← Arena leaderboards

Text · Longer Query

Arena · 50 models

RankModelScore
1Gemini 4 Carbon (High)1,553.2107
2Gemini 4 Argon (High)1,542.0323
3Claude Opus 5.5 (High)1,533.2487
4Claude Fable 5.1 (Max)1,525.3778
5Claude Opus 4.6 (High)1,517.5332
6Claude Opus 5 (Max)1,517.1511
7Claude Opus 4.61,514.0039
8Claude Opus 5 (High)1,513.7504
9Claude Fable 5 (High)1,510.2438
10Gemini 3.8 Flash (High)1,508.5634
11Claude Opus 4.7 (High)1,505.1676
12MiMo-V2.6-Pro1,501.8905
13Claude Opus 4.71,498.9491
14Muse Wonder (Max)1,495.0651
15Claude Sonnet 5.5 (xHigh)1,494.4467
16Gemini 3.7 Flash (High)1,494.0884
17Kimi K3 (Max)1,493.4844
18Qwen3.8-Max1,488.4744
19Muse Spark 1.3 (Max)1,487.7192
20GPT-5.5 (High)1,484.1936
21Claude Opus 4.8 (High)1,484.0739
22GLM-5.3-Flash1,483.6707
23GLM-5.3 (Max)1,483.4638
24Gemini 3.5 Flash (High)1,482.8104
25GPT-5.51,482.3263
26Gemini 3.1 Pro Preview1,482.0616
27Qwen3.7-Max-Preview1,481.2027
28MiMo-V2.5-Pro1,481.145
29Claude Opus 4.81,480.0681
30GPT-5.6 Sol (xHigh)1,480.0028
31GLM-5.2 (Max)1,479.0028
32Claude Opus 4.5 (20251101)1,478.867
33Claude Sonnet 4.61,478.6767
34Claude Opus 4.5 (High, 32K, 20251101)1,478.2444
35Gemini 3.5 Flash (Medium)1,477.2531
36Qwen3.5-Max-Preview1,476.4131
37Claude Sonnet 4.5 (20250929)1,475.2446
38Claude Sonnet 4.5 (High, 32K, 20250929)1,474.9503
39Gemini 3.6 Flash (High)1,474.7526
40DeepSeek-V4.1-Flash-20260910 (Max)1,473.8548
41Muse Spark 1.2 (xHigh)1,473.7984
42GPT-5.4 (High)1,473.1826
43Gemini 3 Pro1,470.973
44Kimi K2.61,468.293
45GLM-5.11,467.1801
46GPT-5.41,464.0184
47Claude Sonnet 5 (High)1,463.0534
48GPT-6.1 Sol (Max)1,462.9526
49Grok 4.51,461.8697
50ERNIE 5.11,461.7385