Model
Size
Version
Released
Code
RankedAGI
Code
LiveBench
Aider
Polyglot
SWEBench
Verified
Codeforces
ELO
WebDev
Arena
LiveCodeBench
v5
Code
LMArena
GPQA
Diamond
Reason
LiveBench
ELO
LMArena
AIME
2025 I & II
Math
LiveBench
MATH
MMLU
Pro
MMLU
MMMU
Halluc.
Hughes
Aidan
Bench
AIME
2024
IF
LiveBench
Data
LiveBench
Avg
LiveBench
IF
Evaluation
Input
Cost /M
Output
Cost /M
Cutoff
Knowledge
Context
Length
Org.
License
1
OpenAI logo o3 highLatestApr 16, 202578.2%76.7%79.6%89.2%$10$40Jun 24200KOpenAIProprietary
2
OpenAI logo o4 mini highLatestApr 16, 202576.0%80.0%72.0%91.7%$1.1$4.4Jun 24200KOpenAIProprietary
3
Google logo Gemini 2.5 ProPreviewMay 6, 202574.9%72.9%76.9%1419.95GoogleProprietary
4
OpenAI logo o3LatestApr 16, 202573.5%77.9%69.1%27061187.08137487.7%141188.9%91.6%$10$40Jun 24200KOpenAIProprietary
5
Google logo Gemini 2.5 ProOldMar 25, 202570.2%58.1%72.9%63.8%1272.8670.4%135284.0%89.8%144386.7%90.2%89.8%81.7%1.1%92.0%80.6%79.9%82.3%$1.25$10Jan 251MGoogleProprietary
6
Alibaba logo QWQ MaxPreviewFeb 25, 202568.2%68.2%Sep 24AlibabaOpen Source
7
xAI logo Grok 3 (Think)PreviewFeb 17, 202567.4%84.6%93.3%78.0%93.3%Nov 241MxAIProprietary
8
OpenAI logo o3 mini highLatestJan 31, 202567.2%65.5%60.4%49.3%21301147.2780.5%133279.7%89.6%133286.5%76.5%97.9%86.9%0.8%87.3%84.4%70.6%75.8%$1$4.4Oct 23200KOpenAIProprietary
9
Alibaba logo Qwen 3 A22B235BLatestApr 29, 202565.6%65.3%61.8%205670.7%81.5%85.7%128KAlibabaOpen Source
10
OpenAI logo o4 miniLatestApr 16, 202565.0%61.8%68.1%27191093.02133481.4%135281.6%$1.1$4.4Jun 24200KOpenAIProprietary
11
Hanyuan T1LatestMar 21, 202564.9%64.9%69.3%87.2%78.2%TencentOpen Source
12
Alibaba logo Qwen 3 A3B30BLatestApr 29, 202562.6%197462.6%65.8%70.9%80.4%128KAlibabaOpen Source
13
OpenAI logo o1LatestDec 17, 202461.9%61.7%41.0%18911050.1478.3%133176.0%91.6%135979.0%67.3%2.4%320483.3%81.5%65.5%73.5%$15$60Oct 23200KOpenAIProprietary
14
OpenAI logo GPT 4oLatestMar 26, 202561.4%77.5%45.3%1385140869.1%$5$15Oct 23128KOpenAIProprietary
15
Anthropic logo Claude 3.7 Sonnet ThinkingLatestFeb 24, 202560.4%44.7%64.9%133378.2%84.6%130649.5%77.5%75.0%80.0%78.6%72.8%74.3%93.2%$3$15Oct 24200KAnthropicProprietary
16
LG logo EXAONE Deep32BLatestMar 18, 202559.5%59.5%66.1%80.0%74.0%83.0%90.0%LGProprietary
17
OpenAI logo o3 mini mediumLatestJan 31, 202559.1%58.4%53.8%42.9%20361100.1879.2%130976.8%86.3%130576.5%97.3%85.9%79.6%83.2%66.6%70.0%$1$4.4Oct 23200KOpenAIProprietary
18
OpenAI logo o1 ProLatestDec 17, 202458.7%57.1%61.7%19140.83279.0%77.5%79.3%2.4%86.0%81.5%65.5%72.2%$150$600Oct 23200KOpenAIProprietary
19
