dewin summer
@dewin
Artificial Analysis has collected the top 100 LLMs in one table so that you can conveniently choose the one for your tasks.
Select by parameters:
- Benchmarks: Chatbot Arena, MMLU, HumanEval, Index of evals, MT-Bench.
- Cost: entry, exit, average
- Speed in tokens/sec: median, P5, P25, P75, P95 (those who understand, understand).
- Delay: median, P5, P25, P75, P95.
- Size of the context window.
- Compatible with OpenAI library.
Top 1 from each category:
- Benchmarks: Claude 3 Opus, GPT-4 Turbo
- Cost: $0.06/1M Llama 3 (8B) tokens via groq API
- Speed: 912.9 tokens/sec Llama 3 (8B) via groq API
- Latency: 0.13s Mistral 7B via baseten API
- Context window size: 1m Gemini 1.5 Pro
They did it beautifully. 0 reply
1 recast
1 reaction
Artificial Analysis has collected the top 100 LLMs in one table so that you can conveniently choose the one for your tasks.
Select by parameters:
- Benchmarks: Chatbot Arena, MMLU, HumanEval, Index of evals, MT-Bench.
- Cost: entry, exit, average
- Speed in tokens/sec: median, P5, P25, P75, P95 (those who understand, understand).
- Delay: median, P5, P25, P75, P95.
- Size of the context window.
- Compatible with OpenAI library.
Top 1 from each category:
- Benchmarks: Claude 3 Opus, GPT-4 Turbo
- Cost: $0.06/1M Llama 3 (8B) tokens via groq API
- Speed: 912.9 tokens/sec Llama 3 (8B) via groq API
- Latency: 0.13s Mistral 7B via baseten API
- Context window size: 1m Gemini 1.5 Pro
They did it beautifully. 0 reply
1 recast
1 reaction
3 replies
1 recast
11 reactions
0 reply
0 recast
0 reaction
0 reply
0 recast
0 reaction
0 reply
1 recast
1 reaction
0 reply
1 recast
1 reaction
0 reply
1 recast
1 reaction
0 reply
1 recast
1 reaction
0 reply
1 recast
1 reaction
0 reply
1 recast
1 reaction
0 reply
1 recast
1 reaction
0 reply
1 recast
1 reaction
1 reply
1 recast
9 reactions
0 reply
0 recast
0 reaction
0 reply
1 recast
10 reactions
0 reply
0 recast
0 reaction
1 reply
2 recasts
9 reactions
0 reply
1 recast
3 reactions
0 reply
1 recast
3 reactions
