Skip to content

Speed leaderboard

Latest benchmark run per model, sorted by median latency (fastest first). Scores are updated nightly.

Top 10 fastest models

RankModelProviderP50 msP95 msErrorsLast run
1Mistral-Small-3.2-24B-Instruct-2506OVH AI Endpoints (GRA)7712202026-05-09
2Llama-3.1-8B-InstructOVH AI Endpoints (GRA)859502026-05-09
3Qwen3-Coder-30B-A3B-InstructOVH AI Endpoints (GRA)9616302026-05-09
4Qwen2.5-VL-72B-InstructOVH AI Endpoints (GRA)11111902026-05-09
5Mistral-Nemo-Instruct-2407OVH AI Endpoints (GRA)11115102026-05-09
6Mistral-7B-Instruct-v0.3OVH AI Endpoints (GRA)11314902026-05-09
7Meta-Llama-3_3-70B-InstructOVH AI Endpoints (GRA)11412402026-05-09
8gpt-oss-20bOVH AI Endpoints (GRA)21629402026-05-09
9gpt-oss-120bOVH AI Endpoints (GRA)324221102026-05-09
10gpt-5.4-miniOpenAI36156102026-05-09
Show all results (161)
RankModelProviderP50 msP95 msErrorsLast run
11gpt-4.1-nanoOpenAI45546602026-05-09
12gpt-4.1OpenAI46467502026-05-09
13gpt-5-chat-latestOpenAI48169002026-05-09
14gpt-4o-miniOpenAI499111402026-05-09
15o3-miniOpenAI51160202026-05-09
16gpt-5.4OpenAI57666902026-05-09
17gpt-5.4-nanoOpenAI59366302026-05-09
18gpt-4.1-miniOpenAI59464102026-05-09
19o4-miniOpenAI59864302026-05-09
20Gemini 2.5 FlashGoogle Gemini60972902026-05-09
21Claude Haiku 4.5Anthropic61161302026-05-09
22Gemini 2.5 Flash-LiteGoogle Gemini624157702026-05-09
23gpt-4oOpenAI63396002026-05-09
24gpt-5.1OpenAI65174002026-05-09
25Qwen3-32BOVH AI Endpoints (GRA)67769302026-05-09
26gpt-5-miniOpenAI68269102026-05-09
27o3OpenAI69574122026-05-09
28gpt-5-nanoOpenAI69977602026-05-09
29gpt-5.2OpenAI714104802026-05-09
30Qwen3.5-9BOVH AI Endpoints (GRA)77884402026-05-09
31Claude Sonnet 4.6Anthropic809111202026-05-09
32Claude Sonnet 4Anthropic829103502026-05-09
33Claude Opus 4.5Anthropic933114002026-05-09
34gpt-5.3-chat-latestOpenAI952151122026-05-09
35Claude Sonnet 4.5Anthropic981123602026-05-09
36Gemini 2.5 ProGoogle Gemini1074128202026-05-09
37gpt-5.5OpenAI1094116702026-05-09
38Claude Opus 4.7Anthropic1157132002026-05-09
39gpt-5.2-chat-latestOpenAI1195155102026-05-09
40gpt-5OpenAI1252206702026-05-09
41gpt-4o-2024-05-13OpenAI145102026-05-09
42gpt-5.1-chat-latestOpenAI1467154412026-05-09
43Gemini Flash-Lite LatestGoogle Gemini148402026-05-09
44Gemini 3.1 Flash Lite PreviewGoogle Gemini152702026-05-09
45gpt-3.5-turbo-1106OpenAI160702026-05-09
46Claude Opus 4.6Anthropic1625167202026-05-09
47gpt-4.1-nano-2025-04-14OpenAI176602026-05-09
48Nano Banana 2Google Gemini185402026-05-09
49Claude Opus 4Anthropic1879261802026-05-09
50gpt-4o-2024-11-20OpenAI189302026-05-09
51Nano BananaGoogle Gemini197602026-05-09
