LLM Stats · GitHub archive

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

HMMT 2025 · Normalized (reported)

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

  1. DeepSeek: DeepSeek V3.2 Expdeepseek0.836

GSM8k · Raw

llmStatsArchive · LLM Stats · GitHub archive · GSM8k · Raw · score · Higher is better

  1. MoonshotAI: Kimi K2 0711moonshotai0.973
  2. Qwen: Qwen3 235B A22Bqwen0.944
  3. Mistral Large 2407mistralai0.93
  4. Qwen/Qwen2-72Bqwen0.911
  5. Qwen2-7B-Instructqwen0.823

HumanEval-Mul · Raw

llmStatsArchive · LLM Stats · GitHub archive · HumanEval-Mul · Raw · score · Higher is better

  1. DeepSeek: DeepSeek V3deepseek0.826
  2. deepseek-ai/DeepSeek-V2.5deepseek0.738

MultiChallenge (o3-mini grader) · Raw

llmStatsArchive · LLM Stats · GitHub archive · MultiChallenge (o3-mini grader) · Raw · score · Higher is better

  1. OpenAI: GPT-5openai0.696

MMLU-ProX · Normalized (reported)

llmStatsArchive · LLM Stats · GitHub archive · MMLU-ProX · Normalized (reported) · score · Higher is better

  1. Qwen: Qwen3 235B A22B Instruct 2507qwen0.794

FRAMES · Normalized (reported)

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

  1. DeepSeek: DeepSeek V3deepseek0.733

MMMLU · Normalized (reported)

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

  1. Qwen: Qwen3 235B A22Bqwen0.867
  2. OpenAI: GPT-4o (2024-08-06)openai0.814

Humanity's Last Exam · Raw

llmStatsArchive · LLM Stats · GitHub archive · Humanity's Last Exam · Raw · score · Higher is better

  1. OpenAI: o3openai0.202

SimpleQA · Normalized (reported)

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

  1. Qwen: Qwen3 235B A22B Instruct 2507qwen0.543
  2. Google: Gemini 2.5 Progoogle0.508
  3. Google: Gemini 2.5 Flashgoogle0.269

SlakeVQA · Normalized (reported)

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

  1. google/medgemma-4b-itgoogle0.623

AIME 2025 · Normalized (reported)

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

  1. deepseek-v3.1deepseek0.498

TAU-bench Retail · Raw

llmStatsArchive · LLM Stats · GitHub archive · TAU-bench Retail · Raw · score · Higher is better

  1. OpenAI: GPT-4o (2024-08-06)openai0.603

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