fallback, tuned for the hardest open-ended and agentic tasks.

NVIDIA’s 550B open MoE built for enterprise reasoning pipelines.

Nex AGI’s efficiency-focused frontier model.