search arena leaderboard

Sharks, Lee

SPXI instrument · method 0.9 of 87, level 0 (Measurement): Capture Registry (longitudinal observation). An instrument of SPXI, the Semantic Packet for eXchange & Indexing; the whole practice is itemized at spxi.dev/methods.

Capture Registry › capture search-arena-leaderboard-aio-20261029

One record of the canonical Capture Registry (EA-WG-CAPTURES-01), cited at https://www.alexanarch.org/captures/search-arena-leaderboard-aio-20261029/. the canonical Capture Registry (version 12.365) · the address page · this card in the gallery · this record as data · table of contents.

AXN:0AB6.CAPTURE — this address. Each observation below is one AXN, sealed with its analysis and measures; the identifier names the reading together with the response it reads.
AXN:0AB6.CAPTURE.⛳🧱🟢⏪🎻🏛️ — Google AI Overview, 2026-10-29 · sealed observation (SHA-256 5422c4d78a20fc30…)

Machine Reception2026-10-29

search arena leaderboard

Originator: arena.ai · outside the archive (out-universe) · dataset · SPXI treatment: partial

BROAD MATCH

no
image

THE SEARCH ARENA LEADERBOARD, ON GOOGLE'S AI OVERVIEW, SIGNED OUT, 2026-10-29: a pointer to 'the AI Search Leaderboard and the main Arena Leaderboard' and a table, 'Top Models on the AI Search Leaderboard', of eleven models with provider and Elo rating, from GPT-5.6 Sol (xHigh), OpenAI, 1261 ± 6, to ERNIE 5.1, Baidu, 1227 ± 9. Two cards, both Arena's.

Full record — 1,988 characters, 2 sources

Capture record

captured: 2026-10-29
surface: Google AI Overview
auth state: signed out, incognito
evidence class: paste
PER (historical scalar): 0.5
PER units retained: inst, src
citations read: 2
observation id: OBS-cd6ab4746f08
address id: ADDR-ad4b00d7a1f0

Reading

The innocent reading first. Asked for the leaderboard, the Overview gives it: the top models and their ratings, with links to the boards.

Findings

A TABLE IN THE ENTITY'S PLACE. No operator, no method (head-to-head human votes), no counts, and none of the dataset paper's findings on citation; the composition is a table.
THE TABLE AGAINST THE PAGE. The leaderboard as this record's fetcher read it on 2026-10-29 states its update as 25 February 2026, 22 models and 247,944 votes, its first row Anthropic at 1255 ± 10, its second xAI at 1225 ± 8. The composed table's ratings, providers and order do not match it. Which page is current is not established here: Google may hold a later render. Checked 2026-10-29 against the MMRS meta-aggregator record of 2026-10-28 and the entity's own pages, re-read the same day.

Analysis analyst prose, not machine text

At an address naming the leaderboard, the Overview returns rankings and no account of the leaderboard; its figures cannot be reconciled with the page as read. The record keeps the entity; the capture keeps what was composed in its place.

Machine text, verbatim

CAPTURE-TIME VERBATIM RECORD — paste of the expanded Overview with its source cards · complete as supplied · READ IN FULL 2026-10-29

[Google AI Overview at the query, signed out and incognito (operator defaults of 2026-10-01 and 2026-10-14), 2026-10-29. The paste is the Overview expanded (the 'AI Mode Conversation' view, with the source cards that follow the answer); the 'You said' line carries the query twice, run together, and is given once here. Inline links are Google redirect URLs, kept as pasted. The closing disclaimer cut.] [QUERENT] search arena leaderboard [SYSTEM] You can view the live model rankings and evaluations on the AI Search Leaderboard and the main Arena Leaderboard. Top Models on the AI Search Leaderboard Rank Model Provider Elo Rating 1 GPT-5.6 Sol (xHigh) OpenAI 1261 ± 6 2 Qwen3.8-Max Alibaba 1261 ± 13 3 Claude Opus 4.6 (Search) Anthropic 1251 ± 5 4 GPT-5.5 (Search) OpenAI 1247 ± 5 5 Claude Fable 5.1 (High) Anthropic 1246 ± 7 6 Claude Opus 5 (High) Anthropic 1242 ± 7 7 GPT-6 Astra (Max) OpenAI 1234 ± 8 8 GPT-6.1 Sol (Max) OpenAI 1233 ± 9 9 Claude Opus 4.7 Anthropic 1230 ± 5 10 Claude Fable 5 (High) Anthropic 1229 ± 7 11 ERNIE 5.1 Baidu 1227 ± 9 Would you like to explore leaderboards for a specific category like coding, vision, or image generation? Arena AI

Sources (2) as cited, and as the copy produced them

Arena AI third_party
AI Search Leaderboard: Top Models for Research
AI Search Leaderboard: Top Models for Research Start Voting Agent Chat Code Start Voting Agent Chat Code Image Video View overall rankings across LLMs with inte...
as pastedAI Search Leaderboard: Top Models for Research AI Search Leaderboard: Top Models for Research Start Voting Agent Chat Code Start Voting Agent Chat Code Image Video View overall rankings across LLMs with inte... Arena AI
Arena AI third_party
Arena Leaderboard: Official AI Model Rankings & Benchmarks
GPT-6.1 Terra is #8 in Agent · Max Kimi K3.1 Pro is #9 in WebDev · Max MAI-Image-2.7-Preview is #3 in Image Edit Spark-X2.6 is #71 in WebDev Krea 3 Ultra is #9 ...
as pastedArena Leaderboard: Official AI Model Rankings & Benchmarks GPT-6.1 Terra is #8 in Agent · Max Kimi K3.1 Pro is #9 in WebDev · Max MAI-Image-2.7-Preview is #3 in Image Edit Spark-X2.6 is #71 in WebDev Krea 3 Ultra is #9 ...

↻ Re-run permalink