← Arena leaderboards

Text · Factuality · Business & Management & Financial Operations

Arena · 50 models

RankModelScore
1Gemini 4 Carbon (High)1,511.1631
2Gemini 4 Argon (High)1,508.8401
3Claude Opus 5.5 (High)1,502.9499
4GPT-5.5 (High)1,499.8
5GPT-5.4 (High)1,499.5758
6Claude Opus 4.6 (High)1,499.4693
7Claude Opus 5 (Max)1,499.058
8Claude Fable 5.1 (Max)1,497.1183
9Muse Wonder (Max)1,495.8207
10GPT-5.51,495.6995
11Claude Opus 4.61,491.7119
12Claude Fable 5 (High)1,491.2462
13Muse Spark 1.3 (Max)1,489.4572
14Muse Spark 1.2 (xHigh)1,488.4941
15Claude Opus 4.7 (High)1,488.1029
16Claude Opus 5 (High)1,488.0218
17GPT-5.41,485.1898
18Claude Opus 4.71,484.346
19Qwen3.8-Max1,483.7255
20Qwen3.5-Max-Preview1,483.6865
21Gemini 3.7 Flash (High)1,483.205
22DeepSeek-V4.1-Flash-20260910 (Max)1,482.6214
23GPT-5.6 Sol (xHigh)1,482.472
24Claude Opus 4.8 (High)1,479.763
25Kimi K3 (Max)1,479.1844
26MiMo-V2.6-Pro1,478.3163
27Gemini 3.5 Flash (High)1,478.2713
28GPT-6.1 Sol (Max)1,475.9976
29Gemini 3.6 Flash (High)1,475.5679
30Claude Sonnet 5.5 (xHigh)1,475.5035
31Gemini 3 Pro1,474.9507
32Gemini 3.8 Flash (High)1,474.5739
33GPT-5.6 Terra (xHigh)1,474.2602
34MiMo-V2.5-Pro1,473.9426
35Claude Opus 4.81,472.863
36Claude Sonnet 4.61,472.5492
37ERNIE 5.11,471.9017
38GLM-5.3 (Max)1,470.4849
39Gemini 3.1 Pro Preview1,469.1909
40Grok 4.51,468.6293
41GPT-5.6 Luna (xHigh)1,468.5404
42Muse Spark1,467.968
43GPT-6 Astra (Max)1,467.8556
44Claude Opus 4.5 (20251101)1,466.7764
45Muse Spark 1.11,466.0457
46GPT-5.1 (High)1,465.0441
47Qwen3.7-Max-Preview1,464.975
48GLM-5.3-Flash1,464.8547
49Gemini 3.5 Flash (Medium)1,464.6109
50GLM-5.11,464.0691