Media

11/26/2025

Behind the Scenes of Vibe Code Bench

Last week, we released Vibe Code Bench. This is our most ambitious benchmark to-date. I hope it will provide a useful signal for researchers and vibe-coders alike.

Rayan Krishnan

Media

11/21/2025

The Winners (and Losers) of This New Vibe-Coding Benchmark Will Surprise You

Media

11/13/2025

Why Nvidia Keeps Backing Would-Be Competitors to OpenAI

Media

10/26/2025

OpenAI's Less-Flashy Rival Might Have a Better Business Model

Model

Minimax M2.5 - another step forward for open-weight coding models

Vals AI

02/12/26

Model

Full results for GLM 5

Vals AI

02/12/26

Model

GLM 5 - the new frontier open-weight coding model

FAB v1.1 Released!

Claude Opus 4.6 is the new SOTA

Vals AI

02/05/26

Model

Qwen 3 Max Thinking Evaluated on Vals Index!

Vals AI

02/04/26

Benchmark

ProofBench Released: Evaluating Formal Mathematical Reasoning

Vals AI

01/30/2026

Model

Kimi K2.5 Evaluated on (almost) all benchmarks!

Vals AI

01/27/26

Model

Kimi K2.5 sets a new open-source standard

Vals AI

01/26/26

Benchmark

Results for Terminal-Bench 2.0 Released!

Vals AI

01/23/26

Vals AI News

Behind the Scenes of Vibe Code Bench

Join our mailing list to receive benchmark updates