AI Flash Report

Chatbot Arena Elo leaderboard

52 models ranked, highest score first.

Chatbot Arena Elo leaderboard — 52 models ranked by score
# Model Company Score
1 Qwen3.7 Max Alibaba 1537
2 Claude Opus 4.7 Anthropic 1493
3 Muse Spark Meta 1489
4 Gemini 3.1 Pro Preview Google 1488
5 Claude Opus 4.8 Anthropic 1479
6 Gemini 3.5 Flash Google 1477
7 GLM-5.1 Z AI 1475
8 GPT-5.5 Instant OpenAI 1472
9 GPT-5.5 OpenAI 1472
10 Claude Sonnet 4.6 Anthropic 1470
11 Claude Opus 4.5 Anthropic 1469
12 GPT-5.4 OpenAI 1466
13 MiMo-V2.5-Pro Xiaomi 1465
14 Kimi K2.6 Kimi 1461
15 Qwen3.6 Max Preview Alibaba 1460
16 DeepSeek V4 Pro DeepSeek 1457
17 Gemma 4 31B Google 1451
18 MiniMax-M3 MiniMax 1450
19 MiMo-V2-Pro Xiaomi 1449
20 GPT-5.4 mini OpenAI 1449
21 Grok 4.3 xAI 1446
22 Qwen3.6 Plus Alibaba 1444
23 Qwen3.5 397B A17B Alibaba 1444
24 GPT-5.1 OpenAI 1439
25 Gemma 4 26B A4B Google 1438
26 GPT-5.2 OpenAI 1435
27 DeepSeek V4 Flash DeepSeek 1434
28 GPT-5 OpenAI 1434
29 Gemini 3.1 Flash-Lite Preview Google 1433
30 MiMo-V2.5 Xiaomi 1432
31 MiMo-V2-Omni Xiaomi 1427
32 Mistral Medium 3.5 Mistral 1425
33 DeepSeek V3.2 DeepSeek 1425
34 Qwen3.5 122B A10B Alibaba 1417
35 MiniMax-M2.7 MiniMax 1415
36 Mistral Large 3 Mistral 1415
37 Gemini 2.5 Flash Google 1411
38 Qwen3.5 27B Alibaba 1409
39 GPT-5.3 Codex OpenAI 1407
40 GPT-5.4 nano OpenAI 1402
41 Qwen3.5 35B A3B Alibaba 1396
42 Step 3.5 Flash 2603 StepFun 1395
43 Claude 3.5 Sonnet Anthropic 1372
44 Trinity Large Thinking Arcee AI 1370
45 NVIDIA Nemotron 3 Super 120B A12B NVIDIA 1361
46 DeepSeek-V3 DeepSeek 1358
47 Mercury 2 Inception 1346
48 GLM 5V Turbo Z AI 1231
49 Granite 4.1 8B IBM 1201
50 Claude 3 Opus Anthropic 1062
51 Claude 3 Sonnet Anthropic 1016
52 Claude 3 Haiku Anthropic 1000