LLM Stats · GitHub archive

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

DROP · Raw

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

  1. DeepSeek: DeepSeek V3deepseek0.916

CBNSL · Raw

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

  1. MoonshotAI: Kimi K2 0711moonshotai0.956

Scale MultiChallenge · Normalized (reported)

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

  1. OpenAI: o3openai0.565

GSM8k · Raw

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

  1. OpenAI: o1openai0.971

EvalPlus · Raw

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

  1. Qwen/Qwen2-72Bqwen0.79
  2. Qwen2-7B-Instructqwen0.703

HumanEvalFIM-Average · Raw

llmStatsArchive · LLM Stats · GitHub archive · HumanEvalFIM-Average · Raw · score · Higher is better

  1. mistralai/Codestral-22B-v0.1mistralai0.916

MGSM · Normalized (reported)

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

  1. OpenAI: GPT-4o (2024-05-13)openai0.905
  2. OpenAI: GPT-4o-mini (2024-07-18)openai0.87
  3. Qwen: Qwen3 235B A22Bqwen0.835

WritingBench · Normalized (reported)

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

  1. Qwen: Qwen3 235B A22B Instruct 2507qwen0.852

Android Control High_EM · Raw

llmStatsArchive · LLM Stats · GitHub archive · Android Control High_EM · Raw · score · Higher is better

  1. Qwen/Qwen2.5-VL-32B-Instructqwen0.696
  2. Qwen: Qwen2.5 VL 72B Instructqwen0.674
  3. Qwen/Qwen2.5-VL-7B-Instructqwen0.601

Spider · Raw

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

  1. mistralai/Codestral-22B-v0.1mistralai0.635

MBPP · Normalized (reported)

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

  1. nvidia/Llama-3_3-Nemotron-Super-49B-v1nvidia0.913

DROP · Normalized (reported)

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

  1. google/gemma-3n-E4Bgoogle0.608
  2. google/gemma-3n-E2Bgoogle0.539

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