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

  1. MoonshotAI: Kimi K2 0711moonshotai0.765

Global-MMLU-Lite · Normalized (reported)

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

  1. Google: Gemini 2.5 Progoogle0.886
  2. Google: Gemini 2.5 Flashgoogle0.884

AIME 2025 · Raw

llmStatsArchive · LLM Stats · GitHub archive · AIME 2025 · Raw · score · Higher is better

  1. nvidia/Llama-3_3-Nemotron-Super-49B-v1nvidia0.584

LongBench v2 · Normalized (reported)

llmStatsArchive · LLM Stats · GitHub archive · LongBench v2 · Normalized (reported) · score · Higher is better

  1. DeepSeek: DeepSeek V3deepseek0.487

IFEval · Normalized (reported)

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

  1. nvidia/Llama-3.1-Nemotron-Nano-8B-v1nvidia0.793

MBPP · Normalized (reported)

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

  1. mistralai/Codestral-22B-v0.1mistralai0.782

HMMT25 · Normalized (reported)

llmStatsArchive · LLM Stats · GitHub archive · HMMT25 · Normalized (reported) · score · Higher is better

  1. Qwen: Qwen3 235B A22B Instruct 2507qwen0.554

SWE-Bench Verified · Normalized (reported)

llmStatsArchive · LLM Stats · GitHub archive · SWE-Bench Verified · Normalized (reported) · score · Higher is better

  1. Google: Gemini 2.5 Progoogle0.632
  2. Google: Gemini 2.5 Flashgoogle0.604
  3. OpenAI: GPT-4o (2024-08-06)openai0.332

GPQA · Normalized (reported)

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

  1. DeepSeek: DeepSeek-R1-Distill-Llama-70Bdeepseek0.652
  2. deepseek-ai/DeepSeek-R1-Distill-Qwen-32Bdeepseek0.621
  3. DeepSeek: DeepSeek-R1-Distill-Qwen-14Bdeepseek0.591
  4. DeepSeek: DeepSeek-R1-Distill-Qwen-7Bdeepseek0.491
  5. DeepSeek: DeepSeek-R1-Distill-Llama-8Bdeepseek0.49
  6. 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

  1. nvidia/Llama-3.1-Nemotron-Nano-8B-v1nvidia0.954

HMMT 2025 · Normalized (reported)

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

  1. deepseek-v3.1deepseek0.335

GPQA · Normalized (reported)

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

  1. Qwen: Qwen3 235B A22B Instruct 2507qwen0.775
  2. Qwen: Qwen3 30B A3Bqwen0.658
  3. OpenAI: GPT-4o (2024-05-13)openai0.536
  4. Qwen: Qwen3 235B A22Bqwen0.475
  5. Qwen/Qwen2-72Bqwen0.424
  6. OpenAI: GPT-4o-mini (2024-07-18)openai0.402
  7. Qwen2-7B-Instructqwen0.253

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