Skip to content
Benchmark Heaven

Open source alternatives to Benchmark Heaven

200 open source apps like Benchmark Heaven, closest match first.

Top picks

  1. O

    OpenRouter Model Price Comparison

    Launch

    OpenRouter Model Price Comparison is a web page that puts the AI models available on OpenRouter into one table, so you can compare what they cost. For each model it shows the provider, context length, input and output costs, image cost, sup

  2. L

    LMRing

    Launch

    lmring is a web app for comparing AI models side by side. You pick up to four models from more than 50 providers, including OpenAI, Anthropic, Google, Meta, Mistral and DeepSeek, then write one prompt and send it to all of them at once. Res

    Open sourceSelf-hosted

  3. L

    Litmux

    Launch

    Test your prompts across all major AI models, catch regressions, and find the cheapest model that passes your quality bar. Open source CLI.

    Open source

  4. A

    AI LLM Comparison

    Launch

    A website where you can compare every AI Model ✨

    Open source

  5. G

    Geo Aeo Tracker

    Launch

    Open-source, local-first AI visibility intelligence dashboard. Track your brand across 6 AI models.

    Open source

  6. F

    Frugon

    Launch

    Frugon is a free, open-source command-line tool that estimates how much you could save on LLM bills. You give it the request logs your app already writes, in OpenAI or Anthropic-style JSONL, and it shows which calls a cheaper model could ha

    Open source

More like Benchmark Heaven

7
I

Inferock Bench

Local LLM cost-tracking proxy for OpenAI, Anthropic, Gemini

Launch
8
O

OneGlanse

Open-source AI visibility, AEO & GEO tracker

Launch
9
G

GoModel

AI gateway written in Go with a unified OpenAI-compatible API

Launch
10
N

NadirClaw

Source-available LLM router and AI cost optimizer

Launch
11
L

Langfuse

Trace, evaluate, and improve AI agents with one open platform

Launch
12
B

Beat API

One API key for 70+ discounted AI models and 1,000+ data APIs

Launch
13
L

Latitude

AI Agent Observability & Monitoring

Launch
14
D

Devo

Model-neutral agent desktop/runtime for private, enterprise

Launch
15
C

Coai

Next Gen Multi-tenant AI One-Stop Solution

Launch
16
K

Kiln

Intuitive app to build your own AI models

Launch
17
P

Primitive Bench

The marketplace for verifiable AI outcomes: state a task

Launch
18
A

Ansvisor

Open-source AI Search Intelligence Platform

Launch
19
L

LocalScore

Local AI Benchmark

Launch
20
U

UnoRouter

Open-source LLM gateway: 300+ AI models behind one OpenAI-compatible key

Launch
21
C

Chat JS

Production-ready AI chat. Start here and make it your own. Formerly Sparka AI

Launch
22
T

Tokencost

Easy token price estimates for 400+ LLMs. TokenOps

Launch
23
R

Routerly.ai

Self-hosted LLM gateway that routes requests across AI providers

Launch
24
S

Spanlens

Drop-in observability platform for OpenAI, Anthropic, and Gemini

Launch
25
A

AI-Flow

Connect multiple AI models easily

Launch
26
M

Misceo

Local Anthropic-compatible AI gateway

Launch
27
M

Manifest

A complete backend in a single YAML file

Launch
28
A

Agent Locker

Worlds Largest Directory of Agentic AI Agents, Tools and Platforms

Launch
29
O

Obot AI

Complete AI Governance Platform from Obot AI

Launch
30
L

Litefuse

Agent Observability and Evaluation Platform

Launch
31
L

Llamafarm

Deploy any AI model, agent, database, RAG

Launch
32
M

Matrixhub

An Open-source, self-hosted AI model hub

Launch
33
P

Proxy

Local-first LLM proxy that meters what every agent run costs

Launch
34
P

Prompttools

Open-source tools for prompt testing and experimentation

Launch
35
C

Claudetop

htop for your Claude Code sessions — real-time cost, cache efficiency, model…

Launch
36
A

Allen AI

Develop AI systems for understanding and interacting, create trusted AI models

Launch
37
O

Open

Self-hosted AI visibility tracking (AEO / GEO / LLMO)

Launch
38
L

LLM Gateway

Route, manage, and analyze LLM requests across multiple providers with one API

Launch
39
T

Traceml

Engine for AI/ML/Data tracking, visualization, explainability, drift detection

Launch
40
Z

Zetaforgedev

Open source AI platform for rapid development of advanced AI and AGI pipelines

Launch
41
W

WebLLM Chat

Chat with AI large language models running natively in your browser

Launch
42
A

AI Gate

Why juggle 6 AI tools

Launch
43
S

Scoopika

Bring AI agents to your application in minutes

Launch
44
L

Llmaker

Selfhost modern LLM stacks. Run the whole fleet from your terminal

Launch
45
A

Anubis Oss

Local LLM Testing & Benchmarking for Apple Silicon

Launch
46
O

Open Responses

Self-hosted alternative to OpenAI's Responses API compatible

Launch
47
S

SillyTavern

LLM Frontend for Power Users

Launch
48
C

CTX

CTX Fit finds the cheapest AI coding setup

Launch
49
B

BricksLLM

🔒 Enterprise-grade API gateway that helps you monitor and impose cost or…

Launch
50
B

Benchmarks

Reproducible voice-AI benchmarking — TTS / STT / S2S latency and accuracy

Launch

About Benchmark Heaven

B

Benchmark Heaven

Model benchmarks & costs

Benchmark Heaven compares AI models on cost and capability, with benchmark results, charts and provider prices. It is the home of JevBench, a decision-model benchmark that measures accuracy, calibration, latency and cost. The site has a cost-versus-capability chart, a providers-per-model view, a provider explorer, a gateways list, and sections for EU and sovereign models and for image and audio benchmarks. A ranking table shows scores from several sources, including Artificial Analysis coding indexes and DesignArena Elo scores for full-stack and web app tasks. Visitors can filter out deprecated models, show one variant for reasoning models, and limit results to open-weights models. The site notes that evidence requirements, such as benchmark evidence and priced providers, appear above each table they apply to. It is marked as beta and work in progress. Models can be submitted for listing. The project publishes its API documentation and licence on GitHub.

Price
Open source
Category
AI
Website
benchmarkheaven.com