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: 2026-02-20 08:16:35 UTC / 2026-02-20 16:16:35 CST (北京时间)

排行榜

Rank
Rank Spread
模型
分数
票数

1

13

Anthropicclaude-opus-4-6Anthropic · Proprietary

1505±8

6,176

2

13

Anthropicclaude-opus-4-6-thinkingAnthropic · Proprietary

1504±8

5,321

3

13

gemini-3.1-pro-previewGoogle · Proprietary

1500±9Preliminary

4,072

4

45

gemini-3-proGoogle · Proprietary

1486±4

37,053

5

411

Bytedancedola-seed-2.0-previewBytedance · Proprietary

1475±10Preliminary

3,379

6

59

grok-4.1-thinkingxAI · Proprietary

1474±4

36,224

7

59

gemini-3-flashGoogle · Proprietary

1474±5

27,834

8

59

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

1471±4

29,153

9

511

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

1467±4

34,076

10

815

grok-4.1xAI · Proprietary

1463±4

40,418

11

815

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

1462±5

19,198

12

1019

gpt-5.1-highOpenAI · Proprietary

1457±4

33,069

13

1024

glm-5Z.ai · MIT

1455±8

5,301

14

1024

ernie-5.0-0110Baidu · Proprietary

1453±6

12,680

15

1224

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

1450±4

45,379

16

1224

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

1450±4

47,618

17

1324

gemini-2.5-proGoogle · Proprietary

1449±3

96,302

18

1228

MoonshotAIkimi-k2.5-thinkingMoonshot · Modified MIT

1449±6

9,793

19

1029

qwen3.5-397b-a17bAlibaba · Apache 2.0

1449±10

3,572

20

1228

ernie-5.0-preview-1203Baidu · Proprietary

1449±7

9,742

21

1327

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

1449±4

49,803

22

1328

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

1445±3

76,620

23

1331

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

1444±6

14,549

24

1829

chatgpt-4o-latest-20250326OpenAI · Proprietary

1442±3

83,247

25

1333

glm-4.7Z.ai · MIT

1441±6

11,968

26

1833

gpt-5.2-highOpenAI · Proprietary

1440±6

17,883

27

1934

gpt-5.2OpenAI · Proprietary

1438±6

14,673

28

1836

MoonshotAIkimi-k2.5-instantMoonshot · Modified MIT

1438±8

5,827

29

2234

gpt-5.1OpenAI · Proprietary

1438±4

35,361

30

2437

gpt-5-highOpenAI · Proprietary

1434±5

32,547

31

2438

qwen3-max-previewAlibaba · Proprietary

1434±5

27,756

32

2540

o3-2025-04-16OpenAI · Proprietary

1432±4

61,262

33

2542

grok-4-1-fast-reasoningxAI · Proprietary

1431±4

29,852

34

2743

MoonshotAIkimi-k2-thinking-turboMoonshot · Modified MIT

1430±4

34,933

35

2951

gpt-5-chatOpenAI · Proprietary

1426±4

31,744

36

3253

glm-4.6Z.ai · MIT

1425±4

35,233

37

2954

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

1425±6

9,201

38

3353

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

1424±4

37,920

39

3156

deepseek-v3.2-expDeepSeek · MIT

1423±6

11,721

40

2956

deepseek-v3.2-exp-thinkingDeepSeek · MIT

1423±7

8,979

41

3553

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

1422±3

70,586

42

3258

grok-4-fast-chatxAI · Proprietary

1422±8

6,982

43

3556

deepseek-v3.2-thinkingDeepSeek · MIT

1420±5

24,549

44

3558

deepseek-v3.2DeepSeek · MIT

1419±5

29,524

45

3561

deepseek-r1-0528DeepSeek · MIT

1419±6

19,273

46

3362

ernie-5.0-preview-1022Baidu · Proprietary

1419±9

4,593

47

3561

deepseek-v3.1DeepSeek · MIT

1418±6

15,260

48

3561

MoonshotAIkimi-k2-0905-previewMoonshot · Modified MIT

1417±6

11,955

49

3561

deepseek-v3.1-thinkingDeepSeek · MIT

1417±7

11,959

50

3661

MoonshotAIkimi-k2-0711-previewMoonshot · Modified MIT

1417±5

28,625

51

3465

deepseek-v3.1-terminusDeepSeek · MIT

1416±10

3,756

52

3569

deepseek-v3.1-terminus-thinkingDeepSeek · MIT

1416±10

3,547

53

3665

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

1415±6

11,649

54

3962

