模型榜单

这是一个基于 Chatbot Arena (lmarena.ai) 数据的排行榜,通过自动化流程生成。

数据更新时间: 2026-02-22 08:10:11 UTC / 2026-02-22 16:10:11 CST (北京时间)

排行榜

Rank
Rank Spread
模型
分数
票数

1

13

Anthropicclaude-opus-4-6-thinkingAnthropic · Proprietary

1505±8

5,662

2

13

Anthropicclaude-opus-4-6Anthropic · Proprietary

1505±8

6,526

3

13

gemini-3.1-pro-previewGoogle · Proprietary

1500±9Preliminary

4,071

4

46

gemini-3-proGoogle · Proprietary

1486±4

37,394

5

413

gpt-5.2-chat-latest-20260210OpenAI · Proprietary

1478±12

2,333

6

413

Bytedancedola-seed-2.0-previewBytedance · Proprietary

1474±10Preliminary

3,610

7

510

gemini-3-flashGoogle · Proprietary

1474±5

28,220

8

510

grok-4.1-thinkingxAI · Proprietary

1473±4

36,584

9

510

Anthropicclaude-opus-4-5-20251101-thinking-32kAnthropic · Proprietary

1472±4

29,500

10

513

Anthropicclaude-opus-4-5-20251101Anthropic · Proprietary

1467±4

34,478

11

815

grok-4.1xAI · Proprietary

1463±4

40,802

12

818

gemini-3-flash (thinking-minimal)Google · Proprietary

1461±5

19,569

13

1121

gpt-5.1-highOpenAI · Proprietary

1457±4

33,460

14

826

Anthropicclaude-sonnet-4-6Anthropic · Proprietary

1457±10

3,297

15

1128

glm-5Z.ai · MIT

1452±8

5,568

16

1226

ernie-5.0-0110Baidu · Proprietary

1452±6

12,970

17

1228

MoonshotAIkimi-k2.5-thinkingMoonshot · Modified MIT

1450±6

10,160

18

1326

Anthropicclaude-sonnet-4-5-20250929Anthropic · Proprietary

1450±4

45,773

19

1326

Anthropicclaude-sonnet-4-5-20250929-thinking-32kAnthropic · Proprietary

1450±4

48,018

20

1426

gemini-2.5-proGoogle · Proprietary

1449±3

96,652

21

1231

qwen3.5-397b-a17bAlibaba · Apache 2.0

1449±9

3,955

22

1330

ernie-5.0-preview-1203Baidu · Proprietary

1449±7

9,743

23

1427

Anthropicclaude-opus-4-1-20250805-thinking-16kAnthropic · Proprietary

1449±3

49,799

24

1430

Anthropicclaude-opus-4-1-20250805Anthropic · Proprietary

1446±3

77,006

25

1433

gpt-4.5-preview-2025-02-27OpenAI · Proprietary

1444±6

14,549

26

1931

chatgpt-4o-latest-20250326OpenAI · Proprietary

1442±3

83,249

27

1435

glm-4.7Z.ai · MIT

1441±6

11,965

28

2035

gpt-5.2-highOpenAI · Proprietary

1439±5

18,269

29

2236

gpt-5.2OpenAI · Proprietary

1438±6

15,067

30

2436

gpt-5.1OpenAI · Proprietary

1437±4

35,744

31

2242

MoonshotAIkimi-k2.5-instantMoonshot · Modified MIT

1436±8

6,204

32

2639

gpt-5-highOpenAI · Proprietary

1434±5

32,544

33

2640

qwen3-max-previewAlibaba · Proprietary

1434±5

27,758

34

2742

o3-2025-04-16OpenAI · Proprietary

1432±4

61,261

35

2744

grok-4-1-fast-reasoningxAI · Proprietary

1431±4

30,221

36

2948

MoonshotAIkimi-k2-thinking-turboMoonshot · Modified MIT

1429±4

35,284

37

3153

gpt-5-chatOpenAI · Proprietary

1426±4

31,744

38

3355

glm-4.6Z.ai · MIT

1425±4

35,230

39

3156

qwen3-max-2025-09-23Alibaba · Proprietary

1425±6

9,200

40

3555

