Open LLM Leaderboard v2
Indexed results from Open LLM Leaderboard v2 · Archive. Each ranking retains its own metric and evaluation conditions.
Open LLM v2 MMLU-PRO · Raw
openLLMLeaderboardV2 · Open LLM Leaderboard v2 · Raw accuracy · percent
- MaziyarPanahi/calme-3.2-instruct-78bmaziyarpanahi73.03%
- MaziyarPanahi/calme-3.1-instruct-78bmaziyarpanahi71.85%
- dfurman/CalmeRys-78B-Orpo-v0.1dfurman70.121%
- MaziyarPanahi/calme-2.4-rys-78bmaziyarpanahi70.022%
- glaiveai/Reflection-Llama-3.1-70Bglaiveai63.414%
- arcee-ai/Arcee-Blitzarcee-ai61.536%
- newsbang/Homer-v1.0-Qwen2.5-72Bnewsbang61.453%
- Sakalti/ultiima-72B-v1.5sakalti60.539%
- Qwen/Qwen2.5-72Bqwen59.683%
- Aryanne/QwentileSwaparyanne59.458%
- rombodawg/Rombos-LLM-V2.5-Qwen-72brombodawg59.35%
- rombodawg/Rombos-LLM-V2.5-Qwen-32brombodawg59.159%
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.