Jigsaw Toxic Comment Classification
Nova 2 Omni Preview 57.8% leads since Dec 2025 Only in system cards Models label Wikipedia talk page comments for toxicity types such as threats, insults and identity hate. Labs report F1 or ROC AUC.
The data comes from a 2017 Kaggle competition. Amazon uses it as a content moderation test for Nova 2 with F1.
- Level
- Everyday Most adults, without training
- Scored
- Checked automatically A program checks the result against an answer key, unit tests or the expected final state.
- Answers
- Multiple choice
Nova 2 Omni Preview leads with 57.8% among models released by Dec 2025
Best score per model as labs report them in their own cards. Labs pick their own settings, so these compare less cleanly than independent runs.
The newest model with a score here came out in Dec 2025, and nobody has reported a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6 Astra
- Claude Opus 5.5
- GPT-6.1 Terra
- GPT-6.1 Sol
- and 16 more
- 1 Nova 2 Omni Preview 57.8%
- 2 Nova 2 Lite 56.5%
- 3 Nova 2.0 Pro Preview 54.7%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Nova 2 Omni Preview | 57.8% | Dec 2025 | Model card | |
| 2 | Nova 2 Lite | 56.5% | Dec 2025 | Model card | |
| 3 | Nova 2.0 Pro Preview | 54.7% | Dec 2025 | Model card |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Labs report it only in system cards
We read the headline results of 479 launch posts from 51 labs, and none of them list this benchmark. Some system cards do, below.
3 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 |
|---|---|---|---|---|
| 2 Dec 2025 | Nova 2 Omni Preview technical report | 57.8 | Jigsaw F1-score, content moderation, non-reasoning mode (Table 14) | Safety |
| 2 Dec 2025 | Nova 2 Lite technical report | 56.5 | Jigsaw F1-score, content moderation, non-reasoning mode (Table 14) | Safety |
| 2 Dec 2025 | Nova 2.0 Pro Preview technical report | 54.7 | Jigsaw F1-score, content moderation, non-reasoning mode (Table 14) | 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% - AgentDojo In use Agents do tool-use tasks while tools and data carry prompt injections. Attack success rate counts hijacked runs. Grok 4 Fast 0%
- MASK In use Measures whether a model contradicts its own elicited beliefs under pressure to lie. Honesty separated from accuracy.
Muse Spark Open 98.1% - 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. GPT-6 Astra 8.50%
- Agentic misalignment suite (Anthropic) In use Agents in simulated company settings face threats or goal conflicts that invite blackmail, leaking or sabotage. Score is the misaligned action rate. Claude Sonnet 4.5 0%