Benchmarks
Leaderboard
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:
| # | |||||||
|---|---|---|---|---|---|---|---|
| 1 | SDXL 1.0C | Hugging Face (nscale) | C | 0 | 0 | — | 2026-07-22 |
| 2 | FLUX.1 Kontext [max] — Multi-Image Fusion | fal.ai | — | 0 | 0 | — | 2026-07-22 |
| 3 | FLUX.1 Kontext [pro] — Multi-Image Fusion | fal.ai | — | 0 | 0 | — | 2026-07-22 |
| 4 | FLUX.1 SchnellB | Hugging Face (nscale) | B | 0 | 0 | — | 2026-07-22 |
| 5 | NVIDIA Nemotron Super 49B v1.5A | OpenRouter | A | 20 | 80 | — | 2026-07-22 |
| 6 | Mistral-Nemo-Instruct-2407 | OVH AI Endpoints (GRA) | — | 93 | 158 | 100 | 2026-07-22 |
| 7 | Meta-Llama-3_3-70B-Instruct | OVH AI Endpoints (GRA) | — | 131 | 147 | 100 | 2026-07-22 |
| 8 | Qwen2.5-VL-72B-Instruct | OVH AI Endpoints (GRA) | — | 163 | 167 | 95 | 2026-07-22 |
| 9 | Llama 4 ScoutA | OpenRouter | A | 171 | 378 | — | 2026-07-22 |
| 10 | Llama 4 MaverickA | OpenRouter | A | 174 | 380 | — | 2026-07-22 |
| 11 | Mistral Voxtral Small 24BA | OpenRouter | A | 186 | 246 | — | 2026-07-22 |
| 12 | Nous Hermes 3 70BA | OpenRouter | A | 196 | 216 | — | 2026-07-22 |
| 13 | Qwen3.5-397B-A17B | OVH AI Endpoints (GRA) | — | 245 | 1818 | 100 | 2026-07-22 |
| 14 | gpt-oss-20bC | OVH AI Endpoints (GRA) | C | 262 | 312 | 98 | 2026-07-22 |
| 15 | Cohere Command-AA | OpenRouter | A | 278 | 613 | — | 2026-07-22 |
| 16 | Llama 3.3 70B InstructA | OpenRouter | A | 296 | 595 | — | 2026-07-22 |
| 17 | gpt-oss-120bC | OVH AI Endpoints (GRA) | C | 328 | 698 | 100 | 2026-07-22 |
| 18 | Mistral-Small-3.2-24B-Instruct-2506 | OVH AI Endpoints (GRA) | — | 350 | 382 | 100 | 2026-07-22 |
| 19 | Gemini 2.5 Flash-LiteB | Google Gemini | B | 416 | 425 | 98 | 2026-07-22 |
| 20 | Qwen3-32B | OVH AI Endpoints (GRA) | — | 438 | 488 | 93 | 2026-07-22 |
| 21 | Qwen3-Coder-30B-A3B-Instruct | OVH AI Endpoints (GRA) | — | 439 | 469 | 100 | 2026-07-22 |
| 22 | gpt-4.1-nanoC | OpenAI | C | 458 | 496 | 100 | 2026-07-22 |
| 23 | gpt-4.1B | OpenAI | B | 466 | 534 | 100 | 2026-07-22 |
| 24 | Qwen3.5-9B | OVH AI Endpoints (GRA) | — | 521 | 541 | 100 | 2026-07-22 |
| 25 | o3-miniC | OpenAI | C | 553 | 624 | 100 | 2026-07-22 |
| 26 | gpt-4oC | OpenAI | C | 553 | 565 | 100 | 2026-07-22 |
| 27 | gpt-4o-miniC | OpenAI | C | 556 | 872 | 100 | 2026-07-22 |
| 28 | gpt-5.4-nanoC | OpenAI | C | 567 | 624 | 100 | 2026-07-22 |
| 29 | gpt-4.1-miniC | OpenAI | C | 573 | 640 | 100 | 2026-07-22 |
| 30 | gpt-5.4-miniA | OpenAI | A | 579 | 579 | 100 | 2026-07-22 |
| 31 | Mistral-7B-Instruct-v0.3 | OVH AI Endpoints (GRA) | — | 615 | 1129 | 87 | 2026-07-22 |
| 32 | gpt-5-chat-latestC | OpenAI | C | 652 | 1504 | 100 | 2026-07-22 |
| 33 | Gemini 2.5 FlashA | Google Gemini | A | 662 | 1240 | 35 | 2026-07-22 |
| 34 | gpt-5.1-chat-latestC | OpenAI | C | 754 | 813 | 100 | 2026-07-22 |
| 35 | gpt-5.2-chat-latestC | OpenAI | C | 759 | 1129 | 100 | 2026-07-22 |
| 36 | gpt-4.1-nano-2025-04-14 | OpenAI | — | 761 | — | 100 | 2026-07-19 |
| 37 | gpt-5.4A | OpenAI | A | 786 | 833 | 100 | 2026-07-22 |
| 38 | Qwen 3.7 MaxA | OpenRouter | A | 787 | 1287 | — | 2026-07-22 |
