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 · Normalized
openLLMLeaderboardV2 · Open LLM Leaderboard v2 · Normalized score · percent
- nvidia/AceMath-72B-Instructnvidia71.45%
- nvidia/AceMath-7B-Instructnvidia63.369%
- nvidia/AceInstruct-72Bnvidia62.613%
- Qwen/Qwen2.5-32B-Instructqwen62.538%
- Qwen/Qwen2.5-Math-72B-Instructqwen62.387%
- maldv/Awqward2.5-32B-Instructmaldv62.311%
- Saxo/Linkbricks-Horizon-AI-Avengers-V6-32Bsaxo62.236%
- Saxo/Linkbricks-Horizon-AI-Avengers-V3-32Bsaxo61.782%
- tanliboy/lambda-qwen2.5-32b-dpo-testtanliboy61.027%
- Saxo/Linkbricks-Horizon-AI-Avengers-V1-32Bsaxo60.272%
- huihui-ai/Qwen2.5-72B-Instruct-abliteratedhuihui-ai60.121%
- RDson/WomboCombo-R1-Coder-14B-Previewrdson59.894%
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.