Open LLM Leaderboard v2

Indexed results from Open LLM Leaderboard v2 · Archive. Each ranking retains its own metric and evaluation conditions.

Open LLM v2 BBH · Raw

openLLMLeaderboardV2 · Open LLM Leaderboard v2 · Raw accuracy · percent

  1. qingy2024/Benchmaxx-Llama-3.2-1B-Instructqingy202482.691%
  2. JungZoona/T3Q-Qwen2.5-14B-Instruct-1M-e3jungzoona75.86%
  3. JungZoona/T3Q-qwen2.5-14b-v1.0-e3jungzoona75.86%
  4. IntervitensInc/internlm2_5-20b-llamafiedintervitensinc74.785%
  5. internlm/internlm2_5-20b-chatinternlm74.736%
  6. shuttleai/shuttle-3shuttleai74.203%
  7. Sakalti/ultiima-72B-v1.5sakalti73.917%
  8. MaziyarPanahi/calme-3.2-instruct-78bmaziyarpanahi73.186%
  9. newsbang/Homer-v1.0-Qwen2.5-72Bnewsbang73.098%
  10. MaziyarPanahi/calme-3.1-instruct-78bmaziyarpanahi73.052%
  11. MaziyarPanahi/calme-2.4-rys-78bmaziyarpanahi72.795%
  12. MaziyarPanahi/calme-2.2-qwen2.5-72bmaziyarpanahi72.764%

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