Todos os 602 LLMs comparados em inteligência e custo

Cada modelo no instantâneo 2026-08-19 de Artificial Analysis e outras fontes, classificado por inteligência por dólar gasto na execução do benchmark. As linhas marcadas com estrela contêm o Pareto frontier de inteligência versus custo. Abra um modelo para seus números, se ainda é o melhor valor e confrontos diretos. “Fronteira aberta” marca os modelos com pesos para download que nenhum outro modelo com pesos para download supera.

Modelos
602
Modelos com pesos para download (open weights)
341
Na fronteira
15
Fronteira de modelos com pesos para download (open-weights frontier)
15
Retrato dos dados
2026-08-19
Pareto frontier de hoje

O melhor custo-benefício para cada orçamento

Cada um é o modelo mais inteligente que você consegue pelo preço. Todos os outros modelos são superados por algum deles. Do mais barato ao mais caro.

  1. OpenAIGPT-5.6 Luna (Non-reasoning)
    Pontuação de inteligência (Intelligence Index)
    26.80
    Custo do benchmark (USD)
    $10.2
  2. OpenAIGPT-5.6 Luna (low)
    Pontuação de inteligência (Intelligence Index)
    33.90
    Custo do benchmark (USD)
    $13.7
  3. OpenAIGPT-5.6 Luna (medium)
    Pontuação de inteligência (Intelligence Index)
    38.90
    Custo do benchmark (USD)
    $21.1
  4. OpenAIGPT-5.6 Luna (high)
    Pontuação de inteligência (Intelligence Index)
    47.00
    Custo do benchmark (USD)
    $55.0
  5. OpenAIGPT-5.6 Luna (xhigh)
    Pontuação de inteligência (Intelligence Index)
    50.10
    Custo do benchmark (USD)
    $95.1
  6. GoogleGemini 3.7 Flash (low)
    Pontuação de inteligência (Intelligence Index)
    50.90
    Custo do benchmark (USD)
    $165
  7. OpenAIGPT-5.6 Luna (max)
    Pontuação de inteligência (Intelligence Index)
    52.30
    Custo do benchmark (USD)
    $172
  8. GoogleGemini 3.7 Flash (medium)
    Pontuação de inteligência (Intelligence Index)
    53.40
    Custo do benchmark (USD)
    $278
  9. GoogleGemini 3.7 Flash (high)
    Pontuação de inteligência (Intelligence Index)
    56.00
    Custo do benchmark (USD)
    $485
  10. MetaMuse Spark 1.2 (xhigh)
    Pontuação de inteligência (Intelligence Index)
    56.80
    Custo do benchmark (USD)
    $639
  11. OpenAIGPT-5.6 Sol (high)
    Pontuação de inteligência (Intelligence Index)
    57.30
    Custo do benchmark (USD)
    $955
  12. SpaceXAIGrok 4.6 (high)
    Pontuação de inteligência (Intelligence Index)
    60.90
    Custo do benchmark (USD)
    $1068
  13. AnthropicClaude Opus 5 (Adaptive Reasoning, High Effort)
    Pontuação de inteligência (Intelligence Index)
    61.50
    Custo do benchmark (USD)
    $1974
  14. AnthropicClaude Opus 5 (Adaptive Reasoning, Xhigh Effort)
    Pontuação de inteligência (Intelligence Index)
    62.50
    Custo do benchmark (USD)
    $2909
  15. AnthropicClaude Opus 5 (Adaptive Reasoning, Max Effort)
    Pontuação de inteligência (Intelligence Index)
    63.10
    Custo do benchmark (USD)
    $3836
Last 30 dias

Lançamentos recentes

Últimos lançamentos
Z AI · 2026-08-18GLM-5.3
Hoje
Fora da fronteira
Dia do lançamento
Fora da fronteira
Alibaba · 2026-08-14Modelos com pesos para download (open weights)Qwen3.8 27B
Ainda não há dados de benchmark
DeepSeek · 2026-08-13Modelos com pesos para download (open weights)DeepSeek V4 Pro 0813
Hoje
Fronteira de modelos com pesos para download (open-weights frontier)
Dia do lançamento
Fronteira de modelos com pesos para download (open-weights frontier)
Google · 2026-08-13Gemini 3.7 Flash
Hoje
Melhor custo-benefício
Dia do lançamento
Melhor custo-benefício
SK Telecom · 2026-08-12Modelos com pesos para download (open weights)A.X-K2
Ainda não há dados de benchmark
SpaceXAI · 2026-08-12Grok 4.6
Hoje
Melhor custo-benefício
Dia do lançamento
Melhor custo-benefício
LG AI Research · 2026-08-12Modelos com pesos para download (open weights)K-EXAONE 2.0 0803
Ainda não há dados de benchmark
Motif Technologies · 2026-08-12Modelos com pesos para download (open weights)Motif 3
Ainda não há dados de benchmark

Modelos 602, melhor valor primeiro

#ModeloCriadorPontuação de inteligência (Intelligence Index)Custo do benchmark (USD)Inteligência por dólar de benchmarkTempo total (E2E)Pesos para downloadLançadoMelhor custo-benefício
1GPT-5.6 Luna (Non-reasoning)OpenAI26.80$10.22.624.15s2026-07-09Melhor custo-benefício
2GPT-5.6 Luna (low)OpenAI33.90$13.72.475.37s2026-07-09Melhor custo-benefício
3GPT-5.6 Luna (medium)OpenAI38.90$21.11.846.41s2026-07-09Melhor custo-benefício
4MiMo-V2.5Xiaomi38.00$25.21.5147.7s2026-04-22Fronteira aberta
5Llama 4 ScoutMeta10.30$11.60.894.49s2025-04-05Fronteira aberta
6GPT-5.6 Luna (high)OpenAI47.00$55.00.8514.6s2026-07-09Melhor custo-benefício
7DeepSeek V3 (Dec '24)DeepSeek14.20$20.00.71-2024-12-26Fronteira aberta
