LiveBench

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

LiveBench Coding

liveBench · LiveBench · Average score · percent

  1. OpenAI: o3 Mini (batch)openai82.813%
  2. QwQ-32Bqwen75.781%
  3. DeepSeek: DeepSeek V3 0324deepseek71.094%
  4. OpenAI: o3 Mini (batch)openai69.531%
  5. OpenAI: o1openai68.75%
  6. OpenAI: o3 Mini (batch)openai64.844%
  7. DeepSeek: DeepSeek V3deepseek61.719%
  8. Perplexity: Sonar Properplexity60.156%
  9. abacusai/Dracarys2-72B-Instructabacusai57.813%
  10. DeepSeek: DeepSeek-R1-Distill-Llama-70Bdeepseek55.469%
  11. OpenAI: o1openai55.469%
  12. NovaSky-AI/Sky-T1-32B-Previewnovasky-ai54.688%

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%

LiveBench Language

liveBench · LiveBench · Average score · percent

  1. Perplexity: Sonar Properplexity68.73%
  2. OpenAI: o1openai64.755%
  3. OpenAI: o1openai63.539%
  4. OpenAI: o1openai61.134%
  5. OpenAI: GPT-4o (2024-05-13)openai51.205%
  6. gpt-4 · azure-openai v0613openai49.856%
  7. OpenAI: o3 Mini (batch)openai49.459%
  8. OpenAI: GPT-4o (2024-11-20)openai49.019%
  9. DeepSeek: DeepSeek V3 0324deepseek48.688%
  10. gpt-4 · azure-openai v1106-Previewopenai48.576%
  11. QwQ-32Bqwen47.686%
  12. Meta: Llama 4 Maverickmeta-llama47.216%

LiveBench Overall

liveBench · LiveBench · Average score · percent

  1. OpenAI: o1openai67.451%
  2. Perplexity: Sonar Properplexity64.066%
  3. OpenAI: o3 Mini (batch)openai63.625%
  4. OpenAI: o1openai63.55%
  5. OpenAI: o1openai61.372%
  6. QwQ-32Bqwen60.788%
  7. DeepSeek: DeepSeek V3 0324deepseek60.106%
  8. OpenAI: o3 Mini (batch)openai56.669%
  9. DeepSeek: DeepSeek V3deepseek54.668%
  10. OpenAI: GPT-4o (2024-05-13)openai54.359%
  11. Meta: Llama 4 Maverickmeta-llama52.398%
  12. OpenAI: o3 Mini (batch)openai51.906%

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