AI models compared
584 models with published results from our own benchmarks and licensed sources, strongest first: by our overall score, then the Artificial Analysis Intelligence Index. Open a model for every result, with its source and date. 225 of them are on sale through OpenRouter, with prices on the API pricing page; launches are on the release tracker.
Sorted by Spring Prompt overall, highest first; models without a value come last. Select a column heading to sort by it.
| Model | Spring Prompt overall | Intelligence Index | Price, blended | Released | Context | Sources |
|---|---|---|---|---|---|---|
| Grok 2 (2024-08-13)xAI · not on sale | – | – | – | 14 Aug 2024 | – | 1 |
| Grok 2 Mini (2024-08-13)xAI · not on sale | – | – | – | – | – | 1 |
| Grok 3 MinixAI · not on sale | – | – | – | – | – | 1 |
| Grok 3 Mini BetaxAI · not on sale | – | – | – | – | – | 1 |
| Grok 3 Preview (02-24)xAI · not on sale | – | – | – | – | – | 1 |
| Grok 4 Fast ChatxAI · not on sale | – | – | – | – | – | 1 |
| Grok 4.1xAI · not on sale | – | – | – | 17 Nov 2025 | – | 1 |
| Grok 4.1 ThinkingxAI · not on sale | – | – | – | – | – | 1 |
| Grok 4.20 Beta (0309, non-reasoning)xAI · not on sale | – | – | – | – | – | 1 |
| Grok 4.20 Beta 1xAI · not on sale | – | – | – | – | – | 1 |
| Guanaco 33BTim Dettmers · not on sale | – | – | – | – | – | 1 |
| Hammer2.1-0.5BMadeAgents · not on sale | – | – | – | – | – | 1 |
| Hammer2.1-1.5BMadeAgents · not on sale | – | – | – | – | – | 1 |
| Hammer2.1-3BMadeAgents · not on sale | – | – | – | – | – | 1 |
| Hammer2.1-7BMadeAgents · not on sale | – | – | – | – | – | 1 |
| Hunyuan Large (2025-02-10)Tencent · not on sale | – | – | – | – | – | 1 |
| Hunyuan Large VisionTencent · not on sale | – | – | – | – | – | 1 |
| Hunyuan Standard (2025-02-10)Tencent · not on sale | – | – | – | – | – | 1 |
| Hunyuan Standard 256KTencent · not on sale | – | – | – | – | – | 1 |
| Hunyuan T1 (2025-07-11)Tencent · not on sale | – | – | – | – | – | 1 |
| Hunyuan Turbo (0110)Tencent · not on sale | – | – | – | – | – | 1 |
| Hunyuan TurboS (2025-02-26)Tencent · not on sale | – | – | – | – | – | 1 |
| Hunyuan TurboS (2025-04-16)Tencent · not on sale | – | – | – | – | – | 1 |
| Hunyuan Vision 1.5 ThinkingTencent · not on sale | – | – | – | – | – | 1 |
| Hy4 PreviewTencent · open weights | – | – | $1.25 | 28 Aug 2026 | 1,048k | 1 |
| Inflection 3 PiInflection AI · not on sale | – | – | – | – | – | 1 |
| Inflection 3 ProductivityInflection AI · not on sale | – | – | – | – | – | 1 |
| INTELLECT-3Prime Intellect · not on sale | – | – | – | – | – | 1 |
| InternLM2.5 20B ChatShanghai AI Lab · not on sale | – | – | – | – | – | 1 |
| InternLM3 8B InstructShanghai AI Lab · not on sale | – | – | – | – | – | 1 |
| Jamba 1.5 LargeAI21 Labs · not on sale | – | – | – | – | – | 1 |
| Jamba 1.5 MiniAI21 Labs · not on sale | – | – | – | – | – | 1 |
| Jamba Mini 2AI21 Labs · not on sale | – | – | – | – | – | 1 |
| Jev 1.13TypeSafe · not on sale | – | – | – | – | – | 1 |
| Kev 4BJared Palmer · not on sale | – | – | – | – | – | 1 |
| Kimi K2 Thinking TurboMoonshot AI · not on sale | – | – | – | – | – | 1 |
| Kimi-VL-A3B-InstructMoonshot AI · not on sale | – | – | – | – | – | 1 |
| Kimi-VL-A3B-Thinking (2506)Moonshot AI · not on sale | – | – | – | – | – | 1 |
| Koala 13BUC Berkeley · not on sale | – | – | – | – | – | 1 |
| LFM2-24B-A2BLiquid AI · not on sale | – | – | – | – | – | 1 |
| LFM2-8B-A1BLiquid AI · not on sale | – | – | – | – | – | 1 |
| Ling-1TAnt Group · not on sale | – | – | – | – | – | 1 |
| Ling-flash-2.0Ant Group · not on sale | – | – | – | – | – | 1 |
| LLaMA 13BMeta · not on sale | – | – | – | – | – | 1 |
| Llama 2 13B ChatMeta · not on sale | – | – | – | – | – | 1 |
| Llama 2 70B SteerLM ChatNVIDIA · not on sale | – | – | – | – | – | 1 |
| Llama 2 7B ChatMeta · not on sale | – | – | – | – | – | 1 |
| Llama 3 70B InstructMeta · not on sale | – | – | – | – | – | 1 |
| Llama 3 8B InstructMeta · not on sale | – | – | – | – | – | 1 |
| Llama 3.1 405B InstructMeta · not on sale | – | – | – | 23 Jul 2024 | – | 1 |
Spring Prompt overall is our score across every source, out of 100 (how it works). The Intelligence Index is Artificial Analysis's, at each model's best setting. Price is the developer's list price, or the typical OpenRouter host, for three input tokens to one output, per million tokens.
Want two models side by side? Compare models.