| 39 | MiniMax M2.5A | OpenRouter | A | 800 | 1217 | — | 2026-07-22 |
| 40 | gpt-5.3-chat-latestC | OpenAI | C | 802 | 1008 | 100 | 2026-07-22 |
| 41 | o4-miniC | OpenAI | C | 858 | 945 | 100 | 2026-07-22 |
| 42 | gpt-5-miniC | OpenAI | C | 901 | 1168 | 100 | 2026-07-22 |
| 43 | Gemini 2.5 ProA | Google Gemini | A | 916 | 988 | 0 | 2026-07-22 |
| 44 | gpt-5.1B | OpenAI | B | 920 | 992 | 100 | 2026-07-22 |
| 45 | o3C | OpenAI | C | 922 | 970 | 100 | 2026-07-22 |
| 46 | gpt-5-nanoC | OpenAI | C | 932 | 1053 | 0 | 2026-07-22 |
| 47 | Claude Opus 4.7B | Anthropic | B | 938 | 1123 | 100 | 2026-07-22 |
| 48 | Qwen 3.6 PlusA | OpenRouter | A | 952 | 1272 | — | 2026-07-22 |
| 49 | gpt-5.2B | OpenAI | B | 973 | 1905 | 100 | 2026-07-22 |
| 50 | GLM-4.5V (vision)A | Z.ai (GLM / Zhipu) | A | 1005 | 1197 | 100 | 2026-07-22 |
| 51 | gpt-5C | OpenAI | C | 1064 | 3486 | 100 | 2026-07-22 |
| 52 | Claude Sonnet 4.6A | Anthropic | A | 1067 | 1380 | 100 | 2026-07-22 |
| 53 | gpt-4.1-2025-04-14 | OpenAI | — | 1099 | — | 100 | 2026-07-19 |
| 54 | DeepSeek v3.2A | OpenRouter | A | 1133 | 1407 | — | 2026-07-22 |
| 55 | gpt-5.5C | OpenAI | C | 1133 | 1263 | 100 | 2026-07-22 |
| 56 | Claude Opus 4.8A | Anthropic | A | 1155 | 1265 | 100 | 2026-07-22 |
| 57 | gpt-5.4-nano-2026-03-17 | OpenAI | — | 1218 | — | 100 | 2026-07-19 |
| 58 | Claude Haiku 4.5A | Anthropic | A | 1238 | 1508 | 100 | 2026-07-22 |
| 59 | gpt-5.4-mini-2026-03-17 | OpenAI | — | 1239 | — | 100 | 2026-07-19 |
| 60 | Gemini 3.1 Flash Lite | Google Gemini | — | 1310 | — | 100 | 2026-07-19 |
| 61 | gpt-5.4-2026-03-05 | OpenAI | — | 1475 | — | 100 | 2026-07-19 |
| 62 | gpt-3.5-turbo-1106 | OpenAI | — | 1513 | — | 98 | 2026-07-19 |
| 63 | gpt-5.1-2025-11-13 | OpenAI | — | 1521 | — | 100 | 2026-07-19 |
| 64 | Gemini Flash-Lite LatestC | Google Gemini | C | 1536 | — | 100 | 2026-07-19 |
| 65 | gpt-4o-2024-11-20C | OpenAI | C | 1574 | — | 100 | 2026-07-19 |
| 66 | GLM-5A | Z.ai (GLM / Zhipu) | A | 1616 | 1978 | 100 | 2026-07-22 |
| 67 | Claude Opus 4.6B | Anthropic | B | 1671 | 1688 | 100 | 2026-07-22 |
| 68 | Claude Sonnet 4.5B | Anthropic | B | 1776 | 2004 | 100 | 2026-07-22 |
| 69 | gpt-4.1-mini-2025-04-14 | OpenAI | — | 1777 | — | 100 | 2026-07-19 |
| 70 | gpt-4o-2024-05-13C | OpenAI | C | 1802 | — | 100 | 2026-07-19 |
| 71 | gpt-3.5-turboC | OpenAI | C | 1814 | — | 100 | 2026-07-19 |
| 72 | DeepSeek v4 ProA | OpenRouter | A | 1849 | 2439 | — | 2026-07-22 |
| 73 | GLM-5 TurboB | Z.ai (GLM / Zhipu) | B | 1924 | 2314 | 100 | 2026-07-22 |
| 74 | gpt-3.5-turbo-0125 | OpenAI | — | 2033 | — | 100 | 2026-07-19 |
| 75 | GLM-4.6V (vision)A | Z.ai (GLM / Zhipu) | A | 2085 | 2196 | 100 | 2026-07-22 |
| 76 | o3-2025-04-16 | OpenAI | — | 2106 | — | 100 | 2026-07-19 |
| 77 | gpt-5.5-2026-04-23 | OpenAI | — | 2146 | — | 100 | 2026-07-19 |
| 78 | gpt-3.5-turbo-16k | OpenAI | — | 2171 | — | 100 | 2026-07-19 |
| 79 | o3-mini-2025-01-31 | OpenAI | — | 2359 | — | 100 | 2026-07-19 |
| 80 | o1-2024-12-17C | OpenAI | C | 2408 | — | 100 | 2026-07-19 |
| 81 | Claude Opus 4.1C | Anthropic | C | 2418 | 3038 | 100 | 2026-07-22 |
