Comprehensive side-by-side LLM comparison
Qwen2.5 72B Instruct leads with 29.8% higher average benchmark score. Gemma 3n E2B Instructed LiteRT (Preview) supports multimodal inputs. Qwen2.5 72B Instruct is available on 4 providers. Overall, Qwen2.5 72B Instruct is the stronger choice for coding tasks.
Gemma 3N E2B IT LiteRT Preview was introduced as an experimental version optimized for LiteRT deployment, designed to push the boundaries of on-device AI. Built to demonstrate the potential of running instruction-tuned models on mobile and edge devices, it represents ongoing efforts to make AI more accessible across hardware platforms.
Alibaba Cloud / Qwen Team
Qwen 2.5 72B was developed as the flagship text model in the Qwen 2.5 series, designed to provide advanced language capabilities with 72 billion parameters. Built to compete with frontier models in reasoning, coding, and general language tasks, it represents Qwen's most capable instruction-following model in this generation.
8 months newer

Qwen2.5 72B Instruct
Alibaba Cloud / Qwen Team
2024-09-19

Gemma 3n E2B Instructed LiteRT (Preview)
2025-05-20
Context window and performance specifications
Average performance across 5 common benchmarks

Gemma 3n E2B Instructed LiteRT (Preview)

Qwen2.5 72B Instruct
Gemma 3n E2B Instructed LiteRT (Preview)
2024-06-01
Available providers and their performance metrics

Gemma 3n E2B Instructed LiteRT (Preview)

Qwen2.5 72B Instruct
DeepInfra

Gemma 3n E2B Instructed LiteRT (Preview)

Qwen2.5 72B Instruct

Gemma 3n E2B Instructed LiteRT (Preview)

Qwen2.5 72B Instruct
Fireworks
Hyperbolic
Together