Alternatives
Products that do what PunditBench does
Pre-registered scoring for LLM football forecasts
- 1
- 2
- 3FP
2018 · boggio-analytics.com
- 4
- 5
- 6
- 7
- 8
- 9
- 10SF
2012 · statmilk.com
- 11
- 12AE
I created a bot which analyses Euro 2024 betting odds and performs some basic analysis based on the recent form of each team and provides advice on which odds are under/over-priced by email to all subscribers. The intelligence of the bot is admittedly rather basic but this simple app shows how easy it is to reliably scrape and parse structured data with AI and perform insightful analysis. The initial version of the bot, shown in the notebook took about 15 minutes to build. Disclosure: this bot is built on our new graph based #nocode platform NodeScript.dev, which we've recently brought…
2024 · notebooks.nodescript.dev
- 13
- 14OS
Hey HN, I fine-tuned a small open-source model on golf forecasting and it beats GPT-5 at predicting golf outcomes. The same approach can be used to build a specialized model in any domain, you just need to update a few search queries. We fine-tuned gpt-oss-120b with LoRA on 3,178 golf forecasting questions, using GRPO with Brier score as the reward. Our model outperformed GPT-5 on Brier Skill (17% vs 12.8%) and ECE (6% vs 10.6%) on 855 held-out questions. How to try it: the model and dataset are open-source, with code, on Hugging Face. How to build your own specialized model: Update the…
Feb 2026 · huggingface.co
- 15
- 16
- 17RE
Recent academic work ([1], [2]) has suggested that LLMs can effectively simulate different Internet subpopulations. For example, you may ask ChatGPT to emulate being a high school teacher explaining Newton’s laws of physics. Building upon this, we created Roundtable, a platform that uses LLMs to predict how people will respond to any arbitrary survey question. To do so, we needed to first reduce bias arising from GPT’s training procedure. Because these models are primarily trained on Internet data, they can be heavily skewed towards the demographics of heavy Internet users (e.g.,…
2023 · roundtable.ai
- 18SE
Hey HN! I built self-driving sim and eval at Waymo. Now I’m building Scorecard to bring that approach to agent eval: reproducible, automated scoring for AI. Scorecard lets you: - Run LLM-as-judge evals on agent workflows: test tool usage, multi-step reasoning, and task completion in CI/CD or in a playground. - Debug failures with OpenTelemetry traces: see which tool failed, why your agent looped, and where reasoning went wrong. - Collaborate on datasets, simulated agents, and evaluation metrics. Try it out → https://app.scorecard.io (free tier, no payment required!) Docs →…
Oct 2025 · docs.scorecard.io
- 19SS
We built this because every sports AI demo uses fake data or locks you behind an enterprise API contract. sports-skills gives your agent real sports data with one install command. No API keys. No accounts. For personal use. Eight connectors out of the box: NFL, soccer across 13 leagues with xG, Formula 1 lap and pit data, NBA, WNBA, Polymarket, Kalshi, and a sports news aggregator pulling from BBC/ESPN/The Athletic. npx skills add machina-sports/sports-skills Open for contributions.
Feb 2026 · github.com
- 20
- 21AL
Try it out here: https://labs.refuel.ai/playground Refuel LLM (84.2%) outperforms trained human annotators (80.4%), GPT-3-5-turbo (81.3%), PaLM-2 (82.3%) and Claude (79.3%) across a benchmark of 15 text labeling datasets. It is a Llama-v2-13b base model, trained on over 2500 unique datasets (5.24B tokens) spanning categories such as classification, entity resolution, matching, reading comprehension and information extraction.
2023
- 22
- 23LM
I wanted to play around with the non-coding agentic capabilities of the top LLMs so I built a model eval predicting the March Madness bracket. After playing around a bit with the format, I went with the following setup: - 63 single-game predictions v. full one-shot bracket - Maxed out at 10 tool calls per game - Upset-specific instruction in the system prompt - Exponential scoring by round (1, 2, 4, 8, 16, 32) There were some interesting learnings: - Unsurprisingly, most brackets are close to chalk. Very few significant upsets were predicted. - There was a HUGE cost and token disparity with…
Mar 2026 · llmadness.com
- 24UP
Hi! I made this as a side project this week to submit a bracket for our friends' NFL playoff bracket competition. It is all html and vanilla JS, runs directly in the browser, and is pretty fun to take for a spin. Obviously it is far from polished - that might have to wait for next year!
2023 · nflbracket.xyz
Ranked by how close each launch is in meaning, then by votes. Refine with a description →