mistral-large-3Mistral · Apache 2.0

1414±5

25,777

55

4062

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

1413±4

52,109

56

4062

Anthropicclaude-opus-4-20250514Anthropic · Proprietary

1413±4

45,501

57

4365

grok-3-preview-02-24xAI · Proprietary

1411±4

33,960

58

4565

mistral-medium-2508Mistral · Proprietary

1411±3

64,496

59

4565

gemini-2.5-flashGoogle · Proprietary

1411±3

95,560

60

4370

glm-4.5Z.ai · MIT

1410±5

24,745

61

4569

grok-4-0709xAI · Proprietary

1410±4

41,971

62

5475

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

1405±4

46,119

63

5475

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

1404±4

32,637

64

5475

grok-4-fast-reasoningxAI · Proprietary

1404±5

18,530

65

5976

o1-2024-12-17OpenAI · Proprietary

1402±4

27,822

66

5085

Minimaxminimax-m2.5MiniMax · Modified MIT

1402±9

4,712

67

5976

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

1402±4

39,502

68

5977

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

1402±5

22,790

69

6279

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

1400±4

36,157

70

5983

longcat-flash-chatMeituan · MIT

1400±6

11,523

71

6286

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

1399±6

9,237

72

6285

deepseek-r1DeepSeek · MIT

1398±5

18,537

73

6291

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

1395±7

7,958

74

6293

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

1394±10

3,706

75

6588

deepseek-v3-0324DeepSeek · MIT

1394±4

46,637

76

6194

Tencenthunyuan-vision-1.5-thinkingTencent · Proprietary

1393±12

2,222

77

6792

mai-1-previewMicrosoft AI · Proprietary

1392±5

18,092

78

6992

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

1391±4

46,607

79

6893

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

1391±5

18,373

80

6993

gpt-5-mini-highOpenAI · Proprietary

1390±5

27,066

81

6993

Anthropicclaude-sonnet-4-20250514Anthropic · Proprietary

1390±4

41,587

82

6894

Stepfunstep-3.5-flashStepFun · Apache 2.0

1389±7

7,382

83

7293

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

1388±4

39,863

84

7093

o1-previewOpenAI · Proprietary

1388±5

31,120

85

6996

Tencenthunyuan-t1-20250711Tencent · Proprietary

1387±9

4,793

86

7094

mimo-v2-flash (thinking)Xiaomi · MIT

1387±6

10,890

87

7394

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

1386±5

26,589

88

7394

Minimaxminimax-m2.1-previewMiniMax · MIT

1386±5

17,143

89

7494

mistral-medium-2505Mistral · Proprietary

1385±5

34,524

90

7596

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

1383±5

24,055

91

7497

Tencenthunyuan-turbos-20250416Tencent · Proprietary

1383±6

11,049

92

7797

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

1382±4

40,485

93

8397

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

1379±4

47,018

94

74107

glm-4.6vZ.ai · MIT

1378±11

2,790

95

89103

qwen3-235b-a22bAlibaba · Apache 2.0

1375±5

27,142

96

89103

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

1375±4

33,874

97

91103

qwen2.5-maxAlibaba · Proprietary

1374±4

33,283

98

94104

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

1373±3

89,445

99

94107

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

1372±4

44,417

100

94107

glm-4.5-airZ.ai · MIT

1371±4

31,293

101

94110

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

1369±6

13,826

102

94110

Minimaxminimax-m1MiniMax · Apache 2.0

1367±4

36,789

103

94114

glm-4.7-flashZ.ai · MIT

1366±7

9,284

104

98112

gemma-3-27b-itGoogle · Gemma

1365±4

48,652

105

97114

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

1365±5

18,054

106

98115

o3-mini-highOpenAI · Proprietary

1364±5

18,584

107

98118