8DeepSeek V4 Flash (Reasoning, High Effort)DeepSeek39.00$57.00.68-2026-04-24Fronteira aberta
9Gemma 4 31B (Non-reasoning)Google22.30$33.80.667.47s2026-04-02
10gpt-oss-120b (low)OpenAI14.90$24.20.6216.5s2025-08-05Fronteira aberta
11GPT-5.6 Luna (xhigh)OpenAI50.10$95.10.5349.3s2026-07-09Melhor custo-benefício
12Ling 3.0 FlashInclusionAI37.80$72.80.52-2026-08-04
13Mistral Small 3.1Mistral14.90$29.80.504.16s2025-03-17
14Gemma 4 26B A4B (Reasoning)Google26.10$53.90.48-2026-04-02
15gpt-oss-20b (high)OpenAI15.20$32.70.4619.4s2025-08-05
16Hy3Tencent42.20$93.20.4540.1s2026-07-06Fronteira aberta
17MiMo-V2.5-ProXiaomi42.90$98.90.4345.9s2026-04-22Fronteira aberta
18DeepSeek V3 0324DeepSeek15.20$35.20.43-2025-03-25
19DeepSeek V4 Flash (Reasoning, Max Effort)DeepSeek42.10$1040.40-2026-04-24
20Llama 4 MaverickMeta14.50$35.90.405.37s2025-04-05
21DeepSeek V4 Pro (Reasoning, High Effort)DeepSeek43.70$1090.4035.0s2026-04-24Fronteira aberta
22NVIDIA Nemotron 3 Nano 30B A3B (Reasoning)NVIDIA14.50$39.40.3712.0s2025-12-15
23GPT-5.6 Terra (Non-reasoning)OpenAI34.60$98.50.355.90s2026-07-09
24Muse Glimmer (high)Meta35.10$1050.3323.4s2026-08-10
25Nemotron 3.5 LightningNVIDIA23.60$71.50.339.43s2026-08-11
26GPT-5.6 Terra (low)OpenAI41.30$1300.326.86s2026-07-09
27Gemini 3.7 Flash (low)Google50.90$1650.312.48s2026-08-13Melhor custo-benefício
28GPT-5.6 Luna (max)OpenAI52.30$1720.30162.6s2026-07-09Melhor custo-benefício
29Gemini 3.1 Flash-LiteGoogle25.60$93.80.277.21s2026-03-03
30MiniMax-M2.7MiniMax38.90$1430.2750.7s2026-03-18
31GPT-4.1 nanoOpenAI9.60$36.70.264.68s2025-04-14
32DeepSeek V4 Pro (Reasoning, Max Effort)DeepSeek45.30$1760.2667.6s2026-04-24Fronteira aberta
33gpt-oss-120b (high)OpenAI24.10$95.00.2516.4s2025-08-05
34Gemini 3.5 Flash-LiteGoogle37.40$1530.2411.3s2026-07-21
35GPT-5.6 Terra (medium)OpenAI46.80$1920.247.09s2026-07-09
36GPT-4.1 miniOpenAI14.80$64.20.235.84s2025-04-14
37Mistral Small 4 (Reasoning)Mistral19.70$87.70.2216.4s2026-03-16
38Mercury 2Inception21.90$97.50.224.53s2026-02-20
39Mistral Large 3Mistral15.90$71.10.2211.6s2025-12-02
40MiniMax-M3MiniMax45.40$2050.2229.1s2026-06-01Fronteira aberta
41Inkling SmallThinking Machines41.20$1930.2139.3s2026-07-30
42Qwen3 Next 80B A3B (Reasoning)Alibaba16.90$84.00.2014.9s2025-09-11
43GPT-5 mini (high)OpenAI25.80$1300.2095.4s2025-08-07
44Gemini 3.7 Flash (medium)Google53.40$2780.196.21s2026-08-13Melhor custo-benefício
45GPT-5.6 Sol (Non-reasoning)OpenAI41.90$2400.179.66s2026-07-09
46Kimi K3 (low)Kimi48.30$2830.1771.8s2026-07-16Fronteira aberta
47GPT-5.5 (Non-reasoning)OpenAI35.80$2120.178.28s2026-04-23
48DeepSeek V4 Flash 0731 (Reasoning, Max Effort)DeepSeek51.80$3230.1625.4s2026-07-31Fronteira aberta
49GPT-5.6 Sol (low)OpenAI50.70$3440.1512.3s2026-07-09
50GPT-5.4 nano (xhigh)OpenAI39.70$2770.146.82s2026-03-17
51Grok 4.3 (high)SpaceXAI37.90$2880.1324.7s2026-04-30
52Solar Pro 4Upstage41.60$3210.1355.9s2026-08-06
53Qwen3.5 122B A10B (Non-reasoning)Alibaba28.20$2210.135.84s2026-02-24
54GPT-5.6 Terra (high)OpenAI50.10$3950.137.61s2026-07-09
55Gemini 3.6 Flash (high)Google51.60$4120.1321.0s2026-07-21
56Grok 4.3 (Non-reasoning)SpaceXAI25.00$2010.125.95s2026-04-30
57Qwen3.7 PlusAlibaba39.40$3220.1246.4s2026-06-01
58GPT-5.5 (low)OpenAI44.50$3740.128.81s2026-04-23
59Kimi K2.5 (Reasoning)Kimi36.00$3040.1283.4s2026-01-27
60Qwen3 235B A22B 2507 (Reasoning)Alibaba19.90$1700.1241.6s2025-07-25
61Gemini 3.7 Flash (high)Google56.00$4850.1216.7s2026-08-13Melhor custo-benefício
62Mistral Medium 3.1Mistral14.70$1340.116.17s2025-08-12
63Grok Build 0.1 0616SpaceXAI40.70$3770.1146.1s2026-06-16
64Qwen3.5 35B A3B (Non-reasoning)Alibaba24.30$2280.115.08s2026-02-24
65Claude Sonnet 5 (Non-reasoning, High Effort)Anthropic42.60$4160.1010.1s2026-06-30
66Nemotron 3 Super 120B A12B (Reasoning)NVIDIA25.70$2540.1021.4s2026-03-11
67Muse Spark 1.1 (xhigh)Meta53.20$5470.1014.0s2026-07-09
68Step 3.7 FlashStepFun30.90$3200.1024.1s2026-05-29
69Grok 4.5 (high)SpaceXAI55.80$5790.1024.1s2026-07-08
70Qwen3 30B A3B 2507 (Reasoning)Alibaba14.60$1520.1020.5s2025-07-30
71GPT-5.6 Sol (medium)OpenAI55.60$5800.1012.6s2026-07-09
72Claude Opus 5 (Adaptive Reasoning, Low Effort)Anthropic52.50$5550.0913.7s2026-07-24
73Ministral 3 14BMistral11.20$1190.096.18s2025-12-02
74GLM-4.6 (Reasoning)Z AI29.30$3140.0952.7s2025-09-30
75Solar Pro 3Upstage14.50$1580.0918.9s2026-04-06
76Qwen3.5 9B (Reasoning)Alibaba21.80$2400.0933.0s2026-03-02
77GPT-5.6 Terra (xhigh)OpenAI52.80$5900.0931.9s2026-07-09
78Muse Spark 1.2 (xhigh)Meta56.80$6390.09-2026-08-05Melhor custo-benefício
79DeepSeek V4 Pro 0813 (Reasoning, Max Effort)DeepSeek53.20$6050.0935.2s2026-08-13Fronteira aberta
80Qwen3.6 27B (Non-reasoning)Alibaba31.30$3590.0912.7s2026-04-22
81Qwen3 Coder NextAlibaba21.30$2500.094.97s2026-02-03
