ModelBench
Model catalog

Models

Every model in the catalog with source-linked pricing, context limits, provider availability, and published benchmark results.

Compare Export CSV
212 models
32K+
Ranked by Coding Index
Mistral AI: Mistral: Ministral 3 8B 2512 T
9.7

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

mistralai/ministral-8b-2512 262.144K context $0.15/M input $0.15/M output
Mistral AI: Mistral: Ministral 3 8B 2512 (batch) T
9.7

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

mistralai/ministral-8b-2512:batch 262.144K context $0.075/M input $0.075/M output
IBM: IBM: Granite 4.1 8B T
Open weights 9.5

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...

ibm-granite/granite-4.1-8b 131.072K context $0.05/M input $0.1/M output
Alibaba Qwen: Qwen: Qwen3 8B T
9.0

Qwen3-8B is a dense 8.2B parameter causal language model from the Qwen3 series, designed for both reasoning-heavy tasks and efficient dialogue. It supports seamless switching between "thinking" mode for math,...

qwen/qwen3-8b 131.072K context $0.117/M input $0.455/M output
Meta: Meta: Llama 4 Scout T
8.2

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimodal input...

meta-llama/llama-4-scout 327.68K context $0.1/M input $0.3/M output
Liquid: LiquidAI: LFM2.5-2.6B T
7.7

LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...

liquid/lfm-2.5-2.6b 128K context $0.35/M input $0.5/M output
Liquid: LiquidAI: LFM2.5-2.6B (free) T
7.7

LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for agentic coding or...

liquid/lfm-2.5-2.6b:free 65.536K context Free input Free output
Google: Gemma 3 12B IT T
Open weights 5.8

Open multimodal Gemma instruction model for multilingual text generation and image understanding

google/gemma-3-12b-it 2025-03-12 131.072K context $0.04/M input $0.12/M output
10 providers
Meta: Meta: Llama 3.1 8B Instruct T
5.4

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...

meta-llama/llama-3.1-8b-instruct 131.072K context $0.05/M input $0.08/M output
Mistral AI: Mistral: Ministral 3 3B 2512 T
4.8

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

mistralai/ministral-3b-2512 131.072K context $0.1/M input $0.1/M output
Google: Gemma 3n E4B IT T
Open weights 3.2

Efficient on-device Gemma 3n model for text, image, and audio understanding

google/gemma-3n-e4b-it 2025-06-26 32.768K context Input not listed Output not listed
1 provider
Google: Gemma 3 4B IT T
Open weights 2.7

Open multimodal Gemma instruction model for efficient text generation and image understanding

google/gemma-3-4b-it 2025-03-12 131.072K context $0.04/M input $0.08/M output
9 providers