Open Prompt Leaderboard
Updated 7 minutes agoVotes power leaderboards.
Top Model Scores
ELO ratings for the highest performing models
Loading chart...
Performance vs Accuracy
ELO score vs average latency • Better models are top-left
Loading chart...
1 | Gemini 2.5 Flash | 1235 | +12 | 3.33 s | |
2 | Claude 3 Opus | 1235 | +11 | 5.81 s | Anthropic |
3 | Gemini 1.5 Pro | 1224 | +12 | 8.28 s | |
4 | Gemini 1.5 Flash | 1224 | +12 | 2.51 s | |
5 | Llama 4 Maverick | 1212 | +12 | 1.95 s | Meta |
6 | Llama 3.2 Vision 11b | 1212 | +12 | 5.31 s | Meta |
6 | GPT-4.1 mini | 1212 | +12 | 1.66 s | OpenAI |
7 | GPT-5 | 1212 | +12 | 17.22 s | OpenAI |
8 | Llama 4 Scout | 1211 | -1 | 2.38 s | Meta |
9 | Gemini 2.5 Pro | 1211 | -12 | 16.62 s | |
10 | Gemini 2.0 Flash Exp | 1201 | +13 | 4.25 s | |
11 | Mistral Medium 3.1 | 1200 | -12 | 2.37 s | Mistral |
12 | GPT-5 Mini | 1200 | +12 | 16.98 s | OpenAI |
13 | Gemma 3 4B | 1200 | +12 | 11.90 s | |
14 | Claude 4 Sonnet | 1200 | 0 | 11.22 s | Anthropic |
14 | Gemma 3 27B | 1200 | 0 | 2.99 s | |
14 | GPT-4.1 nano | 1200 | 0 | 3.17 s | OpenAI |
14 | GPT-4o | 1200 | 0 | 3.92 s | OpenAI |
14 | Claude 3.7 Sonnet | 1200 | 0 | 5.38 s | Anthropic |
15 | Grok 4 | 1200 | 0 | 8.81 s | xAI |
16 | Claude 4 Opus | 1200 | 0 | 14.36 s | Anthropic |
17 | Mistral Small 3.1 24B | 1199 | -13 | 3.65 s | Mistral |
18 | Claude 3.5 Haiku | 1190 | +0 | 4.15 s | Anthropic |
19 | Qwen2.5-VL-7B-Instruct | 1189 | +1 | 3.14 s | Qwen |
20 | kimi-vl-a3b-thinking | 1188 | -12 | 2.69 s | Unknown org |
20 | GPT-4o mini | 1188 | -12 | 1.93 s | OpenAI |
20 | Grok 2 Vision 1212 | 1188 | -12 | 1.48 s | xAI |
20 | Claude 3.5 Sonnet | 1188 | -12 | 3.74 s | Anthropic |
20 | Qwen VL Max | 1188 | -12 | 6.83 s | Qwen |
21 | GPT-4.1 | 1187 | -13 | 5.84 s | OpenAI |
22 | GPT-5 Nano | 1178 | -11 | 20.51 s | OpenAI |
23 | Gemma 3 12B | 1176 | -12 | 3.56 s | |
24 | Claude 3 Haiku | 1176 | -12 | 1.72 s | Anthropic |
25 | Pixtral 12B | 1176 | -12 | 4.55 s | Mistral |