Benchmarks
Classement
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 | FLUX.1 Kontext [pro] — Multi-Image FusionB | fal.ai | B | 0 | 0 | — | 2026-07-30 |
| 2 | FLUX.1 Kontext [max] — Multi-Image FusionA | fal.ai | A | 0 | 0 | — | 2026-07-30 |
| 3 | NVIDIA Nemotron Super 49B v1.5A | OpenRouter | A | 51 | 57 | — | 2026-07-30 |
| 4 | Qwen3-Coder-30B-A3B-InstructB | OVH AI Endpoints (GRA) | B | 90 | 103 | 100 | 2026-07-30 |
| 5 | Mistral-Nemo-Instruct-2407C | OVH AI Endpoints (GRA) | C | 100 | 322 | 26 | 2026-07-30 |
| 6 | SDXL 1.0C | Hugging Face (nscale) | C | 100 | 107 | — | 2026-07-30 |
| 7 | Qwen2.5-VL-72B-InstructB | OVH AI Endpoints (GRA) | B | 130 | 1115 | 100 | 2026-07-30 |
| 8 | Meta-Llama-3_3-70B-InstructB | OVH AI Endpoints (GRA) | B | 140 | 1892 | 100 | 2026-07-30 |
| 9 | Mistral-7B-Instruct-v0.3C | OVH AI Endpoints (GRA) | C | 165 | 197 | 100 | 2026-07-30 |
| 10 | Nous Hermes 3 70BA | OpenRouter | A | 185 | 202 | — | 2026-07-30 |
| 11 | Mistral Voxtral Small 24BA | OpenRouter | A | 219 | 225 | — | 2026-07-30 |
| 12 | Llama 4 ScoutA | OpenRouter | A | 224 | 388 | — | 2026-07-30 |
| 13 | gpt-oss-20bC | OVH AI Endpoints (GRA) | C | 249 | 250 | 100 | 2026-07-30 |
| 14 | Qwen3.5-397B-A17BA | OVH AI Endpoints (GRA) | A | 285 | 1040 | 100 | 2026-07-30 |
| 15 | Llama 3.3 70B InstructA | OpenRouter | A | 326 | 392 | — | 2026-07-30 |
| 16 | MiniMax M2.5A | OpenRouter | A | 377 | 609 | — | 2026-07-30 |
| 17 | Mistral-Small-3.2-24B-Instruct-2506B | OVH AI Endpoints (GRA) | B | 378 | 378 | 100 | 2026-07-30 |
| 18 | Gemini 2.5 Flash-LiteB | Google Gemini | B | 413 | 425 | 100 | 2026-07-30 |
| 19 | FLUX.1 SchnellB | Hugging Face (nscale) | B | 421 | 600 | — | 2026-07-30 |
| 20 | gpt-oss-120bC | OVH AI Endpoints (GRA) | C | 433 | 540 | 100 | 2026-07-30 |
| 21 | Qwen 2.5 VL 72B InstructA | OpenRouter | A | 443 | 776 | — | 2026-07-30 |
| 22 | gpt-4.1-miniC | OpenAI | C | 459 | 571 | 95 | 2026-07-30 |
| 23 | Qwen3-32BB | OVH AI Endpoints (GRA) | B | 475 | 620 | 95 | 2026-07-30 |
| 24 | Llama 4 MaverickA | OpenRouter | A | 476 | 5190 | — | 2026-07-30 |
| 25 | gpt-4o-miniC | OpenAI | C | 484 | 639 | 100 | 2026-07-30 |
| 26 | gpt-4.1-nanoC | OpenAI | C | 486 | 521 | 100 | 2026-07-30 |
| 27 | Qwen3.5-9BB | OVH AI Endpoints (GRA) | B | 525 | 529 | 100 | 2026-07-30 |
| 28 | Cohere Command-AA | OpenRouter | A | 535 | 1314 | — | 2026-07-30 |
| 29 | gpt-4.1B | OpenAI | B | 547 | 1727 | 100 | 2026-07-30 |
| 30 | gpt-5.4-nanoC | OpenAI | C | 550 | 736 | 100 | 2026-07-30 |
| 31 | o3-miniC | OpenAI | C | 557 | 601 | 100 | 2026-07-30 |
| 32 | gpt-5.4-miniA | OpenAI | A | 597 | 734 | 100 | 2026-07-30 |
| 33 | gpt-4oC | OpenAI | C | 606 | 777 | 100 | 2026-07-30 |
| 34 | o3C | OpenAI | C | 623 | 645 | 100 | 2026-07-30 |
| 35 | o4-miniC | OpenAI | C | 630 | 667 | 100 | 2026-07-30 |
| 36 | gpt-5-miniC | OpenAI | C | 695 | 794 | 100 | 2026-07-30 |
| 37 | Gemini 2.5 FlashA | Google Gemini | A | 718 | 721 | 100 | 2026-07-30 |
