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, lowest 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 |
|---|---|---|---|---|---|---|
| Gemini 1.5 Pro (001)Google · not on sale | – | – | – | 9 Apr 2024 | – | 1 |
| Gemini 1.5 Pro (002)Google · not on sale | – | – | – | – | – | 1 |
| Gemini 2.0 Flash (001)Google · not on sale | – | – | – | 11 Dec 2024 | – | 1 |
| Gemini 2.0 Flash-Lite Preview (02-05)Google · not on sale | – | – | – | 5 Feb 2025 | – | 1 |
| Gemini 2.5 Flash-Lite Preview (06-17)Google · not on sale | – | – | – | – | – | 1 |
| Gemini 2.5 Pro Preview (06-05)Google | – | – | $3.44 | – | 1,048k | 1 |
| Gemini 3.1 Flash-LiteGoogle | – | – | $0.56 | 3 Mar 2026 | 1,048k | 1 |
| Gemini 3.1 Pro Preview (custom tools)Google | – | – | $4.50 | – | 1,048k | 1 |
| Gemini Advanced (0514)Google · not on sale | – | – | – | – | – | 1 |
| Gemini ProGoogle · not on sale | – | – | – | – | – | 1 |
| Gemini Pro (Dev API)Google · not on sale | – | – | – | – | – | 1 |
| Gemma 1.1 2BGoogle · not on sale | – | – | – | – | – | 1 |
| Gemma 1.1 7BGoogle · not on sale | – | – | – | – | – | 1 |
| Gemma 2 9B SimPOPrinceton NLP · not on sale | – | – | – | – | – | 1 |
| Gemma 2BGoogle · not on sale | – | – | – | – | – | 1 |
| Gemma 3 1BGoogle · not on sale | – | – | – | – | – | 1 |
| Gemma 3n E4BGoogle · not on sale | – | – | – | – | – | 1 |
| Gemma 7BGoogle · not on sale | – | – | – | – | – | 1 |
| GLM-4 (0520)Z.ai · not on sale | – | – | – | 17 Jan 2024 | – | 1 |
| GLM-4-32B-0414Z.ai · not on sale | – | – | – | – | – | 1 |
| GLM-4-PlusZ.ai · not on sale | – | – | – | – | – | 1 |
| GLM-4-Plus (0111)Z.ai · not on sale | – | – | – | – | – | 1 |
| GLM-4.5-Air (FP8)Z.ai · not on sale | – | – | – | – | – | 1 |
| GPT-3.5 Turbo (0125)OpenAI · not on sale | – | – | – | 25 Jan 2024 | – | 1 |
| GPT-3.5 Turbo (1106)OpenAI · not on sale | – | – | – | – | – | 1 |
| GPT-4 (0314)OpenAI · not on sale | – | – | – | – | – | 1 |
| GPT-4 (0613)OpenAI · not on sale | – | – | – | – | – | 1 |
| GPT-4 TurboOpenAI | – | – | $15.00 | 25 Jan 2024 | 128k | 1 |
| GPT-4 Turbo Preview (0125)OpenAI · not on sale | – | – | – | – | – | 1 |
| GPT-4 Turbo Preview (1106)OpenAI · not on sale | – | – | – | – | – | 1 |
| GPT-4.5 PreviewOpenAI · not on sale | – | – | – | 27 Feb 2025 | – | 1 |
| GPT-4o Search (API)OpenAI · not on sale | – | – | – | – | – | 1 |
| GPT-5 Chat (latest)OpenAI · not on sale | – | – | – | – | – | 1 |
| GPT-5.1 ChatOpenAI · not on sale | – | – | – | – | – | 1 |
| GPT-5.2 ChatOpenAI · not on sale | – | – | – | – | – | 1 |
| GPT-5.2 Chat (2026-02-10)OpenAI · not on sale | – | – | – | – | – | 1 |
| GPT-5.6 Sol ProOpenAI | – | – | $8.00 | – | 1,050k | 1 |
| GPT-6 Luna DecisionsOpenAI · not on sale | – | – | – | – | – | 1 |
| GPT4All 13B SnoozyNomic AI · not on sale | – | – | – | – | – | 1 |
| Granite 20B FunctionCallingIBM · not on sale | – | – | – | – | – | 1 |
| Granite 3.0 2B InstructIBM · not on sale | – | – | – | – | – | 1 |
| Granite 3.0 8B InstructIBM · not on sale | – | – | – | – | – | 1 |
| Granite 3.1 2B InstructIBM · not on sale | – | – | – | – | – | 1 |
| Granite 3.2 8B InstructIBM · not on sale | – | – | – | – | – | 1 |
| Granite 3.3 8B InstructIBM · not on sale | – | – | – | – | – | 1 |
| Granite 4.0 350MIBM · not on sale | – | – | – | – | – | 1 |
| Granite 4.1 8BIBM · not on sale | – | – | – | – | – | 1 |
| Granite 4.2 30BIBM · not on sale | – | – | – | – | – | 1 |
| Granite 4.2 3BIBM · not on sale | – | – | – | – | – | 1 |
| Granite H SmallIBM · not on sale | – | – | – | – | – | 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.