Anthropicclaude-opus-4-20250514-thinking-16kAnthropic · Proprietary

1424±4

37,919

41

3158

deepseek-v3.2-exp-thinkingDeepSeek · MIT

1423±7

8,979

42

3258

deepseek-v3.2-expDeepSeek · MIT

1423±6

11,720

43

3655

qwen3-235b-a22b-instruct-2507Alibaba · Apache 2.0

1422±3

70,903

44

3360

grok-4-fast-chatxAI · Proprietary

1422±8

6,981

45

3658

deepseek-v3.2-thinkingDeepSeek · MIT

1420±5

24,849

46

3760

deepseek-v3.2DeepSeek · MIT

1419±5

29,862

47

3763

deepseek-r1-0528DeepSeek · MIT

1419±6

19,272

48

3563

ernie-5.0-preview-1022Baidu · Proprietary

1418±9

4,593

49

3763

deepseek-v3.1DeepSeek · MIT

1418±6

15,261

50

3763

MoonshotAIkimi-k2-0905-previewMoonshot · Modified MIT

1417±6

11,954

51

3763

deepseek-v3.1-thinkingDeepSeek · MIT

1417±7

11,959

52

3863

MoonshotAIkimi-k2-0711-previewMoonshot · Modified MIT

1417±5

28,624

53

3667

deepseek-v3.1-terminusDeepSeek · MIT

1416±10

3,756

54

3671

deepseek-v3.1-terminus-thinkingDeepSeek · MIT

1416±10

3,547

55

3866

qwen3-vl-235b-a22b-instructAlibaba · Apache 2.0

1415±6

11,648

56

4163

mistral-large-3Mistral · Apache 2.0

1414±5

26,204

57

4263

gpt-4.1-2025-04-14OpenAI · Proprietary

1413±4

52,106

58

4263

Anthropicclaude-opus-4-20250514Anthropic · Proprietary

1413±4

45,501

59

4567

grok-3-preview-02-24xAI · Proprietary

1411±4

33,960

60

4766

mistral-medium-2508Mistral · Proprietary

1411±3

64,833

61

4766

gemini-2.5-flashGoogle · Proprietary

1411±3

95,946

62

4572

glm-4.5Z.ai · MIT

1410±5

24,745

63

4771

grok-4-0709xAI · Proprietary

1410±4

41,972

64

5677

Anthropicclaude-haiku-4-5-20251001Anthropic · Proprietary

1405±4

46,470

65

5677

gemini-2.5-flash-preview-09-2025Google · Proprietary

1404±4

32,634

66

5677

grok-4-fast-reasoningxAI · Proprietary

1403±5

18,528

67

6179

o1-2024-12-17OpenAI · Proprietary

1402±4

27,822

68

6179

qwen3-235b-a22b-no-thinkingAlibaba · Apache 2.0

1402±4

39,502

69

6180

qwen3-next-80b-a3b-instructAlibaba · Apache 2.0

1401±5

22,787

70

6480

Anthropicclaude-sonnet-4-20250514-thinking-32kAnthropic · Proprietary

1400±4

36,157

71

6185

longcat-flash-chatMeituan · MIT

1400±6

11,524

72

5990

Minimaxminimax-m2.5MiniMax · Modified MIT

1399±9

5,105

73

6488

qwen3-235b-a22b-thinking-2507Alibaba · Apache 2.0

1399±6

9,236

74

6487

deepseek-r1DeepSeek · MIT

1398±5

18,537

75

6493

qwen3-vl-235b-a22b-thinkingAlibaba · Apache 2.0

1395±7

7,958

76

6495

amazon-nova-experimental-chat-12-10Amazon · Proprietary

1394±10

3,705

77

6790

deepseek-v3-0324DeepSeek · MIT

1394±4

46,635

78

6396

Tencenthunyuan-vision-1.5-thinkingTencent · Proprietary

1393±12

2,222

79

6994

mai-1-previewMicrosoft AI · Proprietary

1392±5

18,093

80

7194

o4-mini-2025-04-16OpenAI · Proprietary

1391±4

46,607

81

6795

Stepfunstep-3.5-flashStepFun · Apache 2.0

1391±7

7,717

82

