Noometry

Reasoning benchmark

LiveBench Data Analysis leaderboard

As of October 2026, Gemini 2.5 Pro has the highest published LiveBench Data Analysis score on Noometry at 79.9%, out of 39 models with results.

Last verified

About LiveBench Data Analysis

LiveBench table reformatting and data-analysis tasks.

Category
Reasoning
Introduced
2024
Unit
Percent (random guessing ≈ 0%)
Official site
livebench.ai

Top 15 models

  1. Gemini 2.5 Pro 79.9%
  2. Claude 3.7 Sonnet 74%
  3. GPT-5.1 72.1%
  4. o3-mini 70.6%
  5. DeepSeek-R1 69.8%
  6. Gemini 2.0 Flash (Feb 2025) 69.4%
  7. Gemini 2.0 Pro 68%
  8. Qwen2.5-Max 67.9%
  9. o1 65.5%
  10. Gemini 2.0 Flash-Lite 65.5%
  11. QwQ-32B 65%
  12. GPT-4.5 64.3%
  13. DeepSeek-V3 60.9%
  14. GPT-4o 60.9%
  15. o1-mini 57.9%

Sponsored placements are available on pages like this one. Advertise on Noometry

All results

#ModelProviderScoreSettingSourceDate
1Gemini 2.5 Pro Google79.9%Epoch AI
2Claude 3.7 Sonnet Anthropic74%Epoch AI
3GPT-5.1 OpenAI72.1%highEpoch AI
4o3-mini OpenAI70.6%highEpoch AI
5DeepSeek-R1 DeepSeek69.8%Epoch AI
6Gemini 2.0 Flash (Feb 2025) Google69.4%Epoch AI
7Gemini 2.0 Pro Google68%Epoch AI
8Qwen2.5-Max Alibaba (Qwen)67.9%Epoch AI
9o1 OpenAI65.5%highEpoch AI
10Gemini 2.0 Flash-Lite Google65.5%Epoch AI
11QwQ-32B Alibaba (Qwen)65%Epoch AI
12GPT-4.5 OpenAI64.3%Epoch AI
13DeepSeek-V3 DeepSeek60.9%Epoch AI
14GPT-4o OpenAI60.9%Epoch AI
15o1-mini OpenAI57.9%mediumEpoch AI
16Claude 3 Opus Anthropic57.9%Epoch AI
17DeepSeek-R1-Distill-Llama-70B DeepSeek55.9%Epoch AI
18Claude 3.5 Sonnet Anthropic55%Epoch AI
19Grok-2 (Dec 2024) xAI54.5%Epoch AI
20Mistral Small Mistral AI53.7%Epoch AI
21Gemma 3 27B Google51.5%Epoch AI
22Mistral Large Mistral AI50.1%Epoch AI
23GPT-4o mini OpenAI50%Epoch AI
24Qwen2.5-Coder-32B Alibaba (Qwen)49.9%Epoch AI
25Llama-3.3-70B-Instruct Meta49.5%Epoch AI
26Claude 3.5 Haiku Anthropic48.5%Epoch AI
27Amazon Nova Pro Amazon48.3%Epoch AI
28Gemma 2 27B Google47.9%Epoch AI
29DeepSeek-R1-Distill-Qwen-32B DeepSeek45.4%Epoch AI
30Phi-4 Microsoft45.2%Epoch AI
31Command R+ Cohere38.1%Epoch AI
32Sonar Perplexity37.9%Epoch AI
33Amazon Nova Lite Amazon37.2%Epoch AI
34Gemma 2 9B Google36.4%Epoch AI
35Phi 3 Mini 4k Instruct Microsoft34.7%Epoch AI
36Amazon Nova Micro Amazon34%Epoch AI
37Command R Cohere33.3%Epoch AI
38Phi 3 Small 8k Instruct Microsoft30.3%Epoch AI
39OLMo 2 Furious 13B Allen Institute for AI (Ai2)20.6%Epoch AI

Compare the leaders

Other reasoning benchmarks

Frequently asked questions

What does LiveBench Data Analysis measure?

LiveBench table reformatting and data-analysis tasks.

Which model has the highest LiveBench Data Analysis score?

As of October 2026, Gemini 2.5 Pro has the highest published LiveBench Data Analysis score on Noometry at 79.9%, out of 39 models with results.

What is the best open-weight model on LiveBench Data Analysis?

QwQ-32B has the highest LiveBench Data Analysis accuracy among open-weight models at 65%, ranking 11 of 39 overall.