82Mistral Small 3.2Mistral10.70$1290.084.18s2025-06-20
83Celeris-1Celeris12.40$1570.080.95s2026-07-24
84Kimi K2.7 CodeKimi43.00$5450.0875.9s2026-06-12
85Ministral 3 8BMistral9.00$1140.084.90s2025-12-02
86Ministral 3 3BMistral7.10$91.60.083.10s2025-12-02
87Qwen3.6 PlusAlibaba40.50$5260.08109.5s2026-04-02
88LongCat 2.0LongCat34.00$4420.0866.4s2026-06-29
89Qwen3.5 122B A10B (Reasoning)Alibaba32.80$4440.0721.5s2026-02-24
90Trinity Large ThinkingArcee AI18.70$2550.0714.1s2026-04-01
91Nemotron 3 Ultra 550B A55B (Reasoning)NVIDIA38.30$5340.0723.1s2026-06-04
92Ring-2.6-1TInclusionAI31.70$4550.07-2026-05-08
93GPT-5.5 Instant (June 2026)OpenAI29.20$4230.0722.4s2026-06-25
94Qwen3.5 397B A17B (Reasoning)Alibaba34.30$5270.0744.0s2026-02-16
95Qwen3.6 35B A3B (Reasoning)Alibaba32.10$5050.0652.0s2026-04-16
96Claude 4.5 Haiku (Reasoning)Anthropic29.90$4710.0622.3s2025-10-15
97GLM-5.2 (max)Z AI52.60$8430.0623.8s2026-06-16
98Inkling (xhigh)Thinking Machines42.30$6980.0635.5s2026-07-15
99GPT-5.6 Sol (high)OpenAI57.30$9550.0624.0s2026-07-09Melhor custo-benefício
100Gemini 3.1 Pro PreviewGoogle47.70$8120.0637.1s2026-02-19
101GLM-5.1 (Reasoning)Z AI41.00$7000.0653.4s2026-04-07
102Grok 4.6 (high)SpaceXAI60.90$10680.0645.7s2026-08-12Melhor custo-benefício
103GLM-4.7 (Reasoning)Z AI34.50$6070.0624.4s2025-12-22
104Qwen3.6 27B (Reasoning)Alibaba37.70$6670.06115.6s2026-04-22
105GPT-5.5 (medium)OpenAI51.40$9390.0513.2s2026-04-23
106Kimi K2.6Kimi45.10$8410.05111.1s2026-04-20
107Claude Opus 5 (Adaptive Reasoning, Medium Effort)Anthropic58.60$11160.0516.1s2026-07-24
108Gemini 3.5 Flash (high)Google52.00$10420.0530.2s2026-05-19
109GLM-5.3 (max)Z AI59.50$12390.0531.4s2026-08-18
110GPT-5.1 (high)OpenAI37.50$7820.0532.9s2025-11-13
111Qwen3.6 35B A3B (Non-reasoning)Alibaba24.60$5300.055.83s2026-04-16
112GPT-5 (high)OpenAI35.30$7890.04105.0s2025-08-07
113DeepSeek R1 (Jan '25)DeepSeek18.60$4170.04-2025-01-20
114Qwen3.7 MaxAlibaba46.70$10640.0416.7s2026-05-19
115Gemini 2.5 ProGoogle25.90$6110.0424.2s2025-06-05
116GPT-5.6 Terra (max)OpenAI56.60$13900.04190.9s2026-07-09
117GPT-5.6 Sol (xhigh)OpenAI59.00$15250.0458.8s2026-07-09
118Magistral Small 1.2Mistral11.50$3010.0418.3s2025-09-17
119GPT-5.4 mini (xhigh)OpenAI40.90$10960.0415.0s2026-03-17
120Claude 4.5 Sonnet (Reasoning)Anthropic37.40$10370.0424.8s2025-09-29
121Qwen3.8 2.4T A95BAlibaba57.70$16720.0356.8s2026-08-12Fronteira aberta
122Mistral Medium 3.5Mistral30.40$8830.0321.2s2026-04-29
123Qwen3.8 MaxAlibaba58.10$17410.0358.8s2026-08-03
124GPT-5.5 (high)OpenAI54.70$17210.0330.5s2026-04-23
125Claude Opus 5 (Adaptive Reasoning, High Effort)Anthropic61.50$19740.0330.3s2026-07-24Melhor custo-benefício
126Kimi K3 (max)Kimi59.70$24250.0268.9s2026-07-16Fronteira aberta
127GPT-5.4 (xhigh)OpenAI53.10$21830.02147.9s2026-03-05
128GPT-5.6 Sol (max)OpenAI60.90$28230.02216.4s2026-07-09
129Claude Opus 5 (Adaptive Reasoning, Xhigh Effort)Anthropic62.50$29090.0249.8s2026-07-24Melhor custo-benefício
130GPT-5.5 (xhigh)OpenAI56.30$27780.0274.7s2026-04-23
131Magistral Medium 1.2Mistral18.00$9200.0222.0s2025-09-18
132Claude Opus 5 (Adaptive Reasoning, Max Effort)Anthropic63.10$38360.0269.4s2026-07-24Melhor custo-benefício
133Claude Opus 4.8 (Adaptive Reasoning, Max Effort)Anthropic57.30$37520.0231.5s2026-05-28
134Claude Opus 4.7 (Adaptive Reasoning, Max Effort)Anthropic55.00$37430.0126.1s2026-04-16
135Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)Anthropic48.40$33550.01158.4s2026-02-17
136Claude Sonnet 5 (Adaptive Reasoning, Max Effort)Anthropic55.30$40110.01191.1s2026-06-30
137Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)Anthropic62.10$54550.01155.6s2026-06-09
138A.X-K2SK Telecom35.00---2026-08-12
139Agnes 2.5 Pro AlphaSapiens AI39.70--21.0s2026-07-24
140Apertus 70B InstructSwiss AI Initiative2.00---2025-09-02
141Apertus 8B InstructSwiss AI Initiative1.00---2025-09-02
142Apriel-v1.5-15B-ThinkerServiceNow21.60---2025-09-30
143Apriel-v1.6-15B-ThinkerServiceNow20.80---2025-11-25
144Arctic InstructSnowflake3.00---2024-04-24
145Claude 2.0Anthropic3.30---2023-07-11
146Claude 2.1Anthropic3.50---2023-11-21
147Claude 3 HaikuAnthropic3.50---2024-03-04
148Claude 3 OpusAnthropic11.80---2024-03-04
149Claude 3 SonnetAnthropic4.40---2024-03-04
150Claude 3.5 HaikuAnthropic12.20---2024-10-22
151Claude 3.5 Sonnet (June '24)Anthropic8.10---2024-06-21
152Claude 3.5 Sonnet (Oct '24)Anthropic9.80---2024-10-22
153Claude 3.7 Sonnet (Non-reasoning)Anthropic23.90---2025-02-24
154Claude 3.7 Sonnet (Reasoning)Anthropic27.60---2025-02-24
155Claude 4 Opus (Non-reasoning)Anthropic26.00---2025-05-22
156Claude 4 Opus (Reasoning)Anthropic31.70---2025-05-22
157Claude 4 Sonnet (Non-reasoning)Anthropic26.00---2025-05-22
158Claude 4 Sonnet (Reasoning)Anthropic29.80---2025-05-22
