New LLMs Debut with High Scores; Mistral, DeepSeek Hit 90%

A recent benchmark test of ten large language models revealed that five new model families debuted with scores of 75% or higher on coding tasks. Two models, Mistral Large 2411 and DeepSeek Chat V3-0324, achieved a record-tying 90% score. The L3 Lunaris 8B model stood out for its exceptional value, scoring 85% at an extremely low cost of $0.0001 per benchmark run. AI

IMPACT New models consistently achieve high scores on coding benchmarks, indicating rapid progress in agent capabilities and cost-efficiency.

RANK_REASON The article details benchmark results for multiple LLMs, including new families and record-breaking scores, which falls under research. [lever_c_demoted from research: ic=1 ai=1.0]

Read on dev.to — LLM tag →

• DeepSeek
• DeepSeek Chat V3-0324
• Inflection
• L3 Lunaris 8B
• Mancer
• Mistral Large 2411
• OpenRouter
• Qwen
• Qwen3 8B
• Qwen Plus 2025-07-28
• Sao10k
• Undi95

• model release
• product

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →