Skip to content

LLM Benchmark Hub

Model evidence, daily

Models What's New Trends Benchmarks Skill Maps
How It Works Metrics
LLM Benchmark Hub
Loading data...

LiveBench Web Of Lies V2 — leaderboard

Metric: Score. Source: livebench.ai. 65 models tracked.

Top models

#ModelScore
1Claude 3.5 Sonnet (20240620)80
2Llama 3.1 405B Instruct80
3Gemini 1.5 Pro (Preview 0827)80
4Gemini 1.5 Pro (Preview 0801)72
5GPT-4o (2024-05-13)70
6GPT-4 Turbo70
7GPT-4o ChatGPT68
8Gemini 1.5 Flash (Preview 0827)68
9GPT-4o (2024-08-06)66
10Llama 3.1 70B Instruct60
11DeepSeek V2.558
12DeepSeek Coder V256
13Mistral Large 2 (Jul)54
14GPT-4 Preview (0125)52
15Claude 3 Opus (20240229)48

Interactive version: aibenchmarks.dev/benchmark?slug=livebench-web-of-lies-v2 · How the rankings work · Data refreshed daily, snapshot 2026-07-09.