7195

gpt-5-mini-highOpenAI · Proprietary

1390±5

27,065

83

7195

mimo-v2-flash (non-thinking)Xiaomi · MIT

1390±5

18,754

84

7195

Anthropicclaude-sonnet-4-20250514Anthropic · Proprietary

1390±4

41,587

85

7395

Anthropicclaude-3-7-sonnet-20250219-thinking-32kAnthropic · Proprietary

1388±4

39,860

86

7295

o1-previewOpenAI · Proprietary

1388±5

31,120

87

7198

Tencenthunyuan-t1-20250711Tencent · Proprietary

1387±9

4,793

88

7296

mimo-v2-flash (thinking)Xiaomi · MIT

1387±6

10,892

89

7496

qwen3-coder-480b-a35b-instructAlibaba · Apache 2.0

1386±5

26,589

90

7496

Minimaxminimax-m2.1-previewMiniMax · MIT

1385±5

17,138

91

7696

mistral-medium-2505Mistral · Proprietary

1385±5

34,523

92

7798

qwen3-30b-a3b-instruct-2507Alibaba · Apache 2.0

1383±5

24,056

93

7699

Tencenthunyuan-turbos-20250416Tencent · Proprietary

1383±6

11,049

94

7999

gpt-4.1-mini-2025-04-14OpenAI · Proprietary

1382±4

40,484

95

8699

gemini-2.5-flash-lite-preview-09-2025-no-thinkingGoogle · Proprietary

1379±4

47,018

96

76109

glm-4.6vZ.ai · MIT

1378±11

2,790

97

91106

qwen3-235b-a22bAlibaba · Apache 2.0

1375±5

27,142

98

91106

gemini-2.5-flash-lite-preview-06-17-thinkingGoogle · Proprietary

1375±4

33,874

99

93106

qwen2.5-maxAlibaba · Proprietary

1374±4

33,283

100

96106

Anthropicclaude-3-5-sonnet-20241022Anthropic · Proprietary

1373±3

89,445

101

96109

Anthropicclaude-3-7-sonnet-20250219Anthropic · Proprietary

1372±4

44,418

102

96109

glm-4.5-airZ.ai · MIT

1371±4

31,294

103

96112

qwen3-next-80b-a3b-thinkingAlibaba · Apache 2.0

1369±6

13,826

104

96112

Minimaxminimax-m1MiniMax · Apache 2.0

1367±4

36,792

105

100112

gemma-3-27b-itGoogle · Gemma

1365±4

48,652

106

96116

amazon-nova-experimental-chat-11-10Amazon · Proprietary

1365±5

18,388

107

96119

glm-4.7-flashZ.ai · MIT

1365±6

9,653

108

100117

o3-mini-highOpenAI · Proprietary

1364±5

18,584

109

100120

grok-3-mini-highxAI · Proprietary

1363±5

17,505

110

103120

gemini-2.0-flash-001Google · Proprietary

1361±4

44,810

111

103128

deepseek-v3DeepSeek · DeepSeek

1358±5

21,788

112

106130

grok-3-mini-betaxAI · Proprietary

1357±5

23,744

113

106133

mistral-small-2506Mistral · Apache 2.0

1356±5

18,326

114

103135

intellect-3Prime Intellect · MIT

1356±8

5,306

115

108133

gpt-oss-120bOpenAI · Apache 2.0

1354±4

30,893

116

109135

gemini-2.0-flash-lite-preview-02-05Google · Proprietary

1353±4

24,951

117

106136

glm-4.5vZ.ai · MIT

1353±8

4,970

118

111134

Coherecommand-a-03-2025Cohere · CC-BY-NC-4.0

1353±3

57,357

119

111135

gemini-1.5-pro-002Google · Proprietary

1351±3

55,607

120

111137

amazon-nova-experimental-chat-10-20Amazon · Proprietary

1350±6

11,367

121

106147

Tencenthunyuan-turbos-20250226Tencent · Proprietary

1349±12

2,226

122

112136

o3-miniOpenAI · Proprietary