52gpt-3.5-turboOpenAI243502026-05-09
53gpt-4o-mini-search-previewOpenAI247502026-05-09
54gpt-4o-mini-search-preview-2025-03-11OpenAI265102026-05-09
55gpt-5-search-apiOpenAI292702026-05-09
56Claude Opus 4.1Anthropic2936568802026-05-09
57gpt-3.5-turbo-16kOpenAI304202026-05-09
58gpt-5-search-api-2025-10-14OpenAI313502026-05-09
59gpt-4o-2024-08-06OpenAI322802026-05-09
60gpt-4.1-mini-2025-04-14OpenAI326802026-05-09
61Gemini Robotics-ER 1.6 PreviewGoogle Gemini329702026-05-09
62gpt-4.1-2025-04-14OpenAI357802026-05-09
63Gemini Flash LatestGoogle Gemini371702026-05-09
64Gemini 3 Flash PreviewGoogle Gemini391102026-05-09
65gpt-4o-search-preview-2025-03-11OpenAI489902026-05-09
66gpt-4o-mini-2024-07-18OpenAI618202026-05-09
67Gemini 3.1 Pro PreviewGoogle Gemini714702026-05-09
68gpt-4o-search-previewOpenAI721002026-05-09
69Gemini Pro LatestGoogle Gemini763602026-05-09
70gpt-3.5-turbo-0125OpenAI778702026-05-09
71Gemini 3.1 Pro Preview Custom ToolsGoogle Gemini797302026-05-09
72Gemini 3 Pro PreviewGoogle Gemini808702026-05-09
73gpt-4-0613OpenAI833102026-05-09
74Nano Banana ProGoogle Gemini846502026-05-09
75Lyria 3 Clip PreviewGoogle Gemini869902026-05-09
76Nano Banana ProGoogle Gemini981402026-05-09
77gpt-4-turboOpenAI1077702026-05-09
78gpt-4OpenAI1100302026-05-09
79gpt-4-turbo-2024-04-09OpenAI1669402026-05-09
80Gemma 4 31B ITGoogle Gemini2000502026-05-09
81Gemma 4 26B A4B ITGoogle Gemini2138002026-05-09
82pplOVH AI Endpoints (GRA)300003000032026-05-09
83gpt-3.5-turbo-instructOpenAI12026-05-09
84gpt-3.5-turbo-instruct-0914OpenAI12026-05-09
85gpt-4o-audio-previewOpenAI12026-05-09
86gpt-4o-realtime-previewOpenAI12026-05-09
87gpt-4o-realtime-preview-2024-12-17OpenAI12026-05-09
88gpt-4o-audio-preview-2024-12-17OpenAI12026-05-09
89gpt-4o-mini-realtime-preview-2024-12-17OpenAI12026-05-09
90gpt-4o-mini-audio-preview-2024-12-17OpenAI12026-05-09
91o1-2024-12-17OpenAI12026-05-09
92o1OpenAI12026-05-09
93gpt-4o-mini-realtime-previewOpenAI12026-05-09
94gpt-4o-mini-audio-previewOpenAI12026-05-09
95o3-mini-2025-01-31OpenAI12026-05-09
96gpt-4o-transcribeOpenAI12026-05-09
97gpt-4o-mini-transcribeOpenAI12026-05-09
98o1-pro-2025-03-19OpenAI12026-05-09
99o1-proOpenAI12026-05-09
100gpt-4o-mini-ttsOpenAI12026-05-09
101o3-2025-04-16OpenAI12026-05-09
102o4-mini-2025-04-16OpenAI12026-05-09
103gpt-image-1OpenAI12026-05-09
104gpt-4o-realtime-preview-2025-06-03OpenAI12026-05-09
105gpt-4o-audio-preview-2025-06-03OpenAI12026-05-09
106o4-mini-deep-researchOpenAI12026-05-09
107gpt-4o-transcribe-diarizeOpenAI12026-05-09
108o4-mini-deep-research-2025-06-26OpenAI12026-05-09
109gpt-5-2025-08-07OpenAI12026-05-09
110gpt-5-mini-2025-08-07OpenAI12026-05-09