| 82 | gpt-5-search-apiC | OpenAI | C | 2673 | — | 100 | 2026-07-19 |
| 83 | Nano Banana | Google Gemini | — | 2873 | — | 97 | 2026-06-21 |
| 84 | gpt-5-search-api-2025-10-14 | OpenAI | — | 3014 | — | 100 | 2026-07-19 |
| 85 | Gemini 3 Flash PreviewC | Google Gemini | C | 3022 | — | 100 | 2026-07-19 |
| 86 | gpt-4o-mini-2024-07-18C | OpenAI | C | 3060 | — | 100 | 2026-07-19 |
| 87 | Qwen 2.5 VL 72B InstructA | OpenRouter | A | 3161 | 4908 | — | 2026-07-22 |
| 88 | gpt-5.2-2025-12-11 | OpenAI | — | 3263 | — | 100 | 2026-07-19 |
| 89 | Gemini 3.5 FlashA | Google Gemini | A | 3280 | — | 93 | 2026-07-19 |
| 90 | o4-mini-2025-04-16 | OpenAI | — | 3313 | — | 100 | 2026-07-19 |
| 91 | o1C | OpenAI | C | 3333 | — | 100 | 2026-07-19 |
| 92 | GLM-5.2A | Z.ai (GLM / Zhipu) | A | 3372 | 4853 | 100 | 2026-07-22 |
| 93 | Gemini Flash LatestB | Google Gemini | B | 3619 | — | 90 | 2026-07-19 |
| 94 | gpt-4o-search-preview-2025-03-11 | OpenAI | — | 3657 | — | 100 | 2026-07-19 |
| 95 | GLM-4.5 AirB | Z.ai (GLM / Zhipu) | B | 3849 | 4999 | 100 | 2026-07-22 |
| 96 | gpt-4o-mini-search-previewC | OpenAI | C | 3940 | — | 98 | 2026-07-19 |
| 97 | Gemini Robotics-ER 1.6 Preview | Google Gemini | — | 4190 | — | 5 | 2026-06-21 |
| 98 | gpt-4o-2024-08-06C | OpenAI | C | 4274 | — | 100 | 2026-07-19 |
| 99 | Nano Banana 2 | Google Gemini | — | 4330 | — | 91 | 2026-06-21 |
| 100 | gpt-5-mini-2025-08-07 | OpenAI | — | 4421 | — | 100 | 2026-07-19 |
| 101 | gpt-4o-mini-search-preview-2025-03-11 | OpenAI | — | 4803 | — | 100 | 2026-07-19 |
| 102 | gpt-5-nano-2025-08-07 | OpenAI | — | 4887 | — | 0 | 2026-07-19 |
| 103 | Gemini Pro LatestC | Google Gemini | C | 5218 | — | 90 | 2026-07-19 |
| 104 | gpt-4o-search-previewC | OpenAI | C | 5488 | — | 100 | 2026-07-19 |
| 105 | gpt-4C | OpenAI | C | 6284 | — | 100 | 2026-07-19 |
| 106 | GLM-4.7A | Z.ai (GLM / Zhipu) | A | 6713 | 30000 | 100 | 2026-07-22 |
| 107 | GLM-4.6A | Z.ai (GLM / Zhipu) | A | 6823 | 7640 | 100 | 2026-07-22 |
| 108 | gpt-4-0613 | OpenAI | — | 7040 | — | 100 | 2026-07-19 |
| 109 | Gemini 3.1 Pro Preview Custom ToolsC | Google Gemini | C | 7298 | — | 0 | 2026-06-21 |
| 110 | Gemini 3.1 Pro PreviewC | Google Gemini | C | 7493 | — | 95 | 2026-07-19 |
| 111 | CogView-4B | Z.ai (GLM / Zhipu) | B | 8021 | 10085 | 0 | 2026-07-22 |
| 112 | Claude Opus 4.5B | Anthropic | B | 8634 | 9024 | 100 | 2026-07-22 |
| 113 | gpt-5-2025-08-07 | OpenAI | — | 10054 | — | 0 | 2026-07-19 |
| 114 | Nano Banana Pro | Google Gemini | — | 10741 | — | 0 | 2026-06-21 |
| 115 | gpt-4-turboC | OpenAI | C | 10791 | — | 100 | 2026-07-19 |
| 116 | GLM-5.1A | Z.ai (GLM / Zhipu) | A | 11007 | 13364 | 0 | 2026-07-22 |
| 117 | Nano Banana Pro | Google Gemini | — | 11201 | — | 0 | 2026-06-21 |
| 118 | GLM-4.5A | Z.ai (GLM / Zhipu) | A | 11808 | 17109 | 100 | 2026-07-22 |
| 119 | gpt-4-turbo-2024-04-09C | OpenAI | C | 13438 | — | 100 | 2026-07-19 |
| 120 | GLM ImageB | Z.ai (GLM / Zhipu) | B | 30000 | 30000 | — | 2026-07-22 |
120 of 120 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