Open LLM Leaderboard v2
Indexed results from Open LLM Leaderboard v2 · Archive. Each ranking retains its own metric and evaluation conditions.
Open LLM v2 IFEval · Normalized
openLLMLeaderboardV2 · Open LLM Leaderboard v2 · Normalized score · percent
- Meta: Llama 3.3 70B Instructmeta-llama89.976%
- Meta: Llama 3.1 70B Instructmeta-llama86.689%
- MaziyarPanahi/calme-2.1-qwen2.5-72bmaziyarpanahi86.624%
- VAGOsolutions/Llama-3.1-SauerkrautLM-70b-Instructvagosolutions86.564%
- Qwen2.5 72B Instructqwen86.384%
- MaziyarPanahi/calme-2.3-llama3.1-70bmaziyarpanahi86.047%
- huihui-ai/Qwen2.5-72B-Instruct-abliteratedhuihui-ai85.927%
- MaziyarPanahi/calme-2.2-llama3.1-70bmaziyarpanahi85.927%
- YOYO-AI/ZYH-LLM-Qwen2.5-14B-V3yoyo-ai85.779%
- pankajmathur/orca_mini_v8_1_70bpankajmathur85.714%
- dnhkng/RYS-Llama3.1-Largednhkng84.92%
- rubenroy/Gilgamesh-72Brubenroy84.86%
Models
LoadingBenchmarks
Explore every benchmark
LoadingThese charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.