OpenAI logo GPT 4.5PreviewFeb 27, 202558.6%76.1%45.0%38.0%136271.4%71.1%141169.3%74.4%1.2%36.7%72.3%64.3%69.0%$75$150128KOpenAIProprietary
20
Anthropic logo Claude 3.7 SonnetLatestFeb 24, 202557.7%32.4%60.4%70.3%1355.76132668.0%66.0%129563.3%71.8%23.3%76.5%63.4%65.6%90.8%$3$15Oct 24200KAnthropicProprietary
21
Google logo Gemini 2.5 FlashPreviewApr 17, 202557.2%58.4%51.1%1145.1363.5%78.3%78.0%88.4%76.7%88.0%$0.15$0.6Jan 25GoogleProprietary
22
DeepSeek logo DeepSeek R1671BLatestJan 20, 202556.8%48.5%56.9%49.2%20291205.2164.3%134271.5%83.2%135970.0%79.5%84.0%90.8%14.3%80.5%69.8%71.4%83.3%$0.55$2.19Jul 24128KDeepSeekOpen Source
23
OpenAI logo o3 mini lowLatestJan 31, 202556.0%50.8%40.8%183174.5%70.6%69.8%48.0%61.4%95.8%84.9%60.0%80.1%63.0%62.2%$1$4.4Oct 23200KOpenAIProprietary
24
LG logo EXAONE Deep7.8BLatestMar 18, 202555.2%55.2%62.6%76.7%65.7%75.0%83.3%LGProprietary
25
Alibaba logo Qwen 34BLatestApr 29, 202554.2%54.2%167155.9%65.6%73.8%32KAlibabaOpen Source
26
DeepSeek logo DeepSeek V3685BLatestMar 24, 202554.2%40.5%55.1%1209.2349.2%134368.4%65.8%137073.5%81.2%8.0%59.4%81.5%60.4%66.9%$0.27$1.1Jul 24128KDeepSeekOpen Source
27
Google logo Gemini 2 Flash ThinkingOldDec 19, 202453.1%1023.36128364.6%136969.0%275579.3%68.1%61.8%Aug 2432KGoogleProprietary
28
Google logo Gemini Exp 1114OldNov 14, 202452.4%54.7%134354.9%77.1%57.5%56.4%Aug 2432KGoogleProprietary
29
Alibaba logo Qwen 332BLatestApr 29, 202551.4%40.0%197765.7%85.7%81.4%128KAlibabaOpen Source
30
Google logo Gemini Exp 1206OldDec 6, 202450.8%38.2%1022.5157.0%137970.0%77.3%63.2%63.7%Aug 242MGoogleProprietary
31
Google logo Gemini Exp 1121OldNov 21, 202450.4%45.3%136562.7%80.2%57.0%59.0%Aug 2432KGoogleProprietary
32
OpenAI logo GPT 4.1LatestApr 14, 202550.3%43.0%53.0%55.0%1261.3566.3%90.2%75.0%48.1%87.0%$2$8Jun 241MOpenAIProprietary
33
Google logo Gemini 2.0 ProPreviewFeb 5, 202549.4%35.3%1109.54129864.7%60.1%137927.5%71.0%91.8%79.1%72.7%0.8%83.4%68.0%65.1%Aug 242MGoogleProprietary
34
Alibaba logo QwQ32BLatestMar 5, 202549.2%43.0%20.9%63.4%129183.5%131266.0%64.9%79.5%81.8%65.0%72.0%83.9%$0.4$0.55Sep 24131KAlibabaOpen Source
35
Meta logo Llama 4 Behemoth2TPreviewApr 5, 202549.0%49.0%73.7%82.2%85.8%76.1%Aug 24MetaOpen Source
36
DeepSeek logo R1 Distill Llama70BLatestJan 20, 202548.8%46.6%163365.2%67.6%55.0%70.0%41.5%55.9%49.7%Dec 23DeepSeekOpen Source
37
OpenAI logo o1 PreviewOldSep 12, 202448.7%41.0%125855.6%131273.3%68.0%133362.9%85.0%91.0%3.3%189256.7%74.6%64.0%69.1%$15$60Oct 23128KOpenAIProprietary
38
