What does Chatbot Arena Elo · Overall measure?

Chatbot Arena Elo · Overall is a knowledge benchmark in the BenchGecko catalog. 146 AI models have been tested on it. Scores range from 953.1 to 1507.6 out of 1600.

Which model leads on Chatbot Arena Elo · Overall?

Claude Fable 5 from Anthropic leads Chatbot Arena Elo · Overall with a score of 1507.6. The median score across 146 tested models is 1387.4.

Is Chatbot Arena Elo · Overall saturated?

No · the top score is 1507.6 out of 1600 (94%). There is still meaningful room for improvement on Chatbot Arena Elo · Overall.

Does Chatbot Arena Elo · Overall predict performance on other benchmarks?

Yes · Chatbot Arena Elo · Overall scores correlate 0.97 with GSM8K across 8 shared models. Models that do well on Chatbot Arena Elo · Overall tend to do well on GSM8K.

How often is Chatbot Arena Elo · Overall data refreshed?

BenchGecko pulls updates daily. New model scores on Chatbot Arena Elo · Overall appear as soon as they are published by Epoch AI or the model provider.

Benchmark · KnowledgeCompetitive

Chatbot Arena Elo · Overall

Name: Chatbot Arena Elo · Overall Benchmark
Creator: BenchGecko
License: https://creativecommons.org/licenses/by/4.0/

Updated 2026-09-21

Models tested

146

Top score

1507.6

Claude Fable 5

Median

1387.4

min 953.1

Top-5 spread

σ 6.6

wide open

The Frontier

Best score over time · one chart, every benchmark

Chart type

Frontier on Chatbot Arena Elo · Overall rose from 1358.4 to 1507.6 in 18 months · +149.1 points · latest leader Claude Fable 5 from Anthropic.

