Open LLM Leaderboard v2

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

Open LLM v2 MATH Lvl 5 · Raw

openLLMLeaderboardV2 · Open LLM Leaderboard v2 · Raw accuracy · percent

  1. nvidia/AceMath-72B-Instructnvidia71.45%
  2. nvidia/AceMath-7B-Instructnvidia63.369%
  3. nvidia/AceInstruct-72Bnvidia62.613%
  4. Qwen/Qwen2.5-32B-Instructqwen62.538%
  5. Qwen/Qwen2.5-Math-72B-Instructqwen62.387%
  6. maldv/Awqward2.5-32B-Instructmaldv62.311%
  7. Saxo/Linkbricks-Horizon-AI-Avengers-V6-32Bsaxo62.236%
  8. Saxo/Linkbricks-Horizon-AI-Avengers-V3-32Bsaxo61.782%
  9. tanliboy/lambda-qwen2.5-32b-dpo-testtanliboy61.027%
  10. Saxo/Linkbricks-Horizon-AI-Avengers-V1-32Bsaxo60.272%
  11. huihui-ai/Qwen2.5-72B-Instruct-abliteratedhuihui-ai60.121%
  12. RDson/WomboCombo-R1-Coder-14B-Previewrdson59.894%

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