| 38 | gpt-4.1-nano-2025-04-14C | OpenAI | C | 721 | — | 100 | 2026-07-26 |
| 39 | Qwen 3.7 MaxA | OpenRouter | A | 723 | 1255 | — | 2026-07-30 |
| 40 | gpt-5.1B | OpenAI | B | 744 | 780 | 100 | 2026-07-30 |
| 41 | gpt-5.4A | OpenAI | A | 753 | 857 | 100 | 2026-07-30 |
| 42 | Claude Haiku 4.5A | Anthropic | A | 761 | 1895 | 100 | 2026-07-30 |
| 43 | gpt-5C | OpenAI | C | 771 | 2789 | 100 | 2026-07-30 |
| 44 | Gemini 3.1 Flash LiteB | Google Gemini | B | 812 | — | 100 | 2026-07-26 |
| 45 | gpt-5.2-chat-latestC | OpenAI | C | 818 | 825 | 100 | 2026-07-30 |
| 46 | gpt-5-nanoC | OpenAI | C | 840 | 867 | 98 | 2026-07-30 |
| 47 | gpt-5.2B | OpenAI | B | 891 | 1562 | 100 | 2026-07-30 |
| 48 | gpt-5.3-chat-latestC | OpenAI | C | 908 | 1038 | 100 | 2026-07-30 |
| 49 | Qwen 3.6 PlusA | OpenRouter | A | 927 | 927 | — | 2026-07-30 |
| 50 | gpt-4o-2024-11-20C | OpenAI | C | 1003 | — | 100 | 2026-07-26 |
| 51 | Gemini Flash-Lite LatestC | Google Gemini | C | 1008 | — | 100 | 2026-07-26 |
| 52 | gpt-5.4-mini-2026-03-17A | OpenAI | A | 1046 | — | 100 | 2026-07-26 |
| 53 | Claude Opus 4.8A | Anthropic | A | 1053 | 1083 | 100 | 2026-07-30 |
| 54 | gpt-3.5-turboC | OpenAI | C | 1078 | — | 100 | 2026-07-26 |
| 55 | gpt-4o-mini-2024-07-18C | OpenAI | C | 1097 | — | 100 | 2026-07-26 |
| 56 | gpt-5.5C | OpenAI | C | 1126 | 1610 | 100 | 2026-07-30 |
| 57 | gpt-4o-2024-08-06C | OpenAI | C | 1232 | — | 100 | 2026-07-26 |
| 58 | gpt-3.5-turbo-1106C | OpenAI | C | 1249 | — | 100 | 2026-07-26 |
| 59 | gpt-4o-mini-search-previewC | OpenAI | C | 1276 | — | 70 | 2026-07-26 |
| 60 | Claude Opus 4.5B | Anthropic | B | 1288 | 1944 | 100 | 2026-07-30 |
| 61 | GLM-4.6V (vision)A | Z.ai (GLM / Zhipu) | A | 1290 | 1346 | 0 | 2026-07-30 |
| 62 | gpt-5.1-2025-11-13B | OpenAI | B | 1317 | — | 100 | 2026-07-26 |
| 63 | Gemini 2.5 ProA | Google Gemini | A | 1341 | 1520 | 0 | 2026-07-30 |
| 64 | GLM-5A | Z.ai (GLM / Zhipu) | A | 1345 | 1769 | 93 | 2026-07-30 |
| 65 | gpt-5.4-2026-03-05B | OpenAI | B | 1375 | — | 100 | 2026-07-26 |
| 66 | DeepSeek v3.2A | OpenRouter | A | 1408 | 3275 | — | 2026-07-30 |
| 67 | o3-2025-04-16B | OpenAI | B | 1425 | — | 100 | 2026-07-26 |
| 68 | gpt-4.1-2025-04-14C | OpenAI | C | 1445 | — | 100 | 2026-07-26 |
| 69 | gpt-5.4-nano-2026-03-17A | OpenAI | A | 1461 | — | 100 | 2026-07-26 |
| 70 | gpt-3.5-turbo-0125C | OpenAI | C | 1486 | — | 100 | 2026-07-26 |
| 71 | gpt-5.2-2025-12-11B | OpenAI | B | 1507 | — | 100 | 2026-07-26 |
| 72 | gpt-4-0613C | OpenAI | C | 1524 | — | 100 | 2026-07-26 |
| 73 | gpt-5-search-api-2025-10-14B | OpenAI | B | 1551 | — | 100 | 2026-07-26 |
| 74 | Claude Opus 5A | Anthropic | A | 1682 | 1816 | 100 | 2026-07-30 |
| 75 | gpt-4o-2024-05-13C | OpenAI | C | 1695 | — | 100 | 2026-07-26 |
| 76 | gpt-3.5-turbo-16kC | OpenAI | C | 1697 | — | 100 | 2026-07-26 |
| 77 | GLM-4.5V (vision)A | Z.ai (GLM / Zhipu) | A | 1711 | 2437 | 22 | 2026-07-30 |
| 78 | gpt-5.5-2026-04-23A | OpenAI | A | 1728 | — | 100 | 2026-07-26 |