1348±3

58,608

123

108147

amazon-nova-experimental-chat-10-09Amazon · Proprietary

1348±11

2,886

124

107149

Nvidiallama-3.1-nemotron-ultra-253b-v1Nvidia · Nvidia Open Model

1347±12

2,546

125

111142

Minimaxminimax-m2MiniMax · Apache 2.0

1347±8

6,710

126

111142

ling-flash-2.0Ant Group · MIT

1347±7

7,030

127

111146

qwen3-32bAlibaba · Apache 2.0

1347±9

3,932

128

111144

Stepfunstep-3StepFun · Apache 2.0

1346±7

6,586

129

111146

qwen-plus-0125Alibaba · Proprietary

1346±8

5,823

130

116139

gpt-4o-2024-05-13OpenAI · Proprietary

1346±3

112,863

131

113149

glm-4-plus-0111Zhipu · Proprietary

1343±8

5,760

132

119142

Anthropicclaude-3-5-sonnet-20240620Anthropic · Proprietary

1343±3

82,417

133

113151

gemma-3-12b-itGoogle · Gemma

1342±10

3,829

134

113153

Nvidianvidia-llama-3.3-nemotron-super-49b-v1.5Nvidia · Nvidia Open

1341±10

3,426

135

112154

Tencenthunyuan-turbo-0110Tencent · Proprietary

1340±12

2,295

136

121153

gpt-5-nano-highOpenAI · Proprietary

1338±7

8,383

137

122153

nova-2-liteAmazon · Proprietary

1337±6

12,134

138

123150

o1-miniOpenAI · Proprietary

1337±4

51,986

139

123153

qwq-32bAlibaba · Apache 2.0

1336±4

26,093

140

127152

Metallama-3.1-405b-instruct-bf16Meta · Llama 3.1 Community

1335±4

41,392

141

127153

grok-2-2024-08-13xAI · Proprietary

1335±4

63,495

142

125153

gpt-4o-2024-08-06OpenAI · Proprietary

1335±4

45,498

143

123153

gemini-advanced-0514Google · Proprietary

1335±5

50,142

144

122160

Stepfunstep-2-16k-exp-202412StepFun · Proprietary

1334±9

4,829

145

129153

Metallama-3.1-405b-instruct-fp8Meta · Llama 3.1 Community

1334±4

59,655

146

131161

olmo-3.1-32b-instructAllen AI · Apache 2.0

1331±6

12,282

147

133165

01.AIyi-lightning01 AI · Proprietary

1329±5

27,340

148

115184

molmo-2-8bAI2 · Apache 2.0

1328±21

821

149

134166

qwen3-30b-a3bAlibaba · Apache 2.0

1328±5

27,408

150

135166

Metallama-4-maverick-17b-128e-instructMeta · Llama 4

1328±4

41,095

151

126175

Nvidiallama-3.3-nemotron-49b-super-v1Nvidia · Nvidia

1327±12

2,230

152

131175

Tencenthunyuan-large-2025-02-10Tencent · Proprietary

1326±10

3,738

153

145171

gpt-4-turbo-2024-04-09OpenAI · Proprietary

1324±4

98,130

154

145171

Anthropicclaude-3-5-haiku-20241022Anthropic · Proprietary

1324±3

71,150

155

136175

deepseek-v2.5-1210DeepSeek · DeepSeek

1323±8

6,793

156

145171

gemini-1.5-pro-001Google · Proprietary

1323±4

79,132

157

145173

Metallama-4-scout-17b-16e-instructMeta · Llama

1323±5

31,202

158

146171

Anthropicclaude-3-opus-20240229Anthropic · Proprietary

1322±3

194,904

159

144176

gpt-4.1-nano-2025-04-14OpenAI · Proprietary

1322±8

6,107

160

145175

Stepfunstep-1o-turbo-202506StepFun · Proprietary

1322±7

9,682

161

145177

ring-flash-2.0Ant Group · MIT

1320±7

7,190

162

150175

Metallama-3.3-70b-instructMeta · Llama-3.3

