---
format: "aidr-story-markdown/v1"
id: "73fef3cd65f70d79d8da8cf077245384022b08442df6dae695265edc460d7fe9"
canonical_url: "https://aidr.today/73fef3cd?lang=en"
title: "Google's Gemini 4 Carbon Tops Mercor's APEX-Agents Leaderboard With First Mean Score Above 90%"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-02T06:51:34.000Z"
category: "Models"
topics: ["google","agent"]
source_urls: ["https://marketbrief.now/ai/googles-gemini-4-carbon-tops-mercors-apex-agents-leaderboard-with-first-36f3932d","https://x.com/sundarpichai/status/2115489219804352921","https://x.com/arena/status/2115495002998751262","https://x.com/mercor/status/2116226723968872959","https://x.com/ArtificialAnlys/status/2115494553780367384","https://x.com/vector__news/status/2115941930857124080","https://x.com/Waguri_Kaoruko8/status/2116362413796663530","https://x.com/tulseedoshi/status/2115491157807677867"]
summary: "Google's Gemini 4 Carbon debuted at No. 1 on Mercor's APEX-Agents leaderboard with a 90.4% mean. Carbon achieved the only evaluated model mean above 90% across multi-step tasks in investment banking, management consulting, and corporate law. Perplexity CEO Aravind Srinivas stated early evaluations showed Gemini 4 Carbon set a state-of-the-art score on the Wide-And-Deep-Research (WANDR) benchmark."
---

# Google's Gemini 4 Carbon Tops Mercor's APEX\-Agents Leaderboard With First Mean Score Above 90%

> [Open the canonical story](<https://aidr.today/73fef3cd?lang=en>)

**Published:** 2026-11-02T06:51:34.000Z
**Category:** Models
**Topics:** google, agent

## Summary

Google's Gemini 4 Carbon debuted at No\. 1 on Mercor's APEX\-Agents leaderboard with a 90\.4% mean\. Carbon achieved the only evaluated model mean above 90% across multi\-step tasks in investment banking, management consulting, and corporate law\. Perplexity CEO Aravind Srinivas stated early evaluations showed Gemini 4 Carbon set a state\-of\-the\-art score on the Wide\-And\-Deep\-Research \(WANDR\) benchmark\.

## Sources

- [Story source](<https://marketbrief.now/ai/googles-gemini-4-carbon-tops-mercors-apex-agents-leaderboard-with-first-36f3932d>)
- [Story source](<https://x.com/sundarpichai/status/2115489219804352921>)
- [Story source](<https://x.com/arena/status/2115495002998751262>)
- [Story source](<https://x.com/mercor/status/2116226723968872959>)
- [Story source](<https://x.com/ArtificialAnlys/status/2115494553780367384>)
- [Story source](<https://x.com/vector__news/status/2115941930857124080>)
- [Story source](<https://x.com/Waguri_Kaoruko8/status/2116362413796663530>)
- [Supporting source](<https://x.com/tulseedoshi/status/2115491157807677867>)