Benchgen

HellaSwag — Results

RankModelScore
1claude-3-5-sonnet95.4
2claude-3-opus95.4
3gpt-4-061395.3
4gpt-4o95.3
5llama-3-1-70b-instruct93.8
6gemini-1-5-pro92.5
7llama-3-1-405b-instruct92.2
8mimo-v2-5-pro89.8
9claude-3-sonnet89
10command-r-plus88.6
11hermes-3-70b88.2
12qwen2-72b-instruct87.6
13deepseek-v4-1-flash87.2
14gemini-1-5-flash86.5
15gemma-2-27b86.4
16claude-3-haiku85.9
17llama-3-1-nemotron-70b-instruct85.6
18qwen2-5-32b-instruct85.2
19phi-3-5-moe-instruct83.8
20mistral-nemo-instruct83.5
21qwen2-5-coder-32b-instruct83
22gemma-2-9b81.9
23granite-3-3-8b-base80.1
24gemma-3n-e4b-litert-preview78.6
25gemma-3n-e4b78.6
H

HellaSwag — Leaderboard

1 phaseActive

HellaSwag Leaderboard

No self-reported entries.