1319±3

55,552

163

147175

glm-4-plusZhipu AI · Proprietary

1319±5

26,134

164

147176

gemma-3n-e4b-itGoogle · Gemma

1319±5

23,320

165

147178

qwen-max-0919Alibaba · Qwen

1318±6

16,479

166

150175

gpt-4o-mini-2024-07-18OpenAI · Proprietary

1318±3

68,800

167

148182

gpt-oss-20bOpenAI · Apache 2.0

1317±6

10,791

168

150181

Nvidianvidia-nemotron-3-nano-30b-a3b-bf16Nvidia · NVIDIA Open Model

1317±6

15,442

169

150184

qwen2.5-plus-1127Alibaba · Proprietary

1315±6

10,179

170

154182

athene-v2-chatNexusFlow · NexusFlow

1314±5

24,746

171

154182

mistral-large-2407Mistral · Mistral Research

1314±4

45,460

172

155183

gpt-4-0125-previewOpenAI · Proprietary

1313±4

93,439

173

155183

gpt-4-1106-previewOpenAI · Proprietary

1313±4

100,107

174

150187

Tencenthunyuan-standard-2025-02-10Tencent · Proprietary

1312±10

3,905

175

162186

gemini-1.5-flash-002Google · Proprietary

1310±4

34,909

176

147192

mercuryInception AI · Proprietary

1310±14

1,896

177

166187

grok-2-mini-2024-08-13xAI · Proprietary

1308±4

52,574

178

166187

deepseek-v2.5DeepSeek · DeepSeek

1307±5

24,574

179

166187

athene-70b-0725NexusFlow · CC-BY-NC-4.0

1306±6

19,622

180

164187

olmo-3-32b-thinkAllen AI · Apache 2.0

1305±8

5,878

181

170187

mistral-large-2411Mistral · MRL

1305±4

28,081

182

167187

magistral-medium-2506Mistral · Proprietary

1305±6

12,056

183

172187

mistral-small-3.1-24b-instruct-2503Mistral · Apache 2.0

1305±4

34,078

184

165194

gemma-3-4b-itGoogle · Gemma

1303±9

4,177

185

174187

qwen2.5-72b-instructAlibaba · Qwen

1303±4

39,409

186

174197

Nvidiallama-3.1-nemotron-70b-instructNvidia · Llama 3.1

1299±8

7,136

187

175198

Tencenthunyuan-large-visionTencent · Proprietary

1296±9

5,597

188

183198

Metallama-3.1-70b-instructMeta · Llama 3.1 Community

1294±4

55,234

189

185199

amazon-nova-pro-v1.0Amazon · Proprietary

1290±5

24,753

190

184202

jamba-1.5-largeAI21 Labs · Jamba Open

1289±7

8,659

191

184204

ibm-granite-h-smallIBM · Apache 2.0

1288±8

5,657

192

186200

gemma-2-27b-itGoogle · Gemma license

1288±3

75,764

193

185202

reka-core-20240904Reka AI · Proprietary

1288±7

7,309

194

186202

gpt-4-0314OpenAI · Proprietary

1287±5

54,167

195

184208

llama-3.1-tulu-3-70bAi2 · Llama 3.1

1287±10

2,846

196

184208

Nvidiallama-3.1-nemotron-51b-instructNvidia · Llama 3.1

1286±10

3,749

197

187202

gemini-1.5-flash-001Google · Proprietary

1286±4

62,823

198

186208

olmo-3.1-32b-thinkAllen AI · Apache 2.0

1285±7

8,455

199

190208

Anthropicclaude-3-sonnet-20240229Anthropic · Proprietary

1281±4

109,289

200

189208

gemma-2-9b-it-simpoPrinceton · MIT

1279±7

10,069

201

191208

Nvidianemotron-4-340b-instructNvidia · NVIDIA Open Model

1278±5

19,661

202

191210

Coherecommand-r-plus-08-2024Cohere · CC-BY-NC-4.0

1277±7

