AI Model Comparison - OpenRouter & Local LLMs

fjuja

Home LLM Tester Models About Origin Privacy & Terms

ibm-granite/granite-4.0-h-micro meta-llama/llama-3.2-1b-instruct mistralai/ministral-3b-2512

amazon/nova-lite-v1 amazon/nova-micro-v1 google/gemini-3.1-flash-lite google/gemma-4-26b-a4b-it google/gemma-4-31b-it gryphe/mythomax-l2-13b ibm-granite/granite-4.1-8b meta-llama/llama-3.1-8b-instruct microsoft/phi-4-mini-instruct mistralai/ministral-14b-2512 mistralai/ministral-8b-2512 nvidia/nemotron-3-nano-30b-a3b openai/gpt-5.4-nano openai/gpt-oss-20b poolside/laguna-xs-2.1 qwen/qwen3-32b qwen/qwen3-coder-30b-a3b-instruct qwen/qwen3-coder-next qwen/qwen3.6-27b qwen/qwen3.6-35b-a3b tencent/hunyuan-a13b-instruct

amazon/nova-2-lite-v1 anthropic/claude-haiku-4.5 bytedance-seed/seed-2.0-lite deepseek/deepseek-v4-flash google/gemini-3.5-flash google/gemini-3.6-flash inception/mercury-2 meta-llama/llama-4-scout mistralai/mistral-small-2603 nvidia/nemotron-3-super-120b-a12b openai/gpt-5.4-mini openai/gpt-5.6-luna openai/gpt-5.6-luna-pro openai/gpt-oss-120b poolside/laguna-s-2.1 qwen/qwen3-coder-flash qwen/qwen3.7-plus stepfun/step-3.7-flash

ai21/jamba-large-1.7 aion-labs/aion-3.0 amazon/nova-premier-v1 amazon/nova-pro-v1 anthropic/claude-sonnet-4.6 anthropic/claude-sonnet-5 cohere/command-a google/gemini-3.5-flash-lite meta-llama/llama-4-maverick mistralai/devstral-2512 mistralai/mistral-large mistralai/mistral-medium-3-5 mistralai/mistral-medium-3.1 openai/gpt-5.6-terra openai/gpt-5.6-terra-pro poolside/laguna-m.1 qwen/qwen3.5-397b-a17b tencent/hy3 xiaomi/mimo-v2.5-pro

anthropic/claude-fable-5 anthropic/claude-opus-4.8 anthropic/claude-opus-5 anthropic/claude-opus-5-fast deepseek/deepseek-v4-pro google/gemini-3.1-pro-preview minimax/minimax-m3 moonshotai/kimi-k2.6 moonshotai/kimi-k2.7-code moonshotai/kimi-k3 nvidia/nemotron-3-ultra-550b-a55b openai/gpt-5.5 openai/gpt-5.5-pro openai/gpt-5.6-sol openai/gpt-5.6-sol-pro qwen/qwen3-coder-plus qwen/qwen3.7-max x-ai/grok-4.3 x-ai/grok-4.5 z-ai/glm-5.2

gemma3-1b-it-q4f16_1-MLC Llama-3.2-1B-Instruct-q0f16-MLC Llama-3.2-1B-Instruct-q4f16_1-MLC phi-1_5-q4f16_1-MLC Qwen2.5-0.5B-Instruct-q0f16-MLC Qwen2.5-0.5B-Instruct-q4f16_1-MLC Qwen2.5-Coder-0.5B-Instruct-q0f16-MLC Qwen2.5-Coder-0.5B-Instruct-q4f16_1-MLC Qwen3-0.6B-q0f16-MLC Qwen3-0.6B-q4f16_1-MLC SmolLM2-135M-Instruct-q0f16-MLC SmolLM2-360M-Instruct-q0f16-MLC SmolLM2-360M-Instruct-q4f16_1-MLC TinyLlama-1.1B-Chat-v1.0-q4f16_1-MLC

gemma-2-2b-it-q4f16_1-MLC gemma-2b-it-q4f16_1-MLC Llama-3.2-3B-Instruct-q4f16_1-MLC Phi-4-mini-instruct-q4f16_1-MLC Qwen2.5-1.5B-Instruct-q4f16_1-MLC Qwen2.5-3B-Instruct-q4f16_1-MLC Qwen2.5-Coder-1.5B-Instruct-q4f16_1-MLC Qwen3-1.7B-q4f16_1-MLC Qwen3-4B-q4f16_1-MLC SmolLM2-1.7B-Instruct-q4f16_1-MLC

gemma-2-9b-it-q4f16_1-MLC Llama-2-13b-chat-hf-q4f16_1-MLC Llama-3.1-8B-Instruct-q4f16_1-MLC Mistral-7B-Instruct-v0.3-q4f16_1-MLC Qwen2.5-7B-Instruct-q4f16_1-MLC Qwen2.5-Coder-7B-Instruct-q4f16_1-MLC Qwen3-8B-q4f16_1-MLC Qwen3.5-9B-q4f16_1-MLC

Llama-3.1-70B-Instruct-q3f16_1-MLC

May require significant memory on your computer to run.

Please select at least one model before sending.

© 2026 Scollay Petry, All Rights Reserved.

Edit Models

Models

One model ID per line. Changes apply immediately after saving. Browse available model codes: Model list

API Parameters

Global — applies to every model and request.

Temperature ⓘ

0.5

Max tokens ⓘ

Reasoning effort ⓘ

Seed ⓘ

OpenRouter API Key

One key for all OpenRouter sections. Stored on the server and masked here; the full key is only used for API calls.

API Code

Ready-to-run Python (OpenAI SDK pointed at OpenRouter) reproducing the current run. Replace the placeholder API key with your own OpenRouter key.

Python

JavaScript

Compare Results

Choose the model that compares every response into a report. The chosen model runs after all of the input models have been run.

Claude Fable 5

Claude Opus 4.8

Claude Sonnet 5

Claude Haiku 4.5

DeepSeek V4 Pro

Gemini 3.5 Flash

MiniMax M3

Kimi K3

GPT-5.6 Sol

GPT-5.6 Terra

GPT-5.6 Luna

Qwen3.7 Max

GLM-5.2

Consolidate Results

Choose the model that combines every response into one fact-checked article — merging the best content, dropping incorrect claims (or noting discrepancies), and presenting both sides where views legitimately differ. The chosen model runs after all of the input models have been run.

Claude Fable 5

Claude Opus 4.8

Claude Sonnet 5

Claude Haiku 4.5

DeepSeek V4 Pro

Gemini 3.5 Flash

MiniMax M3

Kimi K3

GPT-5.6 Sol

GPT-5.6 Terra

GPT-5.6 Luna

Qwen3.7 Max

GLM-5.2

Downloaded Local Models

Local model weights cached in this browser across all sections. Delete to free up disk space.

Select All

Recent Prompts

Click a prompt to run again. Or check items to delete. Select All

Recent Chats

Click a previous chat to reopen it in the chat window, or check items to delete. Select All

OpenRouter API Key Required

An OpenRouter API key is required to run these models. Get one at openrouter.ai.

Please enter a key.

This key is stored only in your browser and applied to all OpenRouter sections.