Open-Source LLM and Leaderboard 2026 Collaboration
benchmarks claude open-source
| Source: Mastodon | Original article
Open-source LLMs narrow gap with proprietary models. Open-source options are 3x cheaper per output token.
The Open-Source LLM Leaderboard 2026 has been released, ranking the best open-source language models. Kimi K3 takes the top spot in the open-weight category with a score of 57.1, while Claude Fable 5 leads the proprietary models with a score of 59.9. Notably, Kimi K3 is 3x cheaper per 1M output tokens than its proprietary counterpart.
This leaderboard matters as it highlights the growing competitiveness of open-source LLMs, offering a more affordable alternative to proprietary models without significant performance compromises. The gap between open-source and proprietary models has narrowed to 2.8 points, indicating the rapid progress of open-source development.
As the open-source LLM landscape continues to evolve, it will be interesting to watch how these models perform in various benchmarks and applications. The leaderboard will likely be updated regularly, reflecting new releases and improvements in open-source models. With multiple sources providing rankings and comparisons, users can now make informed decisions when choosing between open-source and proprietary LLMs.
Sources
Back to AIPULSEN