9,869

203

196208

Metallama-3-70b-instructMeta · Llama 3 Community

1276±4

156,880

204

196209

gpt-4-0613OpenAI · Proprietary

1275±4

88,721

205

195211

mistral-small-24b-instruct-2501Mistral · Apache 2.0

1274±6

14,677

206

195212

glm-4-0520Zhipu AI · Proprietary

1273±7

9,788

207

196214

reka-flash-20240904Reka AI · Proprietary

1272±7

7,537

208

196217

qwen2.5-coder-32b-instructAlibaba · Apache 2.0

1271±8

5,430

209

203217

Coherec4ai-aya-expanse-32bCohere · CC-BY-NC-4.0

1267±5

27,123

210

205217

gemma-2-9b-itGoogle · Gemma license

1266±4

54,615

211

204218

deepseek-coder-v2DeepSeek · DeepSeek License

1264±6

15,147

212

207218

Coherecommand-r-plusCohere · CC-BY-NC-4.0

1262±4

77,556

213

206218

qwen2-72b-instructAlibaba · Qianwen LICENSE

1262±5

37,325

214

208218

Anthropicclaude-3-haiku-20240307Anthropic · Proprietary

1261±4

117,705

215

207219

amazon-nova-lite-v1.0Amazon · Proprietary

1261±5

19,376

216

208219

gemini-1.5-flash-8b-001Google · Proprietary

1259±4

35,556

217

211219

Azurephi-4Microsoft · MIT

1256±5

24,126

218

208225

olmo-2-0325-32b-instructAllen AI · Apache-2.0

1252±11

3,335

219

215224

Coherecommand-r-08-2024Cohere · CC-BY-NC-4.0

1250±7

10,141

220

218228

mistral-large-2402Mistral · Proprietary

1243±5

62,437

221

218228

amazon-nova-micro-v1.0Amazon · Proprietary

1241±5

19,355

222

218232

jamba-1.5-miniAI21 Labs · Jamba Open

1239±7

8,854

223

218236

ministral-8b-2410Mistral · MRL

1237±9

4,780

224

219236

gemini-pro-dev-apiGoogle · Proprietary

1235±7

18,352

225

220236

qwen1.5-110b-chatAlibaba · Qianwen LICENSE

1234±6

26,191

226

220237

reka-flash-21b-20240226-onlineReka AI · Proprietary

1233±7

15,451

227

218238

Tencenthunyuan-standard-256kTencent · Proprietary

1233±12

2,729

228

220236

qwen1.5-72b-chatAlibaba · Qianwen LICENSE

1233±5

39,296

229

222237

mixtral-8x22b-instruct-v0.1Mistral · Apache 2.0

1230±5

51,417

230

222238

Coherecommand-rCohere · CC-BY-NC-4.0

1227±5

54,038

231

222238

reka-flash-21b-20240226Reka AI · Proprietary

1227±6

24,806

232

223239

gpt-3.5-turbo-0125OpenAI · Proprietary

1224±5

66,191

233

227239

Metallama-3-8b-instructMeta · Llama 3 Community

1223±4

104,636

234

223240

mistral-mediumMistral · Proprietary

1223±6

34,552

235

223240

Coherec4ai-aya-expanse-8bCohere · CC-BY-NC-4.0

1223±7

9,827

236

222243

gemini-proGoogle · Proprietary

1222±12

6,390

237

223243

llama-3.1-tulu-3-8bAi2 · Llama 3.1

1221±11

2,895

238

234243

01.AIyi-1.5-34b-chat01 AI · Apache-2.0

1213±5

24,142

239

229245

HuggingFacezephyr-orpo-141b-A35b-v0.1HuggingFace · Apache 2.0

1213±11

4,653

240

236243

Metallama-3.1-8b-instructMeta · Llama 3.1 Community

1212±4

49,605

241

232249

granite-3.1-8b-instructIBM · Apache 2.0

1209±11

3,092

242

236249

qwen1.5-32b-chatAlibaba · Qianwen LICENSE

