LLM Stats · GitHub archive
Indexed results from LLM Stats · GitHub archive. Each ranking retains its own metric and evaluation conditions.
ACEBench · Raw
llmStatsArchive · LLM Stats · GitHub archive · ACEBench · Raw · score · Higher is better
Global-MMLU-Lite · Normalized (reported)
llmStatsArchive · LLM Stats · GitHub archive · Global-MMLU-Lite · Normalized (reported) · score · Higher is better
AIME 2025 · Raw
llmStatsArchive · LLM Stats · GitHub archive · AIME 2025 · Raw · score · Higher is better
LongBench v2 · Normalized (reported)
llmStatsArchive · LLM Stats · GitHub archive · LongBench v2 · Normalized (reported) · score · Higher is better
IFEval · Normalized (reported)
llmStatsArchive · LLM Stats · GitHub archive · IFEval · Normalized (reported) · score · Higher is better
MBPP · Normalized (reported)
llmStatsArchive · LLM Stats · GitHub archive · MBPP · Normalized (reported) · score · Higher is better
HMMT25 · Normalized (reported)
llmStatsArchive · LLM Stats · GitHub archive · HMMT25 · Normalized (reported) · score · Higher is better
SWE-Bench Verified · Normalized (reported)
llmStatsArchive · LLM Stats · GitHub archive · SWE-Bench Verified · Normalized (reported) · score · Higher is better
GPQA · Normalized (reported)
llmStatsArchive · LLM Stats · GitHub archive · GPQA · Normalized (reported) · score · Higher is better
- DeepSeek: DeepSeek-R1-Distill-Llama-70Bdeepseek0.652
- deepseek-ai/DeepSeek-R1-Distill-Qwen-32Bdeepseek0.621
- DeepSeek: DeepSeek-R1-Distill-Qwen-14Bdeepseek0.591
- DeepSeek: DeepSeek-R1-Distill-Qwen-7Bdeepseek0.491
- DeepSeek: DeepSeek-R1-Distill-Llama-8Bdeepseek0.49
- deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5Bdeepseek-ai0.338
MATH-500 · Normalized (reported)
llmStatsArchive · LLM Stats · GitHub archive · MATH-500 · Normalized (reported) · score · Higher is better
HMMT 2025 · Normalized (reported)
llmStatsArchive · LLM Stats · GitHub archive · HMMT 2025 · Normalized (reported) · score · Higher is better
GPQA · Normalized (reported)
llmStatsArchive · LLM Stats · GitHub archive · GPQA · Normalized (reported) · score · Higher is better
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.