LiveBench

Indexed results from LiveBench. Each ranking retains its own metric and evaluation conditions.

LiveBench Instruction Following

liveBench · LiveBench · Average score · percent

  1. DeepSeek: DeepSeek V3 0324deepseek86.783%
  2. Qwen/Qwen2-72B-Instructqwen85.417%
  3. QwQ-32Bqwen85.3%
  4. OpenAI: o1openai83.15%
  5. OpenAI: o1openai82.9%
  6. OpenAI: o3 Mini (batch)openai82.5%
  7. OpenAI: o1openai80.867%
  8. OpenAI: o3 Mini (batch)openai79.85%
  9. Meta: Llama 4 Maverickmeta-llama79.583%
  10. Perplexity: Sonarperplexity79.311%
  11. OpenAI: o3 Mini (batch)openai78.583%
  12. gpt-4 · azure-openai v1106-Previewopenai77.083%

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