DeepSeek logo Deepseek V3671BOldDec 26, 202448.6%48.4%42.0%1134963.9140.5%127959.1%56.8%131525.0%60.5%75.9%88.5%3.9%75.3%60.9%60.5%86.1%$0.07$1.1Jul 24128KDeepSeekOpen Source
39
Anthropic logo Claude 3.5 SonnetLatestOct 22, 202448.3%32.3%51.6%49.0%7171245.439.8%131365.0%58.7%12823.0%51.3%78.3%78.0%88.0%70.4%4.6%269116.0%69.3%52.8%60.7%89.3%$3$15Apr 24200KAnthropicProprietary
40
Mistral logo Mistral Large123BOldJul 24, 202447.1%124448.0%42.0%125043.7%72.0%65.9%85.0%4.1%67.9%44.0%50.4%$2$6Jul 24128KMistralProprietary
41
LG logo EXAONE Deep2.4BLatestMar 18, 202546.6%46.6%54.3%73.3%56.4%65.8%76.7%LGProprietary
42
xAI logo Grok 3 miniLatestFeb 17, 202546.6%39.7%34.7%70.0%79.0%83.0%69.4%93.0%$0.3$0.5Nov 24130KxAIProprietary
43
Google logo Gemini 1.5 Pro 002OldSep 24, 202445.8%893.3442.1%125359.1%46.0%130157.4%86.5%75.8%86.0%6.6%151570.8%52.3%55.5%81.9%$1.25$2.5Sep 242MGoogleProprietary
44
xAI logo Grok 3LatestFeb 17, 202545.3%37.3%53.3%1148.53133575.4%141279.9%73.2%52.2%$3$15Nov 24130KxAIProprietary
45
xAI logo Grok 2LatestAug 13, 202445.1%125356.0%36.3%129045.8%76.1%75.5%87.5%4.6%82669.6%50.3%54.4%$5$15Aug 24128KxAIProprietary
46
OpenAI logo o1 miniLatestSep 12, 202444.9%32.9%35.0%16501053.6968.4%129260.0%77.3%130859.2%90.0%80.3%85.0%1.4%157763.6%65.4%54.1%53.4%$3$12Oct 23128KOpenAIProprietary
47
Google logo Gemini 2 Flash ThinkingPreviewJan 21, 202544.6%35.7%1034.54129074.2%78.2%138053.5%1.8%82.5%69.4%66.9%Aug 241MGoogleProprietary
48
Anthropic logo Claude 3.5 SonnetOldJun 20, 202444.0%33.4%36.0%128259.4%58.7%126853.3%71.1%76.1%88.7%68.3%143968.0%56.7%59.7%$3$15Apr 24200KAnthropicProprietary
49
OpenAI logo GPT 4oOldJan 29, 202543.8%27.1%133157.9%137748.0%65.1%66.0%57.8%$2.5$10Jun 24128KOpenAIProprietary
50
Mistral logo Mistral Large123BLatestNov 18, 202442.7%37.3%122847.0%43.4%125132.6%72.0%84.0%4.1%95363.7%46.6%50.0%$2$6Jul 24128KMistralProprietary
51
DeepSeek logo R1 Distill Qwen32BLatestJan 20, 202542.6%52.3%169162.1%52.3%72.6%40.9%45.4%42.9%Sep 24DeepSeekOpen Source
52
Google logo Gemini 2.0 Flash ExpOldDec 11, 202442.5%22.2%51.8%983.9741.6%129062.1%59.1%135659.4%89.7%76.4%87.0%1.3%189581.9%59.7%58.0%Aug 241MGoogleProprietary
53
OpenAI logo GPT 4oOldAug 6, 202441.6%31.8%125151.0%54.7%126548.2%78.0%74.7%89.0%133368.6%52.9%55.1%$2.5$10Oct 23128KOpenAIProprietary
54
DeepSeek logo DeepSeek Coder 2236BLatestJul 22, 202441.5%122642.0%45.3%121358.0%63.6%80.0%67.2%38.3%47.2%$0.14$0.28Nov 23128KDeepSeekProprietary
55
Google logo Gemini 1.5 Pro 001OldAug 27, 202440.9%124449.3%126056.1%69.0%9.1%69.3%50.8%55.4%Nov 232MGoogleProprietary
56