grok-3-mini-highxAI · Proprietary

1363±5

17,505

108

101118

gemini-2.0-flash-001Google · Proprietary

1361±4

44,811

109

101126

deepseek-v3DeepSeek · DeepSeek

1358±5

21,788

110

103127

grok-3-mini-betaxAI · Proprietary

1357±5

23,745

111

101133

intellect-3Prime Intellect · MIT

1356±8

5,307

112

104130

mistral-small-2506Mistral · Apache 2.0

1356±5

18,327

113

107132

gpt-oss-120bOpenAI · Apache 2.0

1354±4

30,896

114

107133

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

1353±4

24,951

115

103134

glm-4.5vZ.ai · MIT

1353±8

4,968

116

109132

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

1353±3

57,360

117

109133

gemini-1.5-pro-002Google · Proprietary

1351±3

55,607

118

109135

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

1350±6

11,367

119

104145

Tencenthunyuan-turbos-20250226Tencent · Proprietary

1349±12

2,226

120

111134

o3-miniOpenAI · Proprietary

1348±3

58,607

121

107145

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

1348±11

2,886

122

106147

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

1347±12

2,546

123

109140

Minimaxminimax-m2MiniMax · Apache 2.0

1347±8

6,710

124

109140

ling-flash-2.0Ant Group · MIT

1347±7

7,032

125

109144

qwen3-32bAlibaba · Apache 2.0

1347±9

3,932

126

109142

Stepfunstep-3StepFun · Apache 2.0

1347±7

6,585

127

109144

qwen-plus-0125Alibaba · Proprietary

1346±8

5,823

128

114137

gpt-4o-2024-05-13OpenAI · Proprietary

1346±3

112,863

129

111147

glm-4-plus-0111Zhipu · Proprietary

1343±8

5,760

130

117141

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

1343±3

82,417

131

111149

gemma-3-12b-itGoogle · Gemma

1342±10

3,829

132

112151

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

1341±10

3,429

133

110152

Tencenthunyuan-turbo-0110Tencent · Proprietary

1340±12

2,295

134

119151

gpt-5-nano-highOpenAI · Proprietary

1338±7

8,383

135

120151

nova-2-liteAmazon · Proprietary

1337±6

12,135

136

121148

o1-miniOpenAI · Proprietary

1337±4

51,986

137

121151

qwq-32bAlibaba · Apache 2.0

1336±4

26,094

138

125150

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

1335±4

41,392

139

125151

grok-2-2024-08-13xAI · Proprietary

1335±4

63,495

140

123151

gpt-4o-2024-08-06OpenAI · Proprietary

1335±4

45,498

141

121151

gemini-advanced-0514Google · Proprietary

1335±5

50,142

142

120158

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

1334±9

4,829

143

127151

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

1334±4

59,655

144

129159

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

1331±6

12,287

145

112182

molmo-2-8bAI2 · Apache 2.0

1329±21

821

146

131163

01.AIyi-lightning01 AI · Proprietary

1329±5

27,340

147

132164

qwen3-30b-a3bAlibaba · Apache 2.0

1328±5

27,408

148

133164

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

1328±4

41,096

149

124173

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

1327±12

2,230

150

129173

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

1326±10

3,738

151

143169

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

1324±4

98,130

152

143169

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

1324±3

71,152

153

134173

deepseek-v2.5-1210DeepSeek · DeepSeek

1323±8

6,793

154

143169

gemini-1.5-pro-001Google · Proprietary

1323±4

79,132

155

143171

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

1323±5

31,204

156

144169

Anthropicclaude-3-opus-20240229Anthropic · Proprietary

1322±3

194,904

157

142174

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

1322±8

6,107

158

143173

Stepfunstep-1o-turbo-202506StepFun · Proprietary

1322±7

9,683

159

143175

ring-flash-2.0Ant Group · MIT