| 79 | o3-mini-2025-01-31C | OpenAI | C | 1738 | — | 100 | 2026-07-26 |
| 80 | DeepSeek v4 ProA | OpenRouter | A | 1741 | 1879 | — | 2026-07-30 |
| 81 | GLM-5 TurboB | Z.ai (GLM / Zhipu) | B | 1806 | 6892 | 0 | 2026-07-30 |
| 82 | gpt-4o-search-previewC | OpenAI | C | 2032 | — | 100 | 2026-07-26 |
| 83 | Claude Opus 4.1C | Anthropic | C | 2077 | 2550 | 100 | 2026-07-30 |
| 84 | o4-mini-2025-04-16B | OpenAI | B | 2161 | — | 100 | 2026-07-26 |
| 85 | Claude Sonnet 4.6A | Anthropic | A | 2173 | 2547 | 100 | 2026-07-30 |
| 86 | gpt-4.1-mini-2025-04-14C | OpenAI | C | 2219 | — | 100 | 2026-07-26 |
| 87 | gpt-5-mini-2025-08-07B | OpenAI | B | 2427 | — | 100 | 2026-07-26 |
| 88 | o1C | OpenAI | C | 2530 | — | 100 | 2026-07-26 |
| 89 | Nano BananaB | Google Gemini | B | 2873 | — | 97 | 2026-06-21 |
| 90 | o1-2024-12-17C | OpenAI | C | 2940 | — | 100 | 2026-07-26 |
| 91 | Gemini 3 Flash PreviewC | Google Gemini | C | 2946 | — | 100 | 2026-07-26 |
| 92 | gpt-5-nano-2025-08-07B | OpenAI | B | 2962 | — | 100 | 2026-07-26 |
| 93 | Gemini 3.5 FlashA | Google Gemini | A | 2990 | — | 100 | 2026-07-26 |
| 94 | gpt-4C | OpenAI | C | 3002 | — | 100 | 2026-07-26 |
| 95 | GLM-4.6A | Z.ai (GLM / Zhipu) | A | 3218 | 3420 | 2 | 2026-07-30 |
| 96 | Claude Opus 4.7B | Anthropic | B | 3265 | 4452 | 100 | 2026-07-30 |
| 97 | GLM-5.2A | Z.ai (GLM / Zhipu) | A | 3291 | 3952 | 75 | 2026-07-30 |
| 98 | GLM-5.1A | Z.ai (GLM / Zhipu) | A | 3388 | 4185 | 80 | 2026-07-30 |
| 99 | Gemini Flash LatestB | Google Gemini | B | 3571 | — | 100 | 2026-07-26 |
| 100 | gpt-5-search-apiC | OpenAI | C | 3713 | — | 100 | 2026-07-26 |
| 101 | Claude Sonnet 4.5B | Anthropic | B | 4022 | 8369 | 100 | 2026-07-30 |
| 102 | Gemini Robotics-ER 1.6 PreviewB | Google Gemini | B | 4190 | — | 5 | 2026-06-21 |
| 103 | Nano Banana 2B | Google Gemini | B | 4330 | — | 91 | 2026-06-21 |
| 104 | Gemini Pro LatestC | Google Gemini | C | 4359 | — | 100 | 2026-07-26 |
| 105 | gpt-5-2025-08-07B | OpenAI | B | 4774 | — | 100 | 2026-07-26 |
| 106 | gpt-4-turboC | OpenAI | C | 4835 | — | 100 | 2026-07-26 |
| 107 | Gemini 3.1 Pro PreviewC | Google Gemini | C | 4955 | — | 86 | 2026-07-26 |
| 108 | GLM-4.5 AirB | Z.ai (GLM / Zhipu) | B | 5285 | 12491 | 62 | 2026-07-30 |
| 109 | GLM-4.7A | Z.ai (GLM / Zhipu) | A | 5401 | 30000 | 95 | 2026-07-30 |
| 110 | gpt-4-turbo-2024-04-09C | OpenAI | C | 6778 | — | 100 | 2026-07-26 |
| 111 | GLM-4.5A | Z.ai (GLM / Zhipu) | A | 6994 | 30000 | 95 | 2026-07-30 |
| 112 | Gemini 3.1 Pro Preview Custom ToolsC | Google Gemini | C | 7298 | — | 0 | 2026-06-21 |
| 113 | Claude Fable 5A | Anthropic | A | 8078 | 9455 | 100 | 2026-07-30 |
| 114 | CogView-4B | Z.ai (GLM / Zhipu) | B | 8888 | 9287 | 0 | 2026-07-30 |
| 115 | Nano Banana ProA | Google Gemini | A | 11201 | — | 0 | 2026-06-21 |
| 116 | Claude Opus 4.6B | Anthropic | B | 15178 | 15497 | 100 | 2026-07-30 |
| 117 | GLM ImageB | Z.ai (GLM / Zhipu) | B | 30000 | 30000 | — | 2026-07-30 |
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