MODEL REPORT · OVERALL #3

Gemini 4 Argon

Third among 13 tested configurations: 42.46 V2WScore, 19.6% task success and 91.0% build rate. Inspect the component metrics and actual successful and failed executions.

Published result snapshot · 27 October 2026

Gemini 4 Argon / VIDEO2WORLD
42.46/ 100
V2WSCORE
RESULT SNAPSHOT

The measured result.

The overall score combines functionality, geometry and dynamics, with executability as a gate. Gemini's V8 result was published on 27 October 2026. Comparison rows use the same 222-instance, 39-family score scope and scoring contract, while retaining their original publication dates. The paper's results are a separate historical set.

ModelV2WScore ↑Success ↑Progress ↑
#1 · Claude Opus 5.552.4133.6%0.61
#2 · Claude Fable 5.144.1322.2%0.45
#4 · GPT-6.1 Sol41.1910.9%0.30
COMPONENT METRICS

Beyond the overall score.

MetricValueCoverage
V2WScore42.46n=222 / 222
Task Success19.6%n=222 / 222
Stage Progress0.41n=204 / 222
Scene CD5.50 cmn=202 / 222
Object Shape CD1.04 cmn=201 / 222
Object Size Error3.09 cmn=201 / 222
Terminal Relative Translation Error32.38 cmn=152 / 222
Terminal Relative Rotation Error107.02 degn=73 / 222
Fixed-ref Task11.4%n=172 / 222
Fixed-ref Progress0.24n=172 / 222
Fixed-ref Translation APE18.83 cmn=172 / 222
Build Rate91.0%n=213 / 222

Gemini 4 Argon V8 · published 27 October 2026. Formal V2WScore uses all 222 instances across 39 task families. Component metrics are family-macro averages with their own finite coverage; task success is not a passed-instance count. Earlier model records retain their own publication dates. This report reads published records; it does not represent a fresh runtime reevaluation. Result snapshot and provenance ↗