Winogender
Gemma 2 9B 79.2% leads since Jul 2024 Only in system cards Models resolve pronouns in sentences about occupations. Accuracy shows whether gender stereotypes sway coreference.
In the authors’ words
We present an empirical study of gender bias in coreference resolution systems. We first introduce a novel, Winograd schema-style set of minimal pair sentences that differ only by pronoun gender. With these "Winogender schemas," we evaluate and confirm systematic gender bias in three publicly-available coreference resolution systems, and correlate this bias with real-world and textual gender statistics.
- 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
Gemma 2 9B leads with 79.2% among models released by Jun 2024
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 Jun 2024, 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 Gemma 2 9B 79.2%
- 2 Gemma 2 27B 77.2%
- 3 Gemma 7B 54.2%
- 4 Gemma 2B 51.3%
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Gemma 2 9B | 79.2% | Jul 2024 | Model card | |
| 2 | Gemma 2 27B | 77.2% | Jul 2024 | Model card | |
| 3 | Gemma 7B | 54.2% | Mar 2024 | Model card | |
| 4 | Gemma 2B | 51.3% | Mar 2024 | Model card |
2 models have held number one since 2023
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.
4 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 |
|---|---|---|---|---|
| 31 Jul 2024 | Gemma 2 9B technical report | 79.2 | Winogender, top-1, IT (Table 18) | Bias |
| 31 Jul 2024 | Gemma 2 27B technical report | 77.2 | Winogender, top-1, IT (Table 18) | Bias |
| 13 Mar 2024 | Gemma 7B technical report | 54.2 | Winogender, top-1, IT (Table 8) | Bias |
| 13 Mar 2024 | Gemma 2B technical report | 51.3 | Winogender, top-1, IT (Table 8) | Bias |
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%