1320±7

7,190

160

148173

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

1320±3

55,552

161

145173

glm-4-plusZhipu AI · Proprietary

1319±5

26,134

162

145175

gemma-3n-e4b-itGoogle · Gemma

1319±5

23,320

163

145176

qwen-max-0919Alibaba · Qwen

1318±6

16,479

164

148173

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

1318±3

68,801

165

146180

gpt-oss-20bOpenAI · Apache 2.0

1317±6

10,791

166

148179

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

1317±6

15,445

167

148181

qwen2.5-plus-1127Alibaba · Proprietary

1315±6

10,179

168

152180

athene-v2-chatNexusFlow · NexusFlow

1314±5

24,746

169

152180

mistral-large-2407Mistral · Mistral Research

1314±4

45,460

170

153181

gpt-4-0125-previewOpenAI · Proprietary

1313±4

93,439

171

153181

gpt-4-1106-previewOpenAI · Proprietary

1313±4

100,107

172

148185

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

1312±10

3,905

173

160184

gemini-1.5-flash-002Google · Proprietary

1310±4

34,909

174

145190

mercuryInception AI · Proprietary

1310±14

1,896

175

164185

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

1308±4

52,574

176

164185

deepseek-v2.5DeepSeek · DeepSeek

1307±5

24,574

177

164185

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

1306±6

19,622

178

161185

olmo-3-32b-thinkAllen AI · Apache 2.0

1306±8

5,878

179

168185

mistral-large-2411Mistral · MRL

1305±4

28,081

180

165185

magistral-medium-2506Mistral · Proprietary

1305±6

12,058

181

170185

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

1305±4

34,082

182

163192

gemma-3-4b-itGoogle · Gemma

1303±9

4,177

183

172185

qwen2.5-72b-instructAlibaba · Qwen

1303±4

39,409

184

172195

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

1299±8

7,136

185

173196

Tencenthunyuan-large-visionTencent · Proprietary

1296±9

5,597

186

182196

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

1294±4

55,234

187

183197

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

1290±5

24,753

188

182200

jamba-1.5-largeAI21 Labs · Jamba Open

1289±7

8,659

189

182201

ibm-granite-h-smallIBM · Apache 2.0

1288±8

5,657

190

184198

gemma-2-27b-itGoogle · Gemma license

1288±3

75,764

191

183200

reka-core-20240904Reka AI · Proprietary

1288±7

7,309

192

184200

gpt-4-0314OpenAI · Proprietary

1287±5

54,167

193

182206

llama-3.1-tulu-3-70bAi2 · Llama 3.1

1287±10

2,846

194

182206

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

1286±10

3,749

195

185200

gemini-1.5-flash-001Google · Proprietary

1286±4

62,823

196

184206

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

1285±7

8,455

197

188206

Anthropicclaude-3-sonnet-20240229Anthropic · Proprietary

1281±4

109,289

198

187206

gemma-2-9b-it-simpoPrinceton · MIT

1279±7

10,069

199

189206

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

1278±5

19,661

200

189208

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

1277±7

9,869

201

194206

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

1276±4

156,880

202

194207

gpt-4-0613OpenAI · Proprietary

1275±4

88,721

203

194209

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

1274±6

14,677

204

193210

glm-4-0520Zhipu AI · Proprietary

1274±7

9,788

205

194212

reka-flash-20240904Reka AI · Proprietary

1272±7

7,537

206

194215

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

1271±8

5,430

207

201215

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

1267±5

27,123

208

203215

gemma-2-9b-itGoogle · Gemma license

1266±4

54,615

209

202216

deepseek-coder-v2DeepSeek · DeepSeek License

1264±6

15,147

210

205216

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

1262±4