1204±6

21,744

243

236251

gpt-3.5-turbo-1106OpenAI · Proprietary

1203±9

16,616

244

240250

gemma-2-2b-itGoogle · Gemma license

1199±4

46,618

245

240251

Azurephi-3-medium-4k-instructMicrosoft · MIT

1198±5

25,055

246

241251

mixtral-8x7b-instruct-v0.1Mistral · Apache 2.0

1197±4

73,505

247

241256

dbrx-instruct-previewDatabricks · DBRX LICENSE

1195±6

32,196

248

241260

InternLMinternlm2_5-20b-chatInternLM · Other

1191±7

9,902

249

241260

qwen1.5-14b-chatAlibaba · Qianwen LICENSE

1191±7

17,841

250

244266

Azurewizardlm-70bMicrosoft · Llama 2 Community

1185±9

8,214

251

243267

deepseek-llm-67b-chatDeepSeek · DeepSeek License

1185±12

4,933

252

247263

01.AIyi-34b-chat01 AI · Yi License

1184±7

15,483

253

247266

OpenChatopenchat-3.5-0106OpenChat · Apache-2.0

1182±8

12,636

254

247267

OpenChatopenchat-3.5OpenChat · Apache-2.0

1182±10

7,967

255

247267

granite-3.0-8b-instructIBM · Apache 2.0

1182±9

6,643

256

248267

gemma-1.1-7b-itGoogle · Gemma license

1180±6

23,893

257

248267

Snowflakesnowflake-arctic-instructSnowflake · Apache 2.0

1180±6

32,836

258

247268

granite-3.1-2b-instructIBM · Apache 2.0

1179±11

3,191

259

248268

tulu-2-dpo-70bAllenAI/UW · AI2 ImpACT Low-risk

1178±10

6,534

260

248271

openhermes-2.5-mistral-7bNousResearch · Apache-2.0

1175±10

5,006

261

250270

vicuna-33bLMSYS · Non-commercial

1173±6

22,479

262

250272

starling-lm-7b-betaNexusflow · Apache-2.0

1172±7

16,057

263

250271

Azurephi-3-small-8k-instructMicrosoft · MIT

1171±6

17,763

264

251271

Metallama-2-70b-chatMeta · Llama 2 Community

1171±6

38,491

265

251274

starling-lm-7b-alphaUC Berkeley · CC-BY-NC-4.0

1168±8

10,224

266

253274

Metallama-3.2-3b-instructMeta · Llama 3.2

1167±8

7,936

267

251277

nous-hermes-2-mixtral-8x7b-dpoNousResearch · Apache-2.0

1165±12

3,776

268

258283

qwq-32b-previewAlibaba · Apache 2.0

1157±12

3,233

269

264281

granite-3.0-2b-instructIBM · Apache 2.0

1156±8

6,837

270

260284

Nvidiallama2-70b-steerlm-chatNvidia · Llama 2 Community

1155±13

3,584

271

261287

solar-10.7b-instruct-v1.0Upstage AI · CC-BY-NC-4.0

1153±13

4,155

272

260289

dolphin-2.2.1-mistral-7bCognitive Computations · Apache-2.0

1152±15

1,679

273

265287

mpt-30b-chatMosaicML · CC-BY-NC-SA-4.0

1150±12

2,571

274

267284

mistral-7b-instruct-v0.2Mistral · Apache-2.0

1150±7

19,402

275

267286

Azurewizardlm-13bMicrosoft · Llama 2 Community

1149±9

7,046

276

265291

falcon-180b-chatTII · Falcon-180B TII License

1147±17

1,295

277

267290

qwen1.5-7b-chatAlibaba · Qianwen LICENSE

1144±10

4,735

278

268289

Azurephi-3-mini-4k-instruct-june-2024Microsoft · MIT

1143±6

12,296

279

268290

Metallama-2-13b-chatMeta · Llama 2 Community

1142±7

19,171

280

268290

vicuna-13bLMSYS · Llama 2 Community

1141±7

19,366

281

268292

