Skip to main content

AI Leaderboard

Word of Lore leaderboard and ratings are curated based on AI Field Trials between AI technologies that solve real-world problems.

Global Standings

Rank Name Rating RD W L D Pairings
1 DuckDuckGo AI Chat 1678 185 2 2 0 4
2 Perplexity.ai Pro 1673 264 1 0 0 1
3 Claude 3.5 Sonnet 1670 228 1 0 1 2
4 Claude AI 1670 228 1 0 1 2
5 You.com Chat 1670 275 1 0 0 1
6 You.com Smart 1670 275 1 0 0 1
7 Cohere Chat 1662 291 1 0 0 1
8 Command R+ 1662 291 1 0 0 1
9 Mistral Le Chat 1662 291 1 0 0 1
10 Mistral NeMo 1662 291 1 0 0 1
11 QuillBot AI Detector 1662 291 1 0 0 1
12 OpenAI o1 mini 1534 260 1 0 0 1
13 OpenAI o1 1500 275 0 0 1 1
14 Command R 1500 291 0 0 1 1
15 Llama 3 70B 1500 291 0 0 1 1
16 ChatGPT 1493 156 2 3 1 6
17 Claude 3 Haiku 1465 269 0 1 0 1
18 Perplexity.ai Chat 1458 227 1 1 0 2
19 Llama 3.1 70B 1451 235 1 1 0 2
20 GPT-4o 1445 201 1 2 0 3
21 Mixtral 8x7B Instruct 1421 243 1 1 0 2
22 GPT-4o mini 1354 230 1 1 0 2
23 Llama 3 8B 1337 291 0 1 0 1
24 Sapling AI Detector 1337 291 0 1 0 1
25 Gemini Advanced 1329 275 0 1 0 1
26 Gemini Chat 1329 275 0 1 0 1
27 Meta AI 1329 275 0 1 0 1
28 Perplexity.ai Quick Search 1329 275 0 1 0 1

Model Standings

Rank Name Rating RD W L D Pairings
1 Claude 3.5 Sonnet 1670 228 1 0 1 2
2 Command R+ 1662 291 1 0 0 1
3 Mistral NeMo 1662 291 1 0 0 1
4 OpenAI o1 mini 1534 260 1 0 0 1
5 OpenAI o1 1500 275 0 0 1 1
6 Command R 1500 291 0 0 1 1
7 Llama 3 70B 1500 291 0 0 1 1
8 Claude 3 Haiku 1465 269 0 1 0 1
9 Llama 3.1 70B 1451 235 1 1 0 2
10 GPT-4o 1445 201 1 2 0 3
11 Mixtral 8x7B Instruct 1421 243 1 1 0 2
12 GPT-4o mini 1354 230 1 1 0 2
13 Llama 3 8B 1337 291 0 1 0 1

Chat Standings

Rank Name Rating RD W L D Pairings
1 DuckDuckGo AI Chat 1678 185 2 2 0 4
2 Claude AI 1670 228 1 0 1 2
3 You.com Chat 1670 275 1 0 0 1
4 Cohere Chat 1662 291 1 0 0 1
5 Mistral Le Chat 1662 291 1 0 0 1
6 ChatGPT 1493 156 2 3 1 6
7 Perplexity.ai Chat 1458 227 1 1 0 2
8 Gemini Advanced 1329 275 0 1 0 1
9 Gemini Chat 1329 275 0 1 0 1
10 Meta AI 1329 275 0 1 0 1

AI Trial Face-Offs

Workflow Name Opponent Name Outcome Rating Period Trial Code Trial Number
DuckDuckGo AI Chat & GPT-4o mini DuckDuckGo AI Chat & Claude 3 Haiku 1-0 20241031 SUM 6
Mistral Le Chat & NeMo Gemini Advanced 1-0 20240930 SUM 5
QuillBot AI Detector Sapling AI Detector 1-0 20240930 AGT 1
DuckDuckGo AI Chat & Llama 3.1 70B DuckDuckGo AI Chat & Mixtral 8x7B 1-0 20240915 SUM 4
Claude 3.5 Sonnet ChatGPT OpenAI o1 1-1 20240915 JDG 4
ChatGPT GPT-4o ChatGPT OpenAI o1-mini 0-1 20240915 EGW 2
Claude 3.5 Sonnet Llama 3.1 70B 1-0 20240915 EGW 1
ChatGPT GPT-4o Perplexity.ai Pro 0-1 20240830 SUM 3
Mixtral 8x7B Instruct Llama 3 8B Instruct 1-0 20240830 JDG 3
You.com Smart Perplexity.ai Quick Search 1-0 20240812 SUM 2
Cohere Chat Command R+ Gemini Chat 1-0 20240812 SUM 1
Cohere Command R Llama 3 70B 1-1 20240729 JDG 2
ChatGPT GPT-4o ChatGPT GPT-4o mini 1-0 20240729 JDG 1

The ratings are as of October 31, 2024. The current rating period ends on November 30, 2024. For the latest trial results from the current rating period, see AI Field Trial Face-Offs.