77,556

211

204216

qwen2-72b-instructAlibaba · Qianwen LICENSE

1262±5

37,325

212

206216

Anthropicclaude-3-haiku-20240307Anthropic · Proprietary

1261±4

117,705

213

205217

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

1261±5

19,376

214

206217

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

1259±4

35,556

215

209217

Azurephi-4Microsoft · MIT

1256±5

24,126

216

206223

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

1252±11

3,335

217

213222

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

1250±7

10,141

218

216226

mistral-large-2402Mistral · Proprietary

1243±5

62,437

219

216226

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

1241±5

19,355

220

216230

jamba-1.5-miniAI21 Labs · Jamba Open

1239±7

8,854

221

216234

ministral-8b-2410Mistral · MRL

1237±9

4,780

222

217234

gemini-pro-dev-apiGoogle · Proprietary

1235±7

18,352

223

218234

qwen1.5-110b-chatAlibaba · Qianwen LICENSE

1234±6

26,191

224

218235

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

1233±7

15,451

225

216236

Tencenthunyuan-standard-256kTencent · Proprietary

1233±12

2,729

226

218234

qwen1.5-72b-chatAlibaba · Qianwen LICENSE

1233±5

39,296

227

220235

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

1230±5

51,417

228

220236

Coherecommand-rCohere · CC-BY-NC-4.0

1227±5

54,038

229

220236

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

1227±6

24,806

230

221237

gpt-3.5-turbo-0125OpenAI · Proprietary

1224±5

66,191

231

225237

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

1223±4

104,636

232

221238

mistral-mediumMistral · Proprietary

1223±6

34,552

233

221238

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

1223±7

9,827

234

220241

gemini-proGoogle · Proprietary

1222±12

6,390

235

221241

llama-3.1-tulu-3-8bAi2 · Llama 3.1

1221±11

2,895

236

232241

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

1214±5

24,142

237

227243

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

1213±11

4,653

238

234241

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

1212±4

49,605

239

230247

granite-3.1-8b-instructIBM · Apache 2.0

1209±11

3,092

240

234247

qwen1.5-32b-chatAlibaba · Qianwen LICENSE

1204±6

21,744

241

234249

gpt-3.5-turbo-1106OpenAI · Proprietary

1203±9

16,616

242

238248

gemma-2-2b-itGoogle · Gemma license

1199±4

46,618

243

238249

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

1198±5

25,055

244

239249

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

1197±4

73,505

245

239254

dbrx-instruct-previewDatabricks · DBRX LICENSE

1195±6

32,196

246

239258

InternLMinternlm2_5-20b-chatInternLM · Other

1191±7

9,902

247

239258

qwen1.5-14b-chatAlibaba · Qianwen LICENSE

1191±7

17,841

248

242264

Azurewizardlm-70bMicrosoft · Llama 2 Community

1185±9

8,214

249

241265

deepseek-llm-67b-chatDeepSeek · DeepSeek License

1185±12

4,933

250

245261

01.AIyi-34b-chat01 AI · Yi License

1184±7

15,483

251

245264

OpenChatopenchat-3.5-0106OpenChat · Apache-2.0

1183±8

12,636

252

245265

OpenChatopenchat-3.5OpenChat · Apache-2.0

1182±10

7,967

253

245265

granite-3.0-8b-instructIBM · Apache 2.0

1182±9

6,643

254

246265

gemma-1.1-7b-itGoogle · Gemma license

1180±6

23,893

255

246265

Snowflakesnowflake-arctic-instructSnowflake · Apache 2.0

1180±6

32,836

256

245266

granite-3.1-2b-instructIBM · Apache 2.0

1179±11

3,191

257

246266

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

1178±10

6,534

258

246269

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

1175±10

5,006

259

248268

vicuna-33bLMSYS · Non-commercial

1173±6

22,479

260

248270

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