Google logo Gemini 1.5 Flash 001OldAug 27, 202440.6%120847.3%122759.1%6.6%73.0%47.9%50.1%Nov 231MGoogleProprietary
57
Alibaba logo QwQ Preview32BPreviewNov 28, 202440.2%44.0%65.2%57.7%33.5%50.8%75.0%12.9%44.0%35.6%3.2%28.5%Sep 2432KAlibabaOpen Source
58
Google logo Gemini 2.0 FlashLatestFeb 5, 202540.1%26.2%1041.64127160.1%55.3%135727.5%65.6%90.9%77.6%71.7%0.7%85.8%67.5%61.5%$0.1$0.4Aug 241MGoogleProprietary
59
Alibaba logo Qwen 2.5 MaxLatestJan 28, 202540.0%33.8%21.8%981.52129160.1%51.4%133268.5%76.1%75.3%67.9%62.3%$0.0016$0.0064Sep 2432KAlibabaProprietary
60
Anthropic logo Claude 3.5 HaikuLatestOct 22, 202440.0%28.0%40.6%1134.43126341.6%29.3%123935.5%73.0%65.0%81.0%4.9%90461.9%42.4%47.8%$1$5Jul 24200KAnthropicProprietary
61
Google logo Gemini 1.5 Flash 002OldSep 24, 202439.3%36.1%121051.0%50.0%126947.2%77.9%67.3%81.0%3.4%104778.8%44.2%50.3%$0.075$0.3Sep 241MGoogleProprietary
62
Alibaba logo Qwen 2.57BLatestSep 19, 202438.4%26.2%38.2%2.8%52.1%32.8%33.6%Sep 24128KAlibabaOpen Source
63
Alibaba logo Qwen 2.572BLatestSep 19, 202438.0%23.8%31.1%124749.0%46.0%125952.4%83.1%71.1%86.8%4.7%64.4%48.4%51.4%$0.38$0.57Sep 24128KAlibabaOpen Source
64
xAI logo Grok-2 miniLatestAug 13, 202437.5%123051.0%42.0%126673.0%72.0%86.2%69.7%44.3%51.1%Aug 24128KxAIProprietary
65
Amazon logo Nova ProLatestDec 3, 202437.1%122846.9%32.6%124539.1%76.6%84.0%1.8%67.1%43.6%49.2%92.1%$0.8$3.2300KAmazonProprietary
66
Meta logo Llama 3.370BLatestDec 6, 202436.6%123250.5%50.7%125741.1%77.0%68.9%86.0%4.0%77982.7%48.3%56.7%92.1%$0.1$0.4Dec 23MetaOpen Source
67
Google logo Gemma 227BLatestJun 27, 202435.9%120328.1%122026.2%42.3%56.5%75.2%102858.1%43.6%37.4%Jun 248KGoogleOpen Source
68
OpenAI logo GPT 4.1 miniLatestApr 14, 202535.5%47.6%35.0%24.0%1188.5665.0%87.5%73.0%49.6%84.0%$0.4$1.6Jun 241MOpenAIProprietary
69
Google logo Gemini 2.0 Flash-LiteLatestFeb 5, 202533.6%23.4%124651.5%50.1%130655.5%86.8%71.6%68.0%1.2%78.3%57.5%53.2%$0.075$0.3Aug 241MGoogleProprietary
70
Meta logo Llama 4 Scout109BLatestApr 5, 202532.8%895.2632.8%57.2%74.3%69.4%Aug 2410MMetaOpen Source
71
Meta logo Llama 3.170BOldJul 23, 202432.7%120943.0%40.7%124234.4%60.0%66.4%86.0%5.0%69.0%49.1%50.9%87.5%$1$3Dec 23128KMetaOpen Source
72
OpenAI logo GPT 4oOldNov 20, 202432.6%35.2%18.2%31.0%964130639.0%53.3%136113.0%42.5%69.0%74.7%86.0%1.5%126964.9%47.2%53.2%84.6%$2.5$10Nov 23128KOpenAIProprietary
73
Alibaba logo Qwen 2.5 Coder32BLatestNov 12, 202432.4%8.0%903.59122741.0%47.3%122046.0%72.0%79.0%58.7%43.4%45.6%$0.2$0.2Sep 24128KAlibabaOpen Source
74
Meta logo Llama 3.1405BLatestJul 23, 202432.1%24.5%811.9128.4%126051.1%53.3%126640.5%73.8%73.3%87.0%3.9%77875.9%54.5%58.6%88.6%$5$15Dec 23128KMetaOpen Source