159Claude 4.1 Opus (Non-reasoning)Anthropic28.80---2025-08-05
160Claude 4.1 Opus (Reasoning)Anthropic34.50---2025-08-05
161Claude 4.5 Haiku (Non-reasoning)Anthropic24.10--6.59s2025-10-15
162Claude 4.5 Sonnet (Non-reasoning)Anthropic29.90--14.3s2025-09-29
163Claude InstantAnthropic1.70---2023-03-14
164Claude Opus 4.5 (Non-reasoning)Anthropic35.60--12.7s2025-11-24
165Claude Opus 4.5 (Reasoning)Anthropic41.90--22.2s2025-11-24
166Claude Opus 4.6 (Adaptive Reasoning, Max Effort)Anthropic44.90--28.3s2026-02-05
167Claude Opus 4.6 (Non-reasoning, High Effort)Anthropic38.80--16.1s2026-02-05
168Claude Opus 4.7 (Non-reasoning, High Effort)Anthropic43.90--12.7s2026-04-16
169Claude Sonnet 4.6 (Non-reasoning, High Effort)Anthropic36.80--12.9s2026-02-17
170Claude Sonnet 4.6 (Non-reasoning, Low Effort)Anthropic35.10--13.0s2026-02-17
171Claude Sonnet 5 (Adaptive Reasoning, High Effort)Anthropic---19.8s2026-06-30
172Claude Sonnet 5 (Adaptive Reasoning, Low Effort)Anthropic---10.7s2026-06-30
173Claude Sonnet 5 (Adaptive Reasoning, Medium Effort)Anthropic---11.5s2026-06-30
174Claude Sonnet 5 (Adaptive Reasoning, Xhigh Effort)Anthropic---42.7s2026-06-30
175Cogito v2.1 (Reasoning)Deep Cogito----2025-11-18
176Command ACohere7.50--10.1s2025-03-13
177Command-R (Mar '24)Cohere1.70---2024-03-12
178Command-R+ (Apr '24)Cohere2.60---2024-04-04
179DBRX InstructDatabricks2.60---2024-03-27
180DeepHermes 3 - Llama-3.1 8B Preview (Non-reasoning)Nous Research1.90---2025-02-13
181DeepHermes 3 - Mistral 24B Preview (Non-reasoning)Nous Research5.00---2025-03-13
182DeepSeek Coder V2 Lite InstructDeepSeek2.70---2024-06-17
183DeepSeek LLM 67B Chat (V1)DeepSeek2.60---2023-11-29
184DeepSeek R1 0528 (May '25)DeepSeek20.40---2025-05-28
185DeepSeek R1 0528 Qwen3 8BDeepSeek10.30---2025-05-29
186DeepSeek R1 Distill Llama 70BDeepSeek9.80--100.1s2025-01-20
187DeepSeek R1 Distill Llama 8BDeepSeek6.20---2025-01-20
188DeepSeek R1 Distill Qwen 1.5BDeepSeek3.30---2025-01-20
189DeepSeek R1 Distill Qwen 14BDeepSeek9.70---2025-01-20
190DeepSeek R1 Distill Qwen 32BDeepSeek11.00---2025-01-20
191DeepSeek V3.1 (Non-reasoning)DeepSeek21.40---2025-08-21
192DeepSeek V3.1 (Reasoning)DeepSeek21.00---2025-08-21
193DeepSeek V3.1 Terminus (Non-reasoning)DeepSeek21.70---2025-09-22
194DeepSeek V3.1 Terminus (Reasoning)DeepSeek31.40---2025-09-22
195DeepSeek V3.2 (Non-reasoning)DeepSeek25.10---2025-12-01
196DeepSeek V3.2 (Reasoning)DeepSeek32.80---2025-12-01
197DeepSeek V3.2 Exp (Non-reasoning)DeepSeek21.70---2025-09-29
198DeepSeek V3.2 Exp (Reasoning)DeepSeek25.90---2025-09-29
199DeepSeek V3.2 SpecialeDeepSeek22.60---2025-12-01
200DeepSeek V4 Flash (Non-reasoning)DeepSeek29.30---2026-04-24
201DeepSeek V4 Pro (Non-reasoning)DeepSeek31.90--8.37s2026-04-24
202DeepSeek-Coder-V2DeepSeek4.70---2024-06-17
203DeepSeek-V2-ChatDeepSeek3.30---2024-05-06
204DeepSeek-V2.5DeepSeek6.40---2024-09-06
205DeepSeek-V2.5 (Dec '24)DeepSeek6.50---2024-12-10
206Devstral MediumMistral12.40---2025-07-10
207Devstral Small (Jul '25)Mistral9.10---2025-07-10
208Devstral Small (May '25)Mistral11.80---2025-05-21
209DiffusionGemma 26B A4BGoogle13.50---2026-06-10
210Doubao Seed CodeByteDance Seed26.50---2025-11-11
211ERNIE 4.5 300B A47BBaidu8.90---2025-06-30
212ERNIE 5.0 Thinking PreviewBaidu22.30---2025-11-13
213Exaone 4.0 1.2B (Non-reasoning)LG AI Research2.40---2025-07-15
214Exaone 4.0 1.2B (Reasoning)LG AI Research2.50---2025-07-15
215EXAONE 4.0 32B (Non-reasoning)LG AI Research5.70---2025-07-15
216EXAONE 4.0 32B (Reasoning)LG AI Research10.50---2025-07-15
217EXAONE 4.5 33BLG AI Research20.50---2026-04-09
218EXAONE 4.5 33B (Non-reasoning)LG AI Research----2026-04-09
219Falcon-H1R-7BTII UAE9.70---2026-01-04
220G9v3-39A5BAI9Stars31.60---2026-08-03
221G9v3-3BAI9Stars16.20---2026-07-23
222Gemini 1.0 ProGoogle2.70---2023-12-06
223Gemini 1.0 UltraGoogle4.30---2023-12-06
224Gemini 1.5 Flash (May '24)Google4.60---2024-05-14
225Gemini 1.5 Flash (Sep '24)Google7.80---2024-09-24
226Gemini 1.5 Flash-8BGoogle5.20---2024-10-03
227Gemini 1.5 Pro (May '24)Google6.10---2024-05-15
228Gemini 1.5 Pro (Sep '24)Google9.90---2024-09-24
229Gemini 2.0 Flash (experimental)Google10.60---2024-12-11
230Gemini 2.0 Flash (Feb '25)Google12.20---2025-02-05
231Gemini 2.0 Flash Thinking Experimental (Dec '24)Google6.40---2024-12-19
232Gemini 2.0 Flash Thinking Experimental (Jan '25)Google13.30---2025-01-21
233Gemini 2.0 Flash-Lite (Feb '25)Google8.60---2025-02-25
234Gemini 2.0 Flash-Lite (Preview)Google8.40---2025-02-05
235Gemini 2.0 Pro Experimental (Feb '25)Google11.80---2025-02-05
236Gemini 2.5 Flash (Non-reasoning)Google14.20--2.96s2025-05-20
237Gemini 2.5 Flash (Reasoning)Google20.30--21.3s2025-05-20
238Gemini 2.5 Flash Preview (Non-reasoning)Google11.60---2025-04-17
239Gemini 2.5 Flash Preview (Reasoning)Google17.70---2025-04-17
240Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning)Google19.10---2025-09-25
241Gemini 2.5 Flash Preview (Sep '25) (Reasoning)Google24.20---2025-09-25
242Gemini 2.5 Flash-Lite (Non-reasoning)Google6.70--2.47s2025-06-17
243Gemini 2.5 Flash-Lite (Reasoning)Google11.40--26.2s2025-06-17
244Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)Google13.10---2025-09-25
245Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning)Google15.20---2025-09-08
246Gemini 2.5 Pro Preview (Mar' 25)Google23.40---2025-03-25
247Gemini 2.5 Pro Preview (May' 25)Google22.70---2025-05-06
248Gemini 3 Deep ThinkGoogle----2026-02-05
249Gemini 3 Flash Preview (Non-reasoning)Google27.90--3.70s2025-12-17
250Gemini 3 Flash Preview (Reasoning)Google38.70--9.32s2025-12-17
251Gemini 3 Pro Preview (high)Google40.60---2025-11-18
252Gemini 3 Pro Preview (low)Google33.90---2025-11-18
253Gemini 3.5 Flash (medium)Google46.70--23.5s2026-05-19
254Gemini 3.5 Flash (minimal)Google35.80--4.06s2026-05-19
255Gemma 3 1B InstructGoogle1.00---2025-03-13
256Gemma 3 270MGoogle2.00---2025-08-14
257Gemma 3 4B InstructGoogle1.00---2025-03-12
258Gemma 3n E2B InstructGoogle1.00---2025-06-26
259Gemma 3n E4B InstructGoogle1.00--10.5s2025-06-26
260Gemma 3n E4B Instruct Preview (May '25)Google4.20---2025-05-20
261Gemma 4 12B (Non-reasoning)Google13.20--6.70s2026-06-03
262Gemma 4 12B (Reasoning)Google22.20--25.2s2026-06-03
263Gemma 4 26B A4B (Non-reasoning)Google20.40--7.77s2026-04-02
264Gemma 4 E2B (Non-reasoning)Google6.20---2026-04-02
265Gemma 4 E2B (Reasoning)Google9.50---2026-04-02
266Gemma 4 E4B (Non-reasoning)Google8.70--10.6s2026-04-03
267Gemma 4 E4B (Reasoning)Google12.20--46.8s2026-04-03
268GLM 5V Turbo (Reasoning)Z AI35.30---2026-04-01
269GLM-4.5 (Reasoning)Z AI19.70---2025-07-28
270GLM-4.5-AirZ AI16.70--34.9s2025-07-28
271GLM-4.5V (Non-reasoning)Z AI6.80--7.26s2025-08-11
272GLM-4.5V (Reasoning)Z AI9.00--31.7s2025-08-11
273GLM-4.6 (Non-reasoning)Z AI23.40--11.8s2025-09-30
274GLM-4.6V (Non-reasoning)Z AI10.90--10.6s2025-12-08
275GLM-4.6V (Reasoning)Z AI16.90--39.1s2025-12-08
276GLM-4.7 (Non-reasoning)Z AI27.10--5.90s2025-12-22
277GLM-4.7-Flash (Non-reasoning)Z AI15.60--6.34s2026-01-19
278GLM-4.7-Flash (Reasoning)Z AI23.30--28.0s2026-01-19
279GLM-5 (Non-reasoning)Z AI33.20--14.2s2026-02-11
280GLM-5 (Reasoning)Z AI40.60--80.3s2026-02-11
281GLM-5-TurboZ AI39.10---2026-03-15
282GLM-5.1 (Non-reasoning)Z AI36.30--9.83s2026-04-07
283GLM-5.2 (Non-reasoning)Z AI34.80--5.71s2026-06-16
284GPT-3.5 TurboOpenAI3.20---2022-11-30
285GPT-3.5 Turbo (0613)OpenAI----2023-06-13
286GPT-4OpenAI6.80---2023-03-14
287GPT-4 TurboOpenAI7.70--18.3s2023-11-06
288GPT-4.1OpenAI19.60--4.40s2025-04-14
289GPT-4.5 (Preview)OpenAI13.60---2025-02-27
290GPT-4o (Aug '24)OpenAI9.40--6.74s2024-08-06
291GPT-4o (ChatGPT)OpenAI8.10---2025-02-15
292GPT-4o (March 2025, chatgpt-4o-latest)OpenAI12.30---2025-03-27
293GPT-4o (May '24)OpenAI8.40--6.73s2024-05-13
294GPT-4o (Nov '24)OpenAI11.10--4.81s2024-11-20
295GPT-4o miniOpenAI6.70--5.96s2024-07-18
296GPT-4o mini Realtime (Dec '24)OpenAI----2024-12-17
297GPT-4o Realtime (Dec '24)OpenAI----2024-12-17
298GPT-5 (ChatGPT)OpenAI15.40---2025-08-07
299GPT-5 (low)OpenAI31.90--18.3s2025-08-07
300GPT-5 (medium)OpenAI34.60--42.9s2025-08-07
301GPT-5 (minimal)OpenAI17.30--7.78s2025-08-07
302GPT-5 Codex (high)OpenAI37.00---2025-09-23
303GPT-5 mini (medium)OpenAI31.60--18.8s2025-08-07
304GPT-5 mini (minimal)OpenAI14.30--6.24s2025-08-07
305GPT-5 nano (high)OpenAI20.10--97.3s2025-08-07
306GPT-5 nano (medium)OpenAI19.20--50.0s2025-08-07
307GPT-5 nano (minimal)OpenAI7.80--3.96s2025-08-07
308GPT-5.1 (Non-reasoning)OpenAI20.70--6.18s2025-11-13
309GPT-5.1 Codex (high)OpenAI35.60---2025-11-13
310GPT-5.1 Codex mini (high)OpenAI31.30---2025-11-13
311GPT-5.2 (medium)OpenAI38.90---2025-12-11
312GPT-5.2 (Non-reasoning)OpenAI26.50--8.39s2025-12-11
313GPT-5.2 (xhigh)OpenAI43.30--149.3s2025-12-11
314GPT-5.2 Codex (xhigh)OpenAI41.20---2025-12-11
315GPT-5.3 Codex (xhigh)OpenAI45.50--78.6s2026-02-05
316GPT-5.4 (low)OpenAI40.20--7.04s2026-03-05
317GPT-5.4 (Non-reasoning)OpenAI28.30--6.35s2026-03-05
318GPT-5.4 mini (medium)OpenAI30.50--11.3s2026-03-17
319GPT-5.4 mini (Non-Reasoning)OpenAI16.80--3.80s2026-03-17
320GPT-5.4 nano (medium)OpenAI30.80--7.15s2026-03-17
321GPT-5.4 nano (Non-Reasoning)OpenAI17.80--3.61s2026-03-17
322GPT-5.4 Pro (xhigh)OpenAI----2026-03-05
323GPT-5.5 Instant (May 2026)OpenAI34.30---2026-05-05
324GPT-5.5 Pro (xhigh)OpenAI----2026-04-23
325gpt-oss-20b (low)OpenAI14.40--15.8s2025-08-05
326Granite 3.3 8B (Non-reasoning)IBM1.30--63.2s2025-04-16
327Granite 4.0 1BIBM1.60---2025-10-28
328Granite 4.0 350MIBM1.00---2025-10-28
329Granite 4.0 H 1BIBM2.20---2025-10-28
330Granite 4.0 H 350MIBM1.00---2025-10-28
