Open LLM Leaderboard v2
Indexed results from Open LLM Leaderboard v2 · Archive. Each ranking retains its own metric and evaluation conditions.
Open LLM v2 Average
openLLMLeaderboardV2 · Open LLM Leaderboard v2 · Normalized six-task average · percent
- MaziyarPanahi/calme-3.2-instruct-78bmaziyarpanahi52.081%
- MaziyarPanahi/calme-3.1-instruct-78bmaziyarpanahi51.287%
- dfurman/CalmeRys-78B-Orpo-v0.1dfurman51.231%
- MaziyarPanahi/calme-2.4-rys-78bmaziyarpanahi50.765%
- huihui-ai/Qwen2.5-72B-Instruct-abliteratedhuihui-ai48.106%
- Qwen2.5 72B Instructqwen47.98%
- MaziyarPanahi/calme-2.1-qwen2.5-72bmaziyarpanahi47.857%
- newsbang/Homer-v1.0-Qwen2.5-72Bnewsbang47.464%
- ehristoforu/qwen2.5-test-32b-itehristoforu47.368%
- Saxo/Linkbricks-Horizon-AI-Avengers-V1-32Bsaxo47.337%
- MaziyarPanahi/calme-2.2-qwen2.5-72bmaziyarpanahi47.225%
- fluently-lm/FluentlyLM-Prinumfluently-lm47.217%
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.