75
DeepSeek logo DeepSeek 2.5236BOldSep 12, 202432.1%17.8%125542.0%39.3%122155.0%65.8%81.0%56.7%45.8%44.7%$0.14$0.28Nov 23128KDeepSeekProprietary
76
Anthropic logo Claude 3 OpusLatestMar 4, 202430.3%22.0%123650.4%41.3%124843.4%60.1%68.5%84.0%10.1%90863.9%54.3%56.2%$15$75Aug 23200KAnthropicProprietary
77
Google logo Gemini 1.5 Flash8BOldSep 24, 202428.7%116738.4%33.3%117758.7%58.7%52.6%44.0%42.7%$0.0375$0.15Sep 241MGoogleProprietary
78
Mistral logo Mistral Nemo12BLatestJul 24, 202428.7%33.0%25.3%16.9%40.0%44.8%68.0%11.2%51.8%33.4%32.0%$0.15$0.15Apr 24128KMistralProprietary
79
Meta logo Llama 4 Maverick400BLatestApr 5, 202528.2%16.0%1006.5243.4%126569.8%127380.5%84.6%73.4%$0.19$0.49Aug 241MMetaOpen Source
80
Amazon logo Nova LiteLatestDec 3, 202427.5%120042.0%34.7%121730.8%73.3%79.0%1.8%$0.06$0.24300KAmazonProprietary
81
Alibaba logo Qwen 2.532BLatestSep 19, 202427.0%49.5%83.1%69.2%83.9%3.0%79.5%Sep 24128KAlibabaOpen Source
82
Mercury Coder SmallPreviewFeb 26, 202525.0%25.0%Inception LabsProprietary
83
OpenAI logo GPT 4o miniLatestJul 18, 202424.1%25.5%3.6%124543.0%35.3%127235.6%75.0%63.1%82.0%1.7%56.8%44.5%43.3%$0.15$0.6Oct 23128KOpenAIProprietary
84
Anthropic logo Claude 3 HaikuOldMar 7, 202423.5%22.2%118433.3%25.9%117922.9%40.9%42.3%75.2%$0.25$1.25Aug 23200KAnthropicProprietary
85
Alibaba logo Qwen 2.5 Coder14BLatestNov 12, 202423.4%Sep 24128KAlibabaOpen Source
86
Google logo Gemma 29BLatestJun 27, 202422.5%118015.2%19.5%36.6%52.1%71.3%10.1%85952.6%35.1%28.4%Jun 248KGoogleOpen Source
87
Mistral logo Codestral 25.01LatestJan 14, 202521.9%11.1%35.3%256KMistralProprietary
88
Alibaba logo Qwen 2.514BLatestSep 19, 202420.9%45.5%80.0%63.7%80.0%4.2%81.0%Sep 24128KAlibabaOpen Source
89
Alibaba logo Qwen 2.5 Coder7BLatestNov 12, 202420.3%Sep 24128KAlibabaOpen Source
90
Amazon logo Nova MicroLatestDec 3, 202420.2%118140.0%25.1%119833.7%69.3%76.0%1.6%$0.04$0.14128KAmazonProprietary
91
Meta logo Llama 3.18BLatestJul 23, 202419.7%117427.0%15.3%117116.6%64.0%44.3%71.0%5.4%$0.3$0.6Dec 23128KMetaOpen Source
92
Google logo Gemma 312BLatestMar 12, 202519.1%19.1%GoogleOpen Source
93
OpenAI logo GPT 4.1 nanoLatestApr 14, 202517.6%25.3%10.0%50.3%80.1%55.0%29.4%75.0%$0.1$0.4Jun 241MOpenAIProprietary
94
Mercury Coder MiniPreviewFeb 26, 202517.0%17.0%Inception LabsProprietary
95
Google logo Gemma 327BLatestMar 12, 202515.2%25.4%4.9%124442.4%133989.0%67.5%76.9%64.9%3.0%GoogleOpen Source
96
Google logo Gemma 34BLatestMar 12, 202511.7%11.7%GoogleOpen Source
97