331Granite 4.0 H SmallIBM4.90--38.9s2025-09-22
332Granite 4.0 MicroIBM2.00---2025-09-22
333Granite 4.1 30BIBM8.70---2026-04-29
334Granite 4.1 3BIBM4.40---2026-04-29
335Granite 4.1 8BIBM6.40--5.11s2026-04-29
336Grok 2 (Dec '24)SpaceXAI7.80---2024-12-12
337Grok 3SpaceXAI18.60---2025-02-19
338Grok 3 mini Reasoning (high)SpaceXAI22.90--35.5s2025-02-19
339Grok 3 Reasoning BetaSpaceXAI15.20---2025-02-19
340Grok 4SpaceXAI34.10---2025-07-10
341Grok 4 Fast (Non-reasoning)SpaceXAI16.60---2025-09-19
342Grok 4 Fast (Reasoning)SpaceXAI27.90---2025-09-19
343Grok 4.1 Fast (Non-reasoning)SpaceXAI17.00---2025-11-19
344Grok 4.1 Fast (Reasoning)SpaceXAI31.30---2025-11-19
345Grok 4.20 0309 (Non-reasoning)SpaceXAI22.90---2026-03-10
346Grok 4.20 0309 (Reasoning)SpaceXAI37.40---2026-03-10
347Grok 4.20 0309 v2 (Non-reasoning)SpaceXAI22.20--6.50s2026-04-07
348Grok 4.20 0309 v2 (Reasoning)SpaceXAI38.00--27.4s2026-04-07
349Grok 4.3 (low)SpaceXAI36.30--11.6s2026-04-30
350Grok 4.3 (medium)SpaceXAI36.90--17.9s2026-04-30
351Grok BetaSpaceXAI7.30---2024-08-13
352Grok Code Fast 1SpaceXAI22.00---2025-08-28
353Grok-1SpaceXAI5.80---2024-03-17
354Hermes 3 - Llama-3.1 70BNous Research4.80--16.6s2024-08-15
355Hermes 4 - Llama-3.1 405B (Non-reasoning)Nous Research8.60--25.6s2025-08-27
356Hermes 4 - Llama-3.1 405B (Reasoning)Nous Research8.80--86.2s2025-08-27
357Hermes 4 - Llama-3.1 70B (Non-reasoning)Nous Research6.70--10.4s2025-08-27
358Hermes 4 - Llama-3.1 70B (Reasoning)Nous Research9.90--35.4s2025-08-27
359Hy3-preview (Non-reasoning)Tencent26.60---2026-04-23
360Hy3-preview (Reasoning)Tencent34.40---2026-04-23
361HyperCLOVA X SEED Think (32B)Naver17.20---2025-12-26
362HyperNova 60B 2605Multiverse Computing18.30---2026-05-26
363INTELLECT-3Prime Intellect15.70---2025-11-27
364Jamba 1.5 LargeAI21 Labs4.80---2024-08-22
365Jamba 1.5 MiniAI21 Labs2.30---2024-08-22
366Jamba 1.6 LargeAI21 Labs4.70---2025-03-06
367Jamba 1.6 MiniAI21 Labs2.10---2025-03-06
368Jamba 1.7 LargeAI21 Labs5.00---2025-07-07
369Jamba 1.7 MiniAI21 Labs2.30---2025-07-07
370Jamba Reasoning 3BAI21 Labs3.80---2025-10-08
371JT-35B-FlashChina Mobile29.00---2026-05-14
372JT-4.1 Flash 236B A21BChina Mobile39.90---2026-07-09
373JT-MINIChina Mobile18.80---2026-04-15
374K-EXAONE (Non-reasoning)LG AI Research16.90---2025-12-31
375K-EXAONE (Reasoning)LG AI Research22.50---2025-12-31
376K-EXAONE 2.0 0803LG AI Research31.00---2026-08-12
377K2 Think V2MBZUAI Institute de Foundation Models17.40---2025-12-15
378K2-V2 (high)MBZUAI Institute de Foundation Models14.20---2025-12-05
379K2-V2 (low)MBZUAI Institute de Foundation Models8.40---2025-12-05
380K2-V2 (medium)MBZUAI Institute de Foundation Models12.40---2025-12-05
381KAT Coder Pro V2KwaiKAT33.70--6.04s2026-03-27
382KAT-Coder-Pro V1KwaiKAT28.90---2025-11-11
383Kimi K2Kimi19.70--13.4s2025-07-11
384Kimi K2 0905Kimi24.00--13.4s2025-09-05
385Kimi K2 ThinkingKimi33.50--22.0s2025-11-06
386Kimi K2.5 (Non-reasoning)Kimi30.10--14.0s2026-01-27
387Kimi K2.6 (Non-reasoning)Kimi35.40--15.3s2026-04-20
388Kimi Linear 48B A3B InstructKimi8.40---2025-10-30
389LFM 40BLiquid AI3.00---2024-09-30
390LFM2 1.2BLiquid AI1.00---2025-07-10
391LFM2 2.6BLiquid AI2.30---2025-09-23
392LFM2 24B A2BLiquid AI4.60---2026-02-25
393LFM2 8B A1BLiquid AI1.30---2025-10-07
394LFM2.5-1.2B-InstructLiquid AI2.30---2026-01-05
395LFM2.5-1.2B-ThinkingLiquid AI2.30---2026-01-20
396LFM2.5-8B-A1BLiquid AI8.10--9.34s2026-05-28
397LFM2.5-VL-1.6BLiquid AI1.00--4.20s2026-01-05
398Ling 2.6 FlashInclusionAI14.20--6.59s2026-04-21
399Ling-1TInclusionAI12.70---2025-10-08
400Ling-2.6-1TInclusionAI26.60---2026-04-23
401Ling-flash-2.0InclusionAI9.60--8.21s2025-09-17
402Ling-mini-2.0InclusionAI3.40---2025-09-09
403Llama 2 Chat 13BMeta2.60---2023-07-18
404Llama 2 Chat 70BMeta2.60---2023-07-18
405Llama 2 Chat 7BMeta3.90---2023-07-18
406Llama 3 Instruct 70BMeta3.10---2024-04-18
407Llama 3 Instruct 8BMeta1.00---2024-04-18
408Llama 3.1 Instruct 405BMeta8.30---2024-07-23
409Llama 3.1 Instruct 70BMeta6.50--10.4s2024-07-23
410Llama 3.1 Instruct 8BMeta7.40--4.58s2024-07-23
411Llama 3.1 Nemotron Instruct 70BNVIDIA7.40--10.0s2024-10-15
412Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)NVIDIA8.40---2025-05-20
413Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)NVIDIA8.90--54.4s2025-04-07
414Llama 3.1 Tulu3 405BAllen Institute for AI8.10---2025-01-30
415Llama 3.2 Instruct 11B (Vision)Meta3.00--11.7s2024-09-25
416Llama 3.2 Instruct 1BMeta1.00---2024-09-25
417Llama 3.2 Instruct 3BMeta3.90---2024-09-25
418Llama 3.2 Instruct 90B (Vision)Meta6.00---2024-09-25
419Llama 3.3 Instruct 70BMeta9.30--7.32s2024-12-06
420Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)NVIDIA8.30---2025-03-18
421Llama 3.3 Nemotron Super 49B v1 (Reasoning)NVIDIA12.20---2025-03-18
