| Model | Context | Input | Output | Throughput | Latency | Providers | Agents | Coding | Reasoning | Knowledge | Math | Multilingual | Multimodal | Instruction following |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| GPT-SoVITS | — | — | — | — | — | +1 | — | — | — | — | — | — | — | — |
| Gemini 1.5 Pro 001 | — | — | — | — | — | +1 | — | — | — | — | — | — | — | — |
| GPT-4 Vision | — | — | — | — | — | +29 | — | — | — | — | — | — | — | — |
| Text Embedding 3 Large | — | — | — | — | — | +49 | — | — | — | — | — | — | — | — |
| Gemini Flash Lite | — | — | — | — | — | +37 | — | — | — | — | — | — | — | — |
| GLM-4.5 AirX | — | — | — | 71 t/s | 11.56s | +22 | — | — | — | — | — | — | — | — |
| GPT-4o Mini TTS | — | — | — | — | — | +35 | — | — | — | — | — | — | — | — |
| Claude 2.1 | — | — | — | — | — | +8 | — | 19 | 28.5 | — | 20.4 | — | — | — |
| Qwen3.5 Plus Image | — | — | — | — | — | +1 | — | — | — | — | — | — | — | — |
| Grok 3 Mini | — | — | — | 122 t/s | 5.23s | +69 | — | — | — | — | — | — | — | — |
| ChatGPT-4o | — | — | — | 78 t/s | 4.56s | +45 | — | — | — | — | — | — | — | — |
| Claude Instant 1.2 | — | — | — | — | — | +6 | — | — | — | — | — | — | — | — |
| GLM-4 Long | — | — | — | — | — | +15 | — | — | — | — | — | — | — | — |
| MiniMax-Text-01 | — | — | — | — | — | +2 | — | — | — | — | — | — | — | — |
| GPT-4o Mini Transcribe | — | — | — | — | — | +33 | — | — | — | — | — | — | — | — |
| Net GPT-4o | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| MiniMax Feed | — | — | — | — | — | +1 | — | — | — | — | — | — | — | — |
| GPT-4 Gizmo | — | — | — | — | — | +23 | — | — | — | — | — | — | — | — |
| Qwen3 TTS Flash Realtime | — | — | — | — | — | +13 | — | — | — | — | — | — | — | — |
| GPT Image 1.5 | — | — | — | — | — | +98 | — | — | — | — | — | — | — | — |
| GPT-4 Net | — | — | — | — | — | +2 | — | — | — | — | — | — | — | — |
| MiniMax M2.5 Lightning | — | — | — | — | — | +6 | — | — | — | — | — | — | — | — |
| GPT-4o Image | — | — | — | — | — | +27 | — | — | — | — | — | — | — | — |
| GPT-5 Codex Mini | — | — | — | 38 t/s | 3.35s | +60 | — | — | — | — | — | — | — | — |
| ChatGPT Image | — | — | — | — | — | +11 | — | — | — | — | — | — | — | — |
| FLUX Kontext Pro | — | — | — | — | — | +16 | — | — | — | — | — | — | — | — |
| GPT-4o Transcribe Diarize | — | — | — | — | — | +16 | — | — | — | — | — | — | — | — |
| GLM-Z1 AirX | — | — | — | 168 t/s | 0.34s | +7 | — | — | — | — | — | — | — | — |
| Text Embedding 3 Small | — | — | — | — | — | +49 | — | — | — | — | — | — | — | — |
| GLM-Z1 Flash | — | — | — | 109 t/s | 0.45s | +18 | — | — | — | — | — | — | — | — |
| GLM-4V | — | — | — | — | — | +17 | — | — | — | — | — | — | — | — |
| Gemini 2.5 Flash Native Audio | — | — | — | — | — | +6 | — | — | — | — | — | — | — | — |
| BGE Reranker V2 M3 | — | — | — | — | — | +36 | — | — | — | — | — | — | — | — |
| Gemini 2.0 Flash 001 | — | — | — | 108 t/s | 2.70s | +21 | — | — | — | — | — | — | — | — |
| GPT-4o Realtime | — | — | — | — | — | +64 | — | — | — | — | — | — | — | — |
| Qwen3 TTS Flash | — | — | — | — | — | +26 | — | — | — | — | — | — | — | — |
| Claude 1.3 | — | — | — | — | — | +1 | — | — | — | — | — | — | — | — |
| Grok 3 | — | — | — | 43 t/s | 2.64s | +83 | — | 39.7 | 51.4 | — | 60 | — | — | — |
| MiniMax M2.7 HighSpeed | — | — | — | 49 t/s | 3.53s | +49 | — | — | — | — | — | — | — | — |
| GPT-4o Mini Realtime | — | — | — | — | — | +31 | — | — | — | — | — | — | — | — |
| Kimi K2 Instruct | — | — | — | 129 t/s | 1.05s | +76 | — | — | — | — | — | — | — | — |
| GLM-3 Turbo | — | — | — | — | — | +19 | — | — | — | — | — | — | — | — |
| Fish Speech 1.5 | — | — | — | — | — | +1 | — | — | — | — | — | — | — | — |
| MiniMax Video | — | — | — | — | — | +1 | — | — | — | — | — | — | — | — |
| Gemini Embedding 001 | — | — | — | — | — | +52 | — | — | — | — | — | — | — | — |
| Qwen3.1 | — | — | — | 151 t/s | 4.42s | +11 | — | — | — | — | — | — | — | — |
| Grok-2 | — | — | — | 59 t/s | 0.60s | +16 | — | 27.6 | 41.9 | — | 45.6 | — | — | — |
| GPT-4o Mini Audio | — | — | — | — | — | +30 | — | — | — | — | — | — | — | — |
| DeepSeek OCR | — | — | — | — | — | +36 | — | — | — | — | — | — | — | — |
| GLM-4V Plus | — | — | — | — | — | +9 | — | — | — | — | — | — | — | — |
| V0 1.5 MD | — | — | — | — | — | — | — | — | — | — | — | — | — | |
| GPT-4o Audio | — | — | — | — | — | +70 | — | — | — | — | — | — | — | — |
| Gemini 2.0 Flash | — | — | — | 137 t/s | 3.08s | +61 | — | 27.5 | 48.8 | — | 60.5 | — | — | — |
| GPT-4 DALL-E | — | — | — | — | — | +10 | — | — | — | — | — | — | — | — |
| Claude 3.7 Sonnet | — | — | — | 45 t/s | 7.65s | +34 | — | 43.8 | 57.1 | — | 71.7 | — | — | — |
| Claude 3 Sonnet | — | — | — | — | — | +8 | — | 20.2 | 33.9 | — | 23 | — | — | — |
| Gemini 2.0 Flash Lite 001 | — | — | — | — | — | +19 | — | 21.8 | 43.2 | — | 57.5 | — | — | — |
| Gemini 2.0 Flash Lite | — | — | — | 182 t/s | 1.49s | +34 | — | 21.3 | 29.3 | — | 58.8 | — | — | — |
| Kimi K2 Thinking Turbo | — | — | — | — | — | +9 | — | — | — | — | — | — | — | — |
| Gemini 2.0 Pro | — | — | — | 67 t/s | 8.47s | +12 | — | 33 | 49.8 | — | 64.1 | — | — | — |