← Arena leaderboards

Text · Factuality · Russian

Arena · 50 models

RankModelScore
1Gemini 4 Argon (High)1,523.6362
2Claude Opus 5.5 (High)1,517.5446
3Muse Wonder (Max)1,516.5871
4Claude Fable 5.1 (Max)1,512.939
5Gemini 3.8 Flash (High)1,510.4633
6Claude Fable 5 (High)1,507.1841
7Gemini 3.7 Flash (High)1,504.5026
8Claude Opus 5 (Max)1,503.6818
9Claude Opus 5 (High)1,501.0758
10Gemini 3.5 Flash (High)1,497.6939
11GPT-5.4 (High)1,497.6327
12Claude Opus 4.61,497.1931
13Gemini 3.1 Pro Preview1,496.3917
14Claude Opus 4.6 (High)1,495.8207
15Claude Opus 4.7 (High)1,493.491
16Muse Spark 1.3 (Max)1,493.2127
17GPT-5.51,492.3461
18Gemini 3 Pro1,491.5875
19Claude Opus 4.71,488.8485
20Qwen3.5-Max-Preview1,488.5877
21GPT-5.6 Sol (xHigh)1,488.4116
22Gemini 3.5 Flash (Medium)1,488.0733
23Kimi K3 (Max)1,487.4982
24Gemini 3.6 Flash (High)1,487.4494
25GPT-5.5 (High)1,486.3916
26Claude Opus 4.8 (High)1,484.3223
27Qwen3.8-Max1,483.8809
28GPT-6.1 Sol (Max)1,483.8682
29MiMo-V2.6-Pro1,483.6363
30Gemini 3 Flash1,479.4665
31Muse Spark 1.2 (xHigh)1,479.4404
32Muse Spark 1.11,479.367
33GPT-5.6 Terra (xHigh)1,478.5641
34Claude Sonnet 5.5 (xHigh)1,478.4195
35GLM-5.3 (Max)1,477.5378
36Grok 4.51,476.9601
37GPT-5.41,475.7136
38GPT-6 Astra (Max)1,474.2947
39DeepSeek-V4.1-Flash-20260910 (Max)1,474.0506
40Claude Opus 4.81,473.4921
41GLM-5.3-Flash1,472.5193
42GLM-5.2 (Max)1,471.2587
43Grok 4.20 Beta (Reasoning, 0309)1,468.225
44Gemini 2.5 Pro1,467.6713
45Qwen3.7-Plus1,467.2313
46Gemini 3 Flash (Minimal)1,465.7997
47GPT-5.2 Chat (20260210)1,464.628
48GLM-5V-Turbo1,463.8861
49ERNIE 5.11,463.7436
50Grok 4.20 Multi-Agent Beta (0309)1,462.8851