Pink dots = frontier records · 9 totalClick to open model page

Full rankings

146 models tested · sorted by score

#	Model	Score	Price
1	Claude Fable 5· Anthropic	1507.6	$10.00
2	Claude Opus 4.6 (Fast)· Anthropic	1503.7	$30.00
3	Claude Opus 4.6· Anthropic	1497.3	$5.00
4	Claude Opus 4.7· Anthropic	1494.1	$5.00
5	U Muse Spark· Unknown	1489.3	n/a
6	Gemini 3.1 Pro Preview· Google DeepMind	1487.0	$2.00
7	Gemini 3 Pro· Google DeepMind	1485.5	n/a
8	Qwen3.8 Max (0902)· Alibaba Qwen	1481.6	$2.00
9	MiMo-V2.6-Pro· xiaomi	1480.1	$0.43
10	Gemini 3.5 Flash· Google DeepMind	1476.3	$1.50
11	Claude Opus 4.8· Anthropic	1474.5	$5.00
12	GLM 5.3 Flash· z-ai	1473.0	$0.15
13	Gemini 3 Flash Preview· Google DeepMind	1472.7	$0.50
14	Claude Sonnet 4.6· Anthropic	1472.2	$3.00
15	GLM 5.2· z-ai	1471.0	$1.00
16	Claude Opus 4.5· Anthropic	1469.8	$5.00
17	MiMo-V2.5-Pro· xiaomi	1467.5	$0.43
18	Grok 4.5· xAI	1465.8	$2.00
19	GPT-5.4· OpenAI	1464.8	$2.50
20	GLM 5.1· z-ai	1464.6	$0.97
21	Kimi K2.6· moonshotai	1461.0	$0.95
22	Qwen3.6 Max Preview· Alibaba Qwen	1460.3	$1.03
23	DeepSeek V4 Pro· DeepSeek	1457.8	$0.21
24	GLM 5· z-ai	1457.6	$0.60
25	Hy3· tencent	1456.0	$0.13
26	Qwen3.7 Plus· Alibaba Qwen	1455.8	$0.32
27	Gemini 3.5 Flash Lite· Google DeepMind	1455.0	$0.30
28	Gemma 4 31B· Google DeepMind	1452.8	$0.09
29	MiMo-V2.6-Flash· xiaomi	1451.8	$0.14
30	Gemma 4 31B (free)· Google DeepMind	1450.9	$0.00
31	Gemini 2.5 Pro· Google DeepMind	1445.6	$1.25
32	MiMo-V2-Pro· xiaomi	1445.0	$1.00
33	Qwen3.6 Plus· Alibaba Qwen	1443.4	$0.33
34	Qwen3.5 397B A17B· Alibaba Qwen	1441.8	$0.55
35	GLM 4.7· z-ai	1441.5	$0.60
36	Grok 4.3· xAI	1441.4	$1.25
37	MiniMax M3· minimax	1440.1	$0.30
38	GPT-5.1· OpenAI	1438.5	$1.25
39	Gemma 4 26B A4B (free)· Google DeepMind	1438.1	$0.00
40	Qwen3.8 27B· Alibaba Qwen	1437.7	$0.42
41	Gemma 4 26B A4B · Google DeepMind	1437.5	$0.07
42	DeepSeek V4 Flash· DeepSeek	1436.0	$0.03
43	GPT-5.2· OpenAI	1435.6	$1.75
44	MiMo-V2.5· xiaomi	1433.6	$0.14
45	GLM 5V Turbo· z-ai	1433.5	$1.20
46	Gemini 3.1 Flash Lite Preview· Google DeepMind	1432.8	$0.25
47	Mistral Medium 3.5· Mistral AI	1426.9	$1.50
48	GPT-5 Chat· OpenAI	1426.6	$1.25
49	DeepSeek V3.2· DeepSeek	1424.8	$0.28
50	GLM 4.6· z-ai	1424.1	$0.43
51	Qwen3 235B A22B Instruct 2507· Alibaba Qwen	1422.4	$0.09
52	DeepSeek V3.2 Exp· DeepSeek	1422.1	$0.27
53	R1 0528· DeepSeek	1421.6	$0.50
54	DeepSeek V3.1· DeepSeek	1417.2	$0.25
55	Qwen3.5-122B-A10B· Alibaba Qwen	1416.1	$0.26
56	MiniMax M2.7· minimax	1415.0	$0.21
57	DeepSeek V3.1 Terminus· DeepSeek	1414.8	$0.27
58	Qwen3 VL 235B A22B Instruct· Alibaba Qwen	1413.4	$0.21
59	GLM 4.5· z-ai	1411.3	$0.60
60	Gemini 2.5 Flash· Google DeepMind	1409.4	$0.30
61	Qwen3.5-27B· Alibaba Qwen	1408.7	$0.20
62	LongCat Flash Chat· meituan	1401.1	$0.20
63	Qwen3 235B A22B Thinking 2507· Alibaba Qwen	1400.0	$0.23
64	Qwen3 Next 80B A3B Instruct· Alibaba Qwen	1399.0	$0.09
65	R1· DeepSeek	1398.1	$0.70
66	Qwen3.5-Flash· Alibaba Qwen	1395.9	$0.07
67	DeepSeek V3 0324· DeepSeek	1395.6	$0.25
68	Qwen3 VL 235B A22B Thinking· Alibaba Qwen	1395.0	$0.40
69	Qwen3.5-35B-A3B· Alibaba Qwen	1393.8	$0.15
70	Step 3.5 Flash· stepfun	1393.3	$0.10
71	MiMo-V2-Flash· xiaomi	1392.1	$0.09
72	MiniMax M2.5· minimax	1390.8	$0.27
73	o1-preview· OpenAI	1388.5	n/a
