İçeriğe geç

Benchmarks

Sıralama

All active models ranked by P50 latency — the median response time for a standard 500-token output, measured from EU (Amsterdam). Green < 500 ms, yellow 500–1000 ms, red > 1000 ms.

Filter:
#
1FLUX.1 Kontext [pro] — Multi-Image FusionB0
2FLUX.1 Kontext [max] — Multi-Image FusionA0
3NVIDIA Nemotron Super 49B v1.5A51
4Qwen3-Coder-30B-A3B-InstructB90
5Mistral-Nemo-Instruct-2407C100
6SDXL 1.0C100
7Qwen2.5-VL-72B-InstructB130
8Meta-Llama-3_3-70B-InstructB140
9Mistral-7B-Instruct-v0.3C165
10Nous Hermes 3 70BA185
11Mistral Voxtral Small 24BA219
12Llama 4 ScoutA224
13gpt-oss-20bC249
14Qwen3.5-397B-A17BA285
15Llama 3.3 70B InstructA326
16MiniMax M2.5A377
17Mistral-Small-3.2-24B-Instruct-2506B378
18Gemini 2.5 Flash-LiteB413
19FLUX.1 SchnellB421
20gpt-oss-120bC433
21Qwen 2.5 VL 72B InstructA443
22gpt-4.1-miniC459
23Qwen3-32BB475
24Llama 4 MaverickA476
25gpt-4o-miniC484
26gpt-4.1-nanoC486
27Qwen3.5-9BB525
28Cohere Command-AA535
29gpt-4.1B547
30gpt-5.4-nanoC550
31o3-miniC557
32gpt-5.4-miniA597
33gpt-4oC606
34o3C623
35o4-miniC630
36gpt-5-miniC695
37Gemini 2.5 FlashA718
38gpt-4.1-nano-2025-04-14C721
39Qwen 3.7 MaxA723
40gpt-5.1B744
41gpt-5.4A753
42Claude Haiku 4.5A761
43gpt-5C771
44Gemini 3.1 Flash LiteB812
45gpt-5.2-chat-latestC818
46gpt-5-nanoC840
47gpt-5.2B891
48gpt-5.3-chat-latestC908
49Qwen 3.6 PlusA927
50gpt-4o-2024-11-20C1003
51Gemini Flash-Lite LatestC1008
52gpt-5.4-mini-2026-03-17A1046
53Claude Opus 4.8A1053
54gpt-3.5-turboC1078
55gpt-4o-mini-2024-07-18C1097
56gpt-5.5C1126
57gpt-4o-2024-08-06C1232
58gpt-3.5-turbo-1106C1249
59gpt-4o-mini-search-previewC1276
60Claude Opus 4.5B1288
61GLM-4.6V (vision)A1290
62gpt-5.1-2025-11-13B1317
63Gemini 2.5 ProA1341
64GLM-5A1345
65gpt-5.4-2026-03-05B1375
66DeepSeek v3.2A1408
67o3-2025-04-16B1425
68gpt-4.1-2025-04-14C1445
69gpt-5.4-nano-2026-03-17A1461
70gpt-3.5-turbo-0125C1486
71gpt-5.2-2025-12-11B1507
72gpt-4-0613C1524
73gpt-5-search-api-2025-10-14B1551
74Claude Opus 5A1682
75gpt-4o-2024-05-13C1695
76gpt-3.5-turbo-16kC1697
77GLM-4.5V (vision)A1711
78gpt-5.5-2026-04-23A1728
79o3-mini-2025-01-31C1738
80DeepSeek v4 ProA1741
81GLM-5 TurboB1806
82gpt-4o-search-previewC2032
83Claude Opus 4.1C2077
84o4-mini-2025-04-16B2161
85Claude Sonnet 4.6A2173
86gpt-4.1-mini-2025-04-14C2219
87gpt-5-mini-2025-08-07B2427
88o1C2530
89Nano BananaB2873
90o1-2024-12-17C2940
91Gemini 3 Flash PreviewC2946
92gpt-5-nano-2025-08-07B2962
93Gemini 3.5 FlashA2990
94gpt-4C3002
95GLM-4.6A3218
96Claude Opus 4.7B3265
97GLM-5.2A3291
98GLM-5.1A3388
99Gemini Flash LatestB3571
100gpt-5-search-apiC3713
101Claude Sonnet 4.5B4022
102Gemini Robotics-ER 1.6 PreviewB4190
103Nano Banana 2B4330
104Gemini Pro LatestC4359
105gpt-5-2025-08-07B4774
106gpt-4-turboC4835
107Gemini 3.1 Pro PreviewC4955
108GLM-4.5 AirB5285
109GLM-4.7A5401
110gpt-4-turbo-2024-04-09C6778
111GLM-4.5A6994
112Gemini 3.1 Pro Preview Custom ToolsC7298
113Claude Fable 5A8078
114CogView-4B8888
115Nano Banana ProA11201
116Claude Opus 4.6B15178
117GLM ImageB30000

117 of 117 models · click column headers to sort

Fast (< 500 ms)
Medium (500–1000 ms)
Slow (> 1000 ms)
Updated every 6 hours · P50 = median latency · P95 = tail latency