422Llama 65BMeta1.70---2023-02-24
423Llama Nemotron Super 49B v1.5 (Non-reasoning)NVIDIA8.50--12.5s2025-07-25
424Llama Nemotron Super 49B v1.5 (Reasoning)NVIDIA12.40--27.9s2025-07-25
425LongCat Flash LiteLongCat17.40---2026-01-28
426Magistral Medium 1Mistral12.50---2025-06-10
427Magistral Small 1Mistral10.60---2025-06-10
428Mi:dm K 2.5 ProKorea Telecom16.60---2025-12-11
429Mi:dm K 2.5 Pro PreviewKorea Telecom----2025-12-11
430MiMo-V2-Flash (Feb 2026)Xiaomi34.00---2025-12-16
431MiMo-V2-Flash (Non-reasoning)Xiaomi25.10---2025-12-16
432MiMo-V2-Flash (Reasoning)Xiaomi31.90---2025-12-16
433MiMo-V2-OmniXiaomi35.90---2026-03-19
434MiMo-V2-Omni-0327Xiaomi37.30---2026-03-27
435MiMo-V2-ProXiaomi41.40---2026-03-18
436MiMo-V2.5-Pro (Non-reasoning)Xiaomi28.40--11.8s2026-04-22
437MiniCPM-V 4.6 1.3BOpenBMB3.80---2026-05-11
438MiniCPM5-1B (Non-reasoning)OpenBMB11.70---2026-05-25
439MiniCPM5-1B (Reasoning)OpenBMB11.90---2026-05-25
440MiniMax M1 40kMiniMax14.50---2025-06-17
441MiniMax M1 80kMiniMax17.90---2025-06-17
442MiniMax-M2MiniMax28.90--29.7s2025-10-26
443MiniMax-M2.1MiniMax32.10--30.2s2025-12-23
444MiniMax-M2.5MiniMax34.50--28.1s2026-02-12
445Mistral 7B InstructMistral1.70--4.87s2023-09-27
446Mistral Large (Feb '24)Mistral4.10---2024-02-26
447Mistral Large 2 (Jul '24)Mistral7.00---2024-07-24
448Mistral Large 2 (Nov '24)Mistral9.00---2024-11-18
449Mistral MediumMistral3.20--5.95s2023-12-11
450Mistral Medium 3Mistral12.50--10.3s2025-05-07
451Mistral SabaMistral6.20---2025-02-17
452Mistral Small (Feb '24)Mistral3.20--4.12s2024-02-26
453Mistral Small (Sep '24)Mistral4.30--4.08s2024-09-17
454Mistral Small 3Mistral6.70--4.31s2025-01-30
455Mistral Small 4 (Non-reasoning)Mistral12.30--4.46s2026-03-16
456Mixtral 8x22B InstructMistral4.00---2024-04-17
457Mixtral 8x7B InstructMistral2.00---2023-12-11
458Molmo 7B-DAllen Institute for AI3.40---2024-09-25
459Molmo2-8BAllen Institute for AI1.60---2025-12-11
460Motif 3Motif Technologies47.40---2026-08-12
461Motif 3 (Beta)Motif Technologies45.30---2026-07-14
462Motif-2-12.7B-ReasoningMotif Technologies12.80---2025-12-04
463Muse SparkMeta44.30---2026-04-08
464Nanbeige4.1-3BNanbeige11.00---2026-02-11
465Nemotron 3 Nano Omni 30B A3B ReasoningNVIDIA15.00--8.76s2026-04-29
466Nemotron Cascade 2 30B A3BNVIDIA17.80---2026-03-19
467Nex-N2-ProNex AGI41.70--19.7s2026-06-02
468Nova 2.0 Lite (high)Amazon20.80--28.6s2025-10-29
469Nova 2.0 Lite (low)Amazon18.00--22.9s2025-10-29
470Nova 2.0 Lite (medium)Amazon19.20--34.6s2025-10-29
471Nova 2.0 Lite (Non-reasoning)Amazon11.80--4.34s2025-10-29
472Nova 2.0 Omni (low)Amazon16.70---2025-11-26
473Nova 2.0 Omni (medium)Amazon21.30---2025-11-26
474Nova 2.0 Omni (Non-reasoning)Amazon10.40---2025-11-26
475Nova 2.0 Pro Preview (low)Amazon19.80--32.4s2025-11-27
476Nova 2.0 Pro Preview (medium)Amazon22.10--34.7s2025-11-27
477Nova 2.0 Pro Preview (Non-reasoning)Amazon14.40--6.19s2025-11-27
478Nova LiteAmazon6.70--4.16s2024-12-03
479Nova MicroAmazon4.40--2.64s2024-12-03
480Nova PremierAmazon12.70--18.0s2025-04-30
481Nova ProAmazon7.50---2024-12-03
482NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)NVIDIA7.20--3.12s2025-12-15
483NVIDIA Nemotron 3 Nano 4BNVIDIA8.60---2026-03-16
484NVIDIA Nemotron Nano 12B v2 VL (Non-reasoning)NVIDIA4.20--4.80s2025-10-28
485NVIDIA Nemotron Nano 12B v2 VL (Reasoning)NVIDIA8.80--30.6s2025-10-28
486NVIDIA Nemotron Nano 9B V2 (Non-reasoning)NVIDIA7.20--4.32s2025-08-18
487NVIDIA Nemotron Nano 9B V2 (Reasoning)NVIDIA8.70--17.5s2025-08-18
488o1OpenAI23.90---2024-12-05
489o1-miniOpenAI14.00---2024-09-12
490o1-previewOpenAI17.20---2024-09-12
491o1-proOpenAI19.10---2025-03-19
492o3OpenAI31.10--12.8s2025-04-16
493o3-miniOpenAI19.20--8.72s2025-01-31
494o3-mini (high)OpenAI15.70--23.2s2025-01-31
495o3-proOpenAI33.30---2025-06-10
496o4-mini (high)OpenAI26.10--32.7s2025-04-16
497OLMo 2 32BAllen Institute for AI4.70---2025-03-13
498OLMo 2 7BAllen Institute for AI3.50---2024-11-26
499Olmo 3 32B ThinkAllen Institute for AI6.10---2025-11-20
500Olmo 3 7B InstructAllen Institute for AI2.40---2025-11-20
501Olmo 3 7B ThinkAllen Institute for AI3.60---2025-11-20
502Olmo 3.1 32B InstructAllen Institute for AI6.20---2026-01-13
503Olmo 3.1 32B ThinkAllen Institute for AI7.90---2025-12-12
504OpenChat 3.5 (1210)OpenChat2.60---2023-12-18
505PALM-2Google2.80---2023-05-10
506Phi-3 Mini Instruct 3.8BMicrosoft4.30---2024-04-23
507Phi-4Microsoft4.60--15.4s2024-12-12
508Phi-4 Mini InstructMicrosoft5.70--12.3s2024-02-26
509Phi-4 Multimodal InstructMicrosoft4.20--29.5s2025-02-26
510Pixtral LargeMistral8.00---2024-11-18
511Qwen Chat 14BAlibaba1.70---2023-09-25
512Qwen Chat 72BAlibaba3.00---2023-11-30
513Qwen1.5 Chat 110BAlibaba3.70---2024-04-25
514Qwen2 Instruct 72BAlibaba5.70---2024-06-07
