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

  1. MaziyarPanahi/calme-3.2-instruct-78bmaziyarpanahi52.081%
  2. MaziyarPanahi/calme-3.1-instruct-78bmaziyarpanahi51.287%
  3. dfurman/CalmeRys-78B-Orpo-v0.1dfurman51.231%
  4. MaziyarPanahi/calme-2.4-rys-78bmaziyarpanahi50.765%
  5. huihui-ai/Qwen2.5-72B-Instruct-abliteratedhuihui-ai48.106%
  6. Qwen2.5 72B Instructqwen47.98%
  7. MaziyarPanahi/calme-2.1-qwen2.5-72bmaziyarpanahi47.857%
  8. newsbang/Homer-v1.0-Qwen2.5-72Bnewsbang47.464%
  9. ehristoforu/qwen2.5-test-32b-itehristoforu47.368%
  10. Saxo/Linkbricks-Horizon-AI-Avengers-V1-32Bsaxo47.337%
  11. MaziyarPanahi/calme-2.2-qwen2.5-72bmaziyarpanahi47.225%
  12. fluently-lm/FluentlyLM-Prinumfluently-lm47.217%

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These 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.

Install TensorTrace