Tone
An automated evaluation measures whether model refusals are objective, neutral and not preachy.
In-house Google DeepMind evaluation. Model cards report only the change against an earlier Gemini model.
- Made by
- Google DeepMind
- Released
- April 2025
- Kind
- Refusing harmful requests
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- Kept private
- Last in a system card
- October 2026
- Last model added
- October 2026
16
System cards report it, from 1 lab
No scores here yet
No lab, leaderboard or Epoch AI run has reported a score for Tone yet.
Labs report it only in system cards
We read the headline results of 522 launch posts from 52 labs, and none of them list this benchmark. Some system cards do, below.
16 system cards report it, from 1 lab
Besides launch posts, we read the system cards, model cards and technical reports labs publish with a release. They report far more, including safety and frontier-risk tests.
| Date | Document | Score | As the document writes it | Section |
|---|---|---|---|---|
| Oct 13, 2026 |  Gemini 4 Argon system card | Tone score, two suites with no overall: text tone 96.5%, multimodal tone 98.1% (Figure 5.16) | Safety | |
| Oct 13, 2026 | Gemini 4 Argon model card | Tone (higher is better): +5.50pp vs Gemini 3.1 Pro, no absolute rate (safety table, p.9) | Safety | |
| Sep 2, 2026 | Gemini 3.8 Flash model card | Tone (higher is better): +0.2pp vs Gemini 3.7 Flash, no absolute rate (safety table, p.7) | Safety | |
| Aug 13, 2026 | Gemini 3.7 Flash model card | Tone (higher is better): -0.47pp vs Gemini 3.6 Flash, no absolute rate (safety table, p.7) | Safety | |
| Jul 21, 2026 | Gemini 3.6 Flash model card | Tone (higher is better): -3.31% vs Gemini 3.5 Flash, printed as percentage point change, no absolute rate (safety table, p.5) | Safety | |
| Jul 21, 2026 | Gemini 3.5 Flash-Lite model card | Tone (higher is better): +3.04% vs Gemini 3.1 Flash-Lite, printed as percentage point change, no absolute rate (safety table, p.5) | Safety | |
| May 19, 2026 | Gemini 3.5 Flash model card | Tone (higher is better): +8.9% vs Gemini 3 Flash, no absolute rate (safety table, p.6) | Safety | |
| Mar 3, 2026 | Gemini 3.1 Flash-Lite model card | Tone (higher is better): +14.59% vs Gemini 2.5 Flash-Lite, no absolute rate (safety table, p.6) | Safety | |
| Feb 19, 2026 | Gemini 3.1 Pro model card | Tone (higher is better): +0.02% vs Gemini 3.0 Pro, no absolute rate (safety table, p.6) | Safety | |
| Sep 26, 2025 | Gemini 2.5 Flash model card | Tone: +9.7% vs Gemini 2.0 Flash, Thinking, +9.5% Non-thinking, change only, no absolute rate (safety table, p.9) | Safety | |
| Jul 7, 2025 | Gemini 2.5 Pro technical report | Tone: ↑18.4% vs Gemini 1.5 Pro 002, relative change only, no absolute rate (Table 7) | Safety | |
| Jul 7, 2025 | Gemini 2.5 Flash technical report | Tone: ↑7.9% vs Gemini 1.5 Flash 002, relative change only, no absolute rate (Table 7) | Safety | |
| Apr 29, 2025 | Gemini 2.5 Flash model card | Tone: +10.10% vs Gemini 2.0 Flash, change only, no absolute rate (safety table, p.7) | Safety | |
| Apr 28, 2025 | Gemini 2.5 Pro model card | Tone: +5.70% vs Gemini 1.5 Pro 002, change only, no absolute rate (safety table, p.6) | Safety | |
| Apr 15, 2025 | Gemini 2.0 Flash model card | Tone: +1.50% vs Gemini 1.5 Pro 002, change only, no absolute rate (safety table, p.5) | Safety | |
| Apr 10, 2025 | Gemini 2.0 Flash-Lite model card | Tone: +4.40% vs Gemini 1.5 Pro 002, change only, no absolute rate (safety table, p.5) | Safety |
More in Safety and alignment
- FORTRESS In use Paired adversarial and benign national-security misuse prompts. Rubric-graded risk score on adversarial and over-refusal score on benign prompts. Claude Opus 5.5 5.78%
- StrongREJECT In use Forbidden-prompt jailbreak benchmark with a rubric grader that scores how useful a non-refusal actually is.
Inkling 98.6% - Gray Swan IPI Arena benchmark In use Indirect prompt-injection attacks from public red-teaming competitions replayed on tool, coding and browser agents. Attack success rate at k attempts. Gemini 4 Carbon 0%
- DistressBench In use Models reply as a chatbot to 718 simulated users in psychological crisis, in single-turn and multi-turn chats. Three judge models score replies against clinician-written rubrics.
Muse Spark 1.2 88.4% - Lakera B3 (Backbone Breaker Benchmark) In use Crowdsourced prompt-injection attacks hit backbone LLMs inside agent threat snapshots at three defense levels. The score is attack resistance, 100 minus the board's vulnerability percentage. Claude Opus 4.5 89%
- IHEval In use Models face conflicts between system, user and tool instructions. Reports a composite score for following the higher-priority instruction. GPT-4o 70%