Atlas

Benchmarks

← All benchmarks

LiveBench Data Analysis Average

Professional Work · 2024-06-12

LiveBench leaderboard aggregate for livebench data analysis average. LiveBench is refreshed over time to reduce contamination and covers reasoning, coding, mathematics, language, data analysis, instruction following, and agentic coding.

Top models (higher is better)

ModelScore
GPT-5.581.6
GPT-5.479.3
Claude Fable 578.7
Gemini 3.1 Pro Preview78.5
Opus 4.878.3
Opus 4.778.3
GPT-5.2-Codex78.2
GPT-5.278.2
Sonnet 4.678.0
MiniMax M376.2
DeepSeek-V4-Pro74.5
Opus 4.574.4
GLM-5.273.7
Qwen3.7-Max71.8
Sonnet 571.7
GPT-5.4 Mini70.8
Grok Build 0.170.8
Qwen3.6 27B70.4
Qwen3.6 Plus (2026-04-02)69.9
Opus 4.669.9
DeepSeek-V4-Flash68.0
GPT-5.4 Nano67.6
Kimi K2.665.1
Gemini 3.5 Flash64.9
Kimi K2.7 Code62.7
Grok 4.355.8
Loading Atlas data…