LLM Stats · GitHub archive

Indexed results from LLM Stats · GitHub archive. Each ranking retains its own metric and evaluation conditions.

C-Eval · Normalized (reported)

llmStatsArchive · LLM Stats · GitHub archive · C-Eval · Normalized (reported) · score · Higher is better

  1. DeepSeek: DeepSeek V3deepseek0.865

FrontierMath · Normalized (reported)

llmStatsArchive · LLM Stats · GitHub archive · FrontierMath · Normalized (reported) · score · Higher is better

  1. OpenAI: o3openai0.158

GPQA · Normalized (reported)

llmStatsArchive · LLM Stats · GitHub archive · GPQA · Normalized (reported) · score · Higher is better

  1. nvidia/Llama-3_3-Nemotron-Super-49B-v1nvidia0.667

MATH-500 · Normalized (reported)

llmStatsArchive · LLM Stats · GitHub archive · MATH-500 · Normalized (reported) · score · Higher is better

  1. DeepSeek: DeepSeek V3deepseek0.902

PathMCQA · Normalized (reported)

llmStatsArchive · LLM Stats · GitHub archive · PathMCQA · Normalized (reported) · score · Higher is better

  1. google/medgemma-4b-itgoogle0.698

LiveCodeBench v6 · Raw

llmStatsArchive · LLM Stats · GitHub archive · LiveCodeBench v6 · Raw · score · Higher is better

  1. Qwen: Qwen3 235B A22B Instruct 2507qwen0.518

Aider · Normalized (reported)

llmStatsArchive · LLM Stats · GitHub archive · Aider · Normalized (reported) · score · Higher is better

  1. Qwen: Qwen3 235B A22Bqwen0.618
  2. Qwen: Qwen3 32Bqwen0.502

Aider-Polyglot · Raw

llmStatsArchive · LLM Stats · GitHub archive · Aider-Polyglot · Raw · score · Higher is better

  1. OpenAI: o3openai0.813

AIME 2025 · Normalized (reported)

llmStatsArchive · LLM Stats · GitHub archive · AIME 2025 · Normalized (reported) · score · Higher is better

  1. nvidia/Llama-3.1-Nemotron-Nano-8B-v1nvidia0.471

Internal API instruction following (hard) · Raw

llmStatsArchive · LLM Stats · GitHub archive · Internal API instruction following (hard) · Raw · score · Higher is better

  1. OpenAI: GPT-4o (2024-08-06)openai0.292

MATH-500 · Raw

llmStatsArchive · LLM Stats · GitHub archive · MATH-500 · Raw · score · Higher is better

  1. nvidia/Llama-3_3-Nemotron-Super-49B-v1nvidia0.966

DocVQA · Normalized (reported)

llmStatsArchive · LLM Stats · GitHub archive · DocVQA · Normalized (reported) · score · Higher is better

  1. mistralai/Pixtral-12B-2409mistralai0.907

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