515Qwen2.5 Coder Instruct 32BAlibaba6.90---2024-11-11
516Qwen2.5 Coder Instruct 7B Alibaba4.10---2024-09-19
517Qwen2.5 Instruct 32BAlibaba7.20---2024-09-19
518Qwen2.5 Instruct 72BAlibaba9.40---2024-09-19
519Qwen2.5 MaxAlibaba10.10---2025-01-28
520Qwen2.5 TurboAlibaba6.00--6.80s2024-11-18
521Qwen3 0.6B (Non-reasoning)Alibaba1.00---2025-04-28
522Qwen3 0.6B (Reasoning)Alibaba1.00---2025-04-28
523Qwen3 1.7B (Non-reasoning)Alibaba1.10---2025-04-28
524Qwen3 1.7B (Reasoning)Alibaba2.20---2025-04-28
525Qwen3 14B (Non-reasoning)Alibaba6.80--11.1s2025-04-28
526Qwen3 14B (Reasoning)Alibaba10.40--45.1s2025-04-28
527Qwen3 235B A22B (Non-reasoning)Alibaba10.80--11.1s2025-04-28
528Qwen3 235B A22B (Reasoning)Alibaba13.50--43.8s2025-04-28
529Qwen3 235B A22B 2507 InstructAlibaba18.40--11.3s2025-07-21
530Qwen3 30B A3B (Non-reasoning)Alibaba6.60--6.87s2025-04-28
531Qwen3 30B A3B (Reasoning)Alibaba9.20--26.5s2025-04-28
532Qwen3 30B A3B 2507 InstructAlibaba8.90--5.42s2025-07-29
533Qwen3 32B (Non-reasoning)Alibaba8.50--7.25s2025-04-28
534Qwen3 32B (Reasoning)Alibaba11.40--27.1s2025-04-28
535Qwen3 4B (Non-reasoning)Alibaba6.50---2025-04-28
536Qwen3 4B (Reasoning)Alibaba8.20---2025-04-28
537Qwen3 4B 2507 (Reasoning)Alibaba11.90---2025-08-06
538Qwen3 4B 2507 InstructAlibaba6.90---2025-08-06
539Qwen3 8B (Non-reasoning)Alibaba4.80--16.6s2025-04-28
540Qwen3 8B (Reasoning)Alibaba8.30--68.3s2025-04-28
541Qwen3 Coder 30B A3B InstructAlibaba13.60--8.03s2025-07-31
542Qwen3 Coder 480B A35B InstructAlibaba18.20--10.7s2025-07-22
543Qwen3 MaxAlibaba24.50--11.1s2025-09-23
544Qwen3 Max (Preview)Alibaba19.40--12.6s2025-09-05
545Qwen3 Max ThinkingAlibaba32.50---2026-01-26
546Qwen3 Max Thinking (Preview)Alibaba25.50--48.5s2025-11-03
547Qwen3 Next 80B A3B InstructAlibaba13.80--4.92s2025-09-11
548Qwen3 Omni 30B A3B (Reasoning)Alibaba9.50--27.1s2025-09-22
549Qwen3 Omni 30B A3B InstructAlibaba4.80--7.38s2025-09-22
550Qwen3 VL 235B A22B (Reasoning)Alibaba20.90--46.6s2025-09-23
551Qwen3 VL 235B A22B InstructAlibaba14.40--13.3s2025-09-23
552Qwen3 VL 30B A3B (Reasoning)Alibaba13.40--24.7s2025-10-03
553Qwen3 VL 30B A3B InstructAlibaba9.90--6.73s2025-10-03
554Qwen3 VL 32B (Reasoning)Alibaba18.10--30.5s2025-10-21
555Qwen3 VL 32B InstructAlibaba11.00--9.95s2025-10-21
556Qwen3 VL 4B (Reasoning)Alibaba7.70---2025-10-14
557Qwen3 VL 4B InstructAlibaba3.70---2025-10-14
558Qwen3 VL 8B (Reasoning)Alibaba10.50--24.3s2025-10-14
559Qwen3 VL 8B InstructAlibaba8.20--6.92s2025-10-14
560Qwen3.5 0.8B (Non-reasoning)Alibaba2.90---2026-03-02
561Qwen3.5 0.8B (Reasoning)Alibaba5.20---2026-03-02
562Qwen3.5 27B (Non-reasoning)Alibaba30.00--11.7s2026-02-24
563Qwen3.5 27B (Reasoning)Alibaba34.60--37.9s2026-02-24
564Qwen3.5 2B (Non-reasoning)Alibaba5.30---2026-03-02
565Qwen3.5 2B (Reasoning)Alibaba7.40---2026-03-02
566Qwen3.5 35B A3B (Reasoning)Alibaba29.90--18.6s2026-02-24
567Qwen3.5 397B A17B (Non-reasoning)Alibaba32.70--8.07s2026-02-16
568Qwen3.5 4B (Non-reasoning)Alibaba16.10--18.3s2026-03-02
569Qwen3.5 4B (Reasoning)Alibaba20.40--84.4s2026-03-02
570Qwen3.5 9B (Non-reasoning)Alibaba20.60--6.58s2026-03-02
571Qwen3.5 Omni FlashAlibaba19.20--3.91s2026-03-30
572Qwen3.5 Omni PlusAlibaba31.30--12.7s2026-03-30
573Qwen3.6 Max PreviewAlibaba41.10--44.6s2026-04-20
574Qwen3.8 27BAlibaba52.00---2026-08-14
575QwQ 32BAlibaba13.40---2025-03-05
576QwQ 32B-PreviewAlibaba9.10---2024-11-27
577R1 1776Perplexity6.00---2025-02-18
578Reka Flash (Sep '24)Reka AI6.00--11.2s2024-10-04
579Reka Flash 3Reka AI3.70---2025-03-10
580Ring-1TInclusionAI16.30---2025-10-13
581Ring-flash-2.0InclusionAI8.00---2025-09-19
582Sarvam 105B (high)Sarvam11.90---2026-03-06
583Sarvam 30B (high)Sarvam6.40---2026-03-06
584Sarvam M (Reasoning)Sarvam2.60---2025-05-23
585Seed-OSS-36B-InstructByteDance Seed18.50--87.2s2025-08-20
586Solar MiniUpstage6.00---2024-01-25
587Solar Open 100B (Reasoning)Upstage15.20---2025-12-17
588Solar Open2 250BUpstage37.40---2026-08-12
589Solar Pro 2 (Non-reasoning)Upstage7.60---2025-07-09
590Solar Pro 2 (Preview) (Non-reasoning)Upstage9.90---2025-05-20
591Solar Pro 2 (Preview) (Reasoning)Upstage12.50---2025-05-20
592Solar Pro 2 (Reasoning)Upstage8.80---2025-07-09
593SonarPerplexity9.40---2025-01-21
594Sonar ProPerplexity9.10---2025-01-21
595Sonar ReasoningPerplexity11.60---2025-01-28
596Sonar Reasoning ProPerplexity18.00---2025-01-28
597Step 3.5 FlashStepFun26.00--12.2s2026-02-02
598Step 3.5 Flash 2603StepFun26.50--12.8s2026-04-02
599Step3 VL 10BStepFun9.30---2026-01-20
600Tiny Aya GlobalCohere1.00---2026-02-17
601Tri-21B-ThinkTrillion Labs12.30---2026-02-10
602Tri-21B-think PreviewTrillion Labs13.60---2026-02-10
Agentes: Accept: text/markdown or ?format=md retorna esta página como Markdown. JSON: /api/v1/models · Markdown: /api/v1/models?format=md · llms.txt · habilidade do agente