1172±7

16,057

261

248269

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

1171±6

17,763

262

249269

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

1171±6

38,491

263

249272

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

1168±8

10,224

264

251272

Metallama-3.2-3b-instructMeta · Llama 3.2

1167±8

7,936

265

249275

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

1165±12

3,776

266

256281

qwq-32b-previewAlibaba · Apache 2.0

1157±12

3,233

267

262279

granite-3.0-2b-instructIBM · Apache 2.0

1156±8

6,837

268

258282

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

1156±13

3,584

269

259285

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

1153±13

4,155

270

258287

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

1152±15

1,679

271

263285

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

1150±12

2,571

272

265282

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

1150±7

19,402

273

265284

Azurewizardlm-13bMicrosoft · Llama 2 Community

1149±9

7,046

274

262289

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

1147±17

1,295

275

265288

qwen1.5-7b-chatAlibaba · Qianwen LICENSE

1144±10

4,735

276

266287

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

1143±6

12,296

277

266288

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

1142±7

19,171

278

266288

vicuna-13bLMSYS · Llama 2 Community

1141±7

19,366

279

266290

qwen-14b-chatAlibaba · Qianwen LICENSE

1139±11

4,964

280

267290

palm-2Google · Proprietary

1137±9

8,554

281

267290

Metacodellama-34b-instructMeta · Llama 2 Community

1137±9

7,363

282

268290

gemma-7b-itGoogle · Gemma license

1136±10

8,925

283

270291

HuggingFacezephyr-7b-betaHuggingFace · MIT

1131±9

11,116

284

273291

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

1129±7

20,691

285

275291

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

1129±6

20,115

286

271295

guanaco-33bUW · Non-commercial

1128±12

2,921

287

270295

HuggingFacezephyr-7b-alphaHuggingFace · MIT

1127±16

1,785

288

278295

stripedhyena-nous-7bTogether AI · Apache 2.0

1121±11

5,184

289

273296

Metacodellama-70b-instructMeta · Llama 2 Community

1119±18

1,143

290

283295

vicuna-7bLMSYS · Llama 2 Community

1115±9

6,923

291

279296

HuggingFacesmollm2-1.7b-instructHuggingFace · Apache 2.0

1114±14

2,201

292

286295

gemma-1.1-2b-itGoogle · Gemma license

1114±8

10,853

293

286295

Metallama-3.2-1b-instructMeta · Llama 3.2

1111±8

8,045

294

286296

mistral-7b-instructMistral · Apache 2.0

1110±9

8,977

295

286296

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

1108±7

14,148

296

292300

gemma-2b-itGoogle · Gemma license

1092±12

4,779

297

296299

qwen1.5-4b-chatAlibaba · Qianwen LICENSE

1090±9

7,598

298

296303

olmo-7b-instructAllen AI · Apache-2.0

1075±11

6,329

299

297303

koala-13bUC Berkeley · Non-commercial

1071±10

6,964

300

298303

alpaca-13bStanford · Non-commercial

1068±12

5,745

301

296304

gpt4all-13b-snoozyNomic AI · Non-commercial

1066±15

1,743

302

298304

mpt-7b-chatMosaicML · CC-BY-NC-SA-4.0

1062±12

3,925

303

298304

chatglm3-6bTsinghua · Apache-2.0

1056±12

4,658

304

301306

RWKVRWKV-4-Raven-14BRWKV · Apache 2.0

1041±11

4,845

305

304306

chatglm2-6bTsinghua · Apache-2.0

1024±14

2,657

306

304306

oasst-pythia-12bOpenAssistant · Apache 2.0

1022±11

6,311

307

307310

chatglm-6bTsinghua · Non-commercial

996±13

4,914

308

307310

fastchat-t5-3bLMSYS · Apache 2.0

991±12

4,203

309

307310

dolly-v2-12bDatabricks · MIT

980±14

3,412

310

307311

Metallama-13bMeta · Non-commercial

972±16

2,391

311

310311

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?