# Gemini 4 ArgonNon-thinking

> Source: Benchize (https://benchize.com) — https://benchize.com/models/gemini-4-argon-off. When citing or reusing this content, credit "Benchize" and link to https://benchize.com/models/gemini-4-argon-off.

Google

Canonical URL: https://benchize.com/models/gemini-4-argon-off
Last updated: Thu, 22 Oct 2026 04:30:12 GMT

Reproduction and quotation must name Benchize, link to the canonical HTML URL, and retain individual source citations.

Google

## Benchmarks

| Benchmark | Score | ± | Rank |  |
| --- | --- | --- | --- | --- |
| [ToneBench Scriptwriting](https://benchize.com/benchmarks/tonebench%3Ascripts.md) | 1,433.2 | Range 1,394.2–1,472.3 | 83 / 126 |  |
| ### Original source values \| Metric \| Value \| Unit \| Scope \| Direction \| \| --- \| --- \| --- \| --- \| --- \| \| `elo` \| 1433.2 \| rating \| reported \| Higher is better \| \| `overall` \| 74.65 \| percent \| reported \| Higher is better \| \| `anti_slop_numbers` \| 66.39 \| source_score \| rubric \| Higher is better \| \| `continuity_emotion` \| 78.45 \| source_score \| rubric \| Higher is better \| \| `cue_quality` \| 80.92 \| source_score \| rubric \| Higher is better \| \| `hook_strength` \| 79.61 \| source_score \| rubric \| Higher is better \| \| `length_adherence` \| 47.88 \| source_score \| rubric \| Higher is better \| \| `slop` \| 79.01 \| source_score \| rubric \| Higher is better \| \| `slop_score` \| 91.62 \| source_score \| rubric \| Higher is better \| \| `substance_accuracy` \| 80.2 \| source_score \| rubric \| Higher is better \| \| `tone_voice` \| 71.42 \| source_score \| rubric \| Higher is better \| \| `writing_quality` \| 73.61 \| source_score \| rubric \| Higher is better \| \| `youtube_best_practices` \| 79.31 \| source_score \| rubric \| Higher is better \| ### Configuration provider google Reasoning effort unknown scoreScope 10_task_current sourceConfiguration gemini-4-argon thinkingEnabled false ### Reported statistics Uncertainty Reported interval: 1,394.2–1,472.3 interval [1394.2,1472.3] rank 85 runCount 5 ### Source [Original source](https://benchmark.towardsai.com/data/leaderboard.json) Source tonebench Original model label Gemini 4 Argon (no thinking) Evaluated 2026-10-13 Observed 2026-10-21T16:32:48.862Z Evidence SHA-256 `4264338337f418d3ded7ace250cad64fe12cacbd4b79a312bfaf0ae9268a01c3` Source locator `/rows/84` |  |  |  |  |

---
Cite as: Gemini 4 ArgonNon-thinking — Benchize, https://benchize.com/models/gemini-4-argon-off (retrieved 2026-10-22)