Alibaba logo Qwen 2.5 Coder3BLatestNov 12, 202410.8%Sep 2432KAlibabaOpen Source
98
Alibaba logo Qwen 2.5 Coder1.5BLatestNov 12, 20246.1%Sep 2432KAlibabaOpen Source
99
Alibaba logo Qwen 2.51.5BLatestSep 19, 20244.7%32.1%15.8%Sep 2432KAlibabaOpen Source
100
Alibaba logo Qwen 2.5 Coder0.5BLatestNov 12, 20242.0%Sep 2432KAlibabaOpen Source
101
Alibaba logo Qwen 2.50.5BLatestSep 19, 20242.0%14.9%25.2%Sep 2432KAlibabaOpen Source
102
DeepSeek logo R1 Distill Qwen14BLatestJan 20, 2025148159.1%49.0%69.7%Sep 24DeepSeekOpen Source
103
DeepSeek logo R1 Lite PreviewPreviewNov 20, 2024145058.5%91.6%52.5%DeepSeekProprietary
104
DeepSeek logo R1 Distill Llama8BLatestJan 20, 2025120549.0%50.4%Dec 24DeepSeekOpen Source
105
DeepSeek logo R1 Distill Qwen7BLatestJan 20, 2025118949.1%59.0%55.5%Sep 24DeepSeekOpen Source
106
DeepSeek logo R1 Distill Qwen1.5BLatestJan 20, 202595433.8%20.0%28.9%Sep 24DeepSeekOpen Source
107
xAI logo Grok 3 mini (Think)PreviewFeb 17, 202584.0%90.8%95.8%Nov 241MxAIProprietary
108
Sky T1 Preview32BPreviewJan 11, 202556.8%69.2%43.3%NovaSkyOpen Source
109
Microsoft logo Phi 414BLatestDec 12, 202456.1%80.4%70.4%84.8%63.0%MicrosoftOpen Source
110
Mistral logo Pixtral Large123BLatestNov 18, 202452.0%72.0%85.0%6.6%$2$6128KMistralProprietary
111
Alibaba logo Qwen 2.5 VL32BLatestMar 24, 202546.0%82.2%68.8%AlibabaOpen Source
112
Mistral logo Mistral Small 3.124BLatestMar 17, 202546.0%69.3%66.8%80.6%62.8%5.6%128KMistralOpen Source
113
Mistral logo Mistral Small 324BLatestJan 30, 202545.3%70.6%66.3%81.0%3.1%82.9%32KMistralProprietary
114
Meta logo Llama 3.2 (Vision)90BLatestSep 25, 202443.0%68.0%86.0%4.3%$0.9$0.9Dec 23128KMetaOpen Source
115
Meta logo Llama 3.2 (Vision)11BLatestSep 25, 202426.0%51.9%73.0%5.5%$0.19$0.19Dec 23128KMetaOpen Source
116
Meta logo Llama 3.23BLatestSep 25, 2024104821.0%109349.0%22.2%63.4%7.9%$0.08$0.1Dec 23128KMetaOpen Source
117
Meta logo Llama 3.21BLatestSep 25, 2024100914.0%104427.0%11.9%49.3%20.7%$0.04$0.08Dec 23128KMetaOpen Source
118
Mistral logo Mistral Medium 3LatestMay 7, 202577.2%66.1%89.4%$0.4$2Mistral
119
Cohere logo Command A111BLatestMar 13, 202512881310$2.5$10256KCohereOpen Source
120
R1 1776LatestFeb 18, 202590.5%81.0%$2$8128KPerplexityOpen Source
121
DeepSeek logo Deepseek 2.5OldDec 10, 2024126212582.4%Nov 23128KDeepSeekProprietary
122
Alibaba logo Qwen 2.5 TurboLatestNov 15, 2024Sep 241MAlibabaProprietary
123
Alibaba logo Qwen 2.53BLatestSep 19, 202443.7%7.0%Sep 2432KAlibabaOpen Source
124
Google logo Gemma 22BLatestJul 31, 202415.0%51.3%7.0%Jun 248KGoogleOpen Source
124 models