74	Solar Pro 4· upstage	1386.2	$0.09
75	Qwen3 30B A3B Instruct 2507· Alibaba Qwen	1382.7	$0.05
76	GLM 4.6V· z-ai	1378.7	$0.30
77	Qwen3 235B A22B· Alibaba Qwen	1375.2	$0.46
78	Trinity Large Preview (free)· arcee-ai	1375.1	$0.00
79	Claude 3.5 Sonnet· Anthropic	1374.0	n/a
80	Qwen2.5-Max· Alibaba Qwen	1373.8	n/a
81	GLM 4.5 Air· z-ai	1373.3	$0.13
82	Qwen3 Next 80B A3B Thinking· Alibaba Qwen	1369.3	$0.15
83	Trinity Large Thinking· arcee-ai	1367.3	$0.25
84	Gemma 3 27B· Google DeepMind	1365.4	$0.08
85	GLM 4.7 Flash· z-ai	1364.9	$0.06
86	MiniMax M1· minimax	1363.9	$0.55
87	o3 Mini High· OpenAI	1363.6	$1.10
88	Gemini 2.0 Flash· Google DeepMind	1360.0	$0.10
89	DeepSeek V3· DeepSeek	1358.4	$0.26
90	Grok 3 Mini Beta· xAI	1357.4	$0.30
91	INTELLECT-3· prime-intellect	1356.5	$0.20
92	GLM 4.5V· z-ai	1352.4	$0.60
93	gpt-oss-120b· OpenAI	1351.6	$0.04
94	o3 Mini· OpenAI	1348.1	$1.10
95	Qwen3 32B· Alibaba Qwen	1346.9	$0.08
96	Llama 3.1 Nemotron Ultra 253B v1· NVIDIA	1346.8	$0.60
97	GPT-4o (2024-05-13)· OpenAI	1346.1	$5.00
98	MiniMax M2· minimax	1343.4	$0.30
99	Mercury 2· inception	1343.3	$0.25
100	Gemma 3 12B· Google DeepMind	1341.8	$0.05
101	Granite 4.2 8B· ibm-granite	1339.5	$0.06
102	o1-mini· OpenAI	1336.8	n/a
103	QwQ 32B· Alibaba Qwen	1335.8	$0.15
104	GPT-4o (2024-08-06)· OpenAI	1335.5	$2.50
105	Nova 2 Lite· Amazon	1335.0	$0.30
106	Olmo 3.1 32B Instruct· allenai	1330.9	$0.20
107	Qwen3 30B A3B· Alibaba Qwen	1326.5	$0.12
108	Gemini 1.5 Pro (Feb 2024)· Google DeepMind	1322.5	n/a
109	Molmo2 8B· allenai	1321.8	n/a
110	Llama 4 Scout 17B 16E Instruct· Meta	1321.6	n/a
111	Gemma 3n 4B· Google DeepMind	1318.2	$0.06
112	Llama 3.3 70B Instruct· Meta	1317.8	$0.10
113	GPT-4o-mini (2024-07-18)· OpenAI	1317.7	$0.15
114	gpt-oss-20b· OpenAI	1317.6	$0.02
115	Mistral Large 2407· Mistral AI	1314.4	$2.00
116	NVIDIA Nemotron 3 Nano 30B A3B BF16· NVIDIA	1313.5	n/a
117	GPT-4 Turbo (older v1106)· OpenAI	1312.0	$10.00
118	Granite 4.1 8B· ibm-granite	1306.8	$0.05
119	Mercury· inception	1306.1	$0.25
120	Olmo 3 32B Think· allenai	1305.4	$0.15
121	Mistral Large 2411· Mistral AI	1304.7	$2.00
122	Gemma 3 4B· Google DeepMind	1303.2	$0.05
123	Qwen2.5 72B Instruct· Alibaba Qwen	1302.8	$0.36
124	Llama 3.1 Nemotron 70B Instruct· NVIDIA	1298.5	$1.20
125	Llama 3.1 70B Instruct· Meta	1293.3	$0.40
126	Gemma 2 27B· Google DeepMind	1289.4	$0.65
127	Gemini 1.5 Flash (May 2024)· Google DeepMind	1286.5	n/a
128	GPT-4 (older v0314)· OpenAI	1285.8	$30.00
129	Olmo 3.1 32B Think· allenai	1285.6	$0.15
130	Command R+ (08-2024)· Cohere	1276.3	$2.50
131	Llama 3 70B Instruct· Meta	1275.1	$0.51
132	Mistral Small 3· Mistral AI	1274.4	$0.05
133	Qwen2.5 Coder 32B Instruct· Alibaba Qwen	1270.6	$0.66
134	Gemma 2 9B· Google DeepMind	1265.0	$0.03
135	Phi 4· Microsoft	1256.3	$0.07
136	Olmo 2 32B Instruct· allenai	1251.2	$0.05
137	Command R (08-2024)· Cohere	1250.4	$0.15
138	Llama 3 8B Instruct· Meta	1222.8	$0.14
139	Llama 3.1 8B Instruct· Meta	1211.2	$0.02
140	Gemma 2 2b It· Google DeepMind	1200.0	n/a
141	Llama 3.2 3B Instruct· Meta	1166.7	$0.05
142	Mistral 7B Instruct V0.2· Mistral AI	1149.3	n/a
143	Phi 3 Mini 4k Instruct· Microsoft	1128.0	n/a
144	Llama 3.2 1B Instruct· Meta	1111.1	$0.03
145	LLaMA-13B· Meta	975.1	n/a
146	U stablelm-tuned-alpha-7b· Unknown	953.1	n/a