111gpt-5-nano-2025-08-07OpenAI12026-05-09
112gpt-audio-2025-08-28OpenAI12026-05-09
113gpt-realtimeOpenAI12026-05-09
114gpt-realtime-2025-08-28OpenAI12026-05-09
115gpt-audioOpenAI12026-05-09
116gpt-5-codexOpenAI12026-05-09
117gpt-image-1-miniOpenAI12026-05-09
118gpt-5-pro-2025-10-06OpenAI12026-05-09
119gpt-5-proOpenAI12026-05-09
120gpt-audio-miniOpenAI12026-05-09
121gpt-audio-mini-2025-10-06OpenAI12026-05-09
122gpt-realtime-miniOpenAI12026-05-09
123gpt-realtime-mini-2025-10-06OpenAI12026-05-09
124gpt-5.1-2025-11-13OpenAI12026-05-09
125gpt-5.1-codexOpenAI12026-05-09
126gpt-5.1-codex-miniOpenAI12026-05-09
127gpt-5.1-codex-maxOpenAI12026-05-09
128gpt-image-1.5OpenAI12026-05-09
129gpt-5.2-2025-12-11OpenAI12026-05-09
130gpt-5.2-pro-2025-12-11OpenAI12026-05-09
131gpt-5.2-proOpenAI12026-05-09
132gpt-4o-mini-transcribe-2025-12-15OpenAI12026-05-09
133gpt-4o-mini-transcribe-2025-03-20OpenAI12026-05-09
134gpt-4o-mini-tts-2025-03-20OpenAI12026-05-09
135gpt-4o-mini-tts-2025-12-15OpenAI12026-05-09
136gpt-realtime-mini-2025-12-15OpenAI12026-05-09
137gpt-audio-mini-2025-12-15OpenAI12026-05-09
138chatgpt-image-latestOpenAI12026-05-09
139gpt-5.2-codexOpenAI12026-05-09
140gpt-5.3-codexOpenAI12026-05-09
141gpt-realtime-1.5OpenAI12026-05-09
142gpt-audio-1.5OpenAI12026-05-09
143gpt-5.4-2026-03-05OpenAI12026-05-09
144gpt-5.4-proOpenAI12026-05-09
145gpt-5.4-pro-2026-03-05OpenAI12026-05-09
146gpt-5.4-nano-2026-03-17OpenAI12026-05-09
147gpt-5.4-mini-2026-03-17OpenAI12026-05-09
148gpt-image-2OpenAI12026-05-09
149gpt-image-2-2026-04-21OpenAI12026-05-09
150gpt-5.5-2026-04-23OpenAI12026-05-09
151gpt-5.5-proOpenAI12026-05-09
152gpt-5.5-pro-2026-04-23OpenAI12026-05-09
153Gemini 2.0 FlashGoogle Gemini12026-05-09
154Gemini 2.0 Flash 001Google Gemini12026-05-09
155Gemini 2.0 Flash-Lite 001Google Gemini12026-05-09
156Gemini 2.0 Flash-LiteGoogle Gemini12026-05-09
157Gemini 2.5 Flash Preview TTSGoogle Gemini12026-05-09
158Gemini 2.5 Pro Preview TTSGoogle Gemini12026-05-09
159Gemma 3 1BGoogle Gemini12026-05-09
160Gemma 3 4BGoogle Gemini12026-05-09
161Gemma 3 12BGoogle Gemini12026-05-09
162Gemma 3 27BGoogle Gemini12026-05-09
163Gemma 3n E4BGoogle Gemini12026-05-09
164Gemma 3n E2BGoogle Gemini12026-05-09
165Lyria 3 Pro PreviewGoogle Gemini12026-05-09
166Gemini 3.1 Flash TTS PreviewGoogle Gemini12026-05-09
167Gemini Robotics-ER 1.5 PreviewGoogle Gemini12026-05-09
168Gemini 2.5 Computer Use Preview 10-2025Google Gemini12026-05-09
169Deep Research Max Preview (Apr-21-2026)Google Gemini12026-05-09
170Deep Research Preview (Apr-21-2026)Google Gemini12026-05-09
171Deep Research Pro Preview (Dec-12-2025)Google Gemini12026-05-09