qwen-14b-chatAlibaba · Qianwen LICENSE

1139±11

4,964

282

269292

palm-2Google · Proprietary

1137±9

8,554

283

269292

Metacodellama-34b-instructMeta · Llama 2 Community

1137±9

7,363

284

270292

gemma-7b-itGoogle · Gemma license

1136±10

8,925

285

272293

HuggingFacezephyr-7b-betaHuggingFace · MIT

1131±9

11,116

286

275294

Azurephi-3-mini-128k-instructMicrosoft · MIT

1129±7

20,691

287

277293

Azurephi-3-mini-4k-instructMicrosoft · MIT

1129±6

20,115

288

273297

guanaco-33bUW · Non-commercial

1127±12

2,921

289

272297

HuggingFacezephyr-7b-alphaHuggingFace · MIT

1127±16

1,785

290

280297

stripedhyena-nous-7bTogether AI · Apache 2.0

1121±11

5,184

291

275298

Metacodellama-70b-instructMeta · Llama 2 Community

1119±18

1,143

292

285297

vicuna-7bLMSYS · Llama 2 Community

1115±9

6,923

293

281298

HuggingFacesmollm2-1.7b-instructHuggingFace · Apache 2.0

1114±14

2,201

294

287297

gemma-1.1-2b-itGoogle · Gemma license

1114±8

10,853

295

288297

Metallama-3.2-1b-instructMeta · Llama 3.2

1111±8

8,045

296

288298

mistral-7b-instructMistral · Apache 2.0

1110±9

8,977

297

288298

Metallama-2-7b-chatMeta · Llama 2 Community

1108±7

14,148

298

294302

gemma-2b-itGoogle · Gemma license

1092±12

4,779

299

298301

qwen1.5-4b-chatAlibaba · Qianwen LICENSE

1090±9

7,598

300

298305

olmo-7b-instructAllen AI · Apache-2.0

1075±11

6,329

301

299305

koala-13bUC Berkeley · Non-commercial

1071±10

6,964

302

300305

alpaca-13bStanford · Non-commercial

1067±12

5,745

303

298306

gpt4all-13b-snoozyNomic AI · Non-commercial

1066±15

1,743

304

300306

mpt-7b-chatMosaicML · CC-BY-NC-SA-4.0

1062±12

3,925

305

300306

chatglm3-6bTsinghua · Apache-2.0

1056±12

4,658

306

303308

RWKVRWKV-4-Raven-14BRWKV · Apache 2.0

1041±11

4,845

307

306308

chatglm2-6bTsinghua · Apache-2.0

1024±14

2,657

308

306308

oasst-pythia-12bOpenAssistant · Apache 2.0

1022±11

6,311

309

309312

chatglm-6bTsinghua · Non-commercial

996±13

4,914

310

309312

fastchat-t5-3bLMSYS · Apache 2.0

991±12

4,203

311

309312

dolly-v2-12bDatabricks · MIT

980±14

3,412

312

309313

Metallama-13bMeta · Non-commercial

972±16

2,391

313

312313

Stabilitystablelm-tuned-alpha-7bStability AI · CC-BY-NC-SA-4.0

953±13

3,287

说明

  • 排名 (UB):基于 Bradley-Terry 模型计算的排名。此排名反映了模型在竞技场中的综合表现,并提供了其 Elo 分数的 上界 估计,帮助理解模型的潜在竞争力。

  • 模型:大型语言模型 (LLM) 的名称。部分模型名称可能已嵌入相关链接。

  • 分数:模型在竞技场中通过用户投票获得的 Elo 评分。Elo 评分是一种相对排名系统,分数越高表示模型表现越好。

  • 95% 置信区间 (±):模型 Elo 评分的95%置信区间(例如:±6)。这个区间越小,表示模型的评分越稳定和可靠。

  • 票数:该模型在竞技场中收到的总投票数量。投票数越多,通常意味着其评分的统计可靠性越高。

  • 组织/公司:提供该模型的组织或公司。

  • 许可证:模型的许可协议类型,例如专有 (Proprietary)、Apache 2.0、MIT 等。

数据来源与更新频率

本排行榜数据由自动化脚本直接从 1 2arrow-up-right 官方网站获取。此排行榜由 GitHub Actions 每天自动更新。

免责声明

本报告仅供参考。排行榜数据是动态变化的,并基于特定时间段内用户在 Chatbot Arena 上的偏好投票。数据的完整性和准确性取决于上游数据源。不同模型可能采用不同的许可协议,使用时请务必参考模型提供商的官方说明。

最后更新于

这有帮助吗?