EsBBQ
Models answer Spanish questions about people in ambiguous and unambiguous situations. The evaluation measures how social stereotypes affect their choices.
- Made by
- Valle Ruiz-Fernández and colleagues
- Released
- July 2025
- Kind
- Bias, fairness and politics
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Propensity
- Behavior
- Bias
- Language
- Spanish
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Based on
- BBQ (Bias Benchmark for QA)
- Strongest model tested
-
Llama 3.1-8B #203 on the capability index
- Last model added
- March 2025
- Scores refreshed
- November 20th, 2026
Qwen2.5-7B leads with 85% among models released by March 2025 Qwen2.5-7B leads with 85% among models released by March 2025
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall accuracy, so this is the plain mean of ambiguous and disambiguated context accuracy. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in March 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 85.0
Qwen2.5-7B
- 81.0
Gemma 3 12B
- 77.0
Qwen2.5-3B
- 76.5 Mistral-v0.3 7B instruct
- 69.0
Gemma 3 4B
- 67.5
Llama 3.1-8B
- 64.5 EuroLLM 9B instruct
- 57.0 Occiglot-EU5 7B instruct
- 55.5
Qwen2.5-1.5B
- 53.0
Gemma 3 1B
- 50.0 Salamandra 7B instruct
- 47.5
Gemma 3 12B PT
- 46.5 EuroLLM 9B base
- 46.5 Llama-3.1 8B base
- 46.0 Qwen2.5 7B base
- 45.5 Occiglot-EU5 7B base
- 45.5 Tower-v0.1 13B instruct
- 45.0 Qwen2.5 3B base
- 45.0
Mistral 7B v0.3
- 44.5 EuroLLM 1.7B base
- 43.5 Salamandra 7B base
- 43.5 Tower-v0.1 13B base
- 42.5 Qwen2.5 1.5B base
- 42.0 Tower-v0.1 7B instruct
- 41.5
Gemma 3 4B PT
- 40.0 FLOR 1.3B base
- 39.0 FLOR 6.3B base
- 39.0 Tower-v0.1 7B base
- 38.0 FLOR 1.3B instruct
- 37.0 Salamandra 2B base
- 35.5
Gemma 3 1B PT
- 34.5 Salamandra 2B instruct
- 33.5 EuroLLM 1.7B instruct
- 33.5 FLOR 6.3B instruct
- 1
Qwen2.5-7B Zero-shot 85%
- 2
Gemma 3 12B Zero-shot 81%
- 3
Qwen2.5-3B Zero-shot 77%
- 4 Mistral-v0.3 7B instruct Zero-shot 76.5%
- 5
Gemma 3 4B Zero-shot 69%
- 6
Llama 3.1-8B Zero-shot 67.5%
- 7 EuroLLM 9B instruct Zero-shot 64.5%
- 8 Occiglot-EU5 7B instruct Zero-shot 57%
- 9
Qwen2.5-1.5B Zero-shot 55.5%
- 10
Gemma 3 1B Zero-shot 53%
- 11 Salamandra 7B instruct Zero-shot 50%
- 12
Gemma 3 12B PT Zero-shot 47.5%
- 13 EuroLLM 9B base Zero-shot 46.5%
- 14 Llama-3.1 8B base Zero-shot 46.5%
- 15 Qwen2.5 7B base Zero-shot 46%
- 16 Occiglot-EU5 7B base Zero-shot 45.5%
- 17 Tower-v0.1 13B instruct Zero-shot 45.5%
- 18 Qwen2.5 3B base Zero-shot 45%
- 19
Mistral 7B v0.3 Zero-shot 45%
- 20 EuroLLM 1.7B base Zero-shot 44.5%
- 21 Salamandra 7B base Zero-shot 43.5%
- 22 Tower-v0.1 13B base Zero-shot 43.5%
- 23 Qwen2.5 1.5B base Zero-shot 42.5%
- 24 Tower-v0.1 7B instruct Zero-shot 42%
- 25
Gemma 3 4B PT Zero-shot 41.5%
- 26 FLOR 1.3B base Zero-shot 40%
- 27 FLOR 6.3B base Zero-shot 39%
- 28 Tower-v0.1 7B base Zero-shot 39%
- 29 FLOR 1.3B instruct Zero-shot 38%
- 30 Salamandra 2B base Zero-shot 37%
- 31
Gemma 3 1B PT Zero-shot 35.5%
- 32 Salamandra 2B instruct Zero-shot 34.5%
- 33 EuroLLM 1.7B instruct Zero-shot 33.5%
- 34 FLOR 6.3B instruct Zero-shot 33.5%
Source: The EsBBQ paper
- 1
Qwen2.5-7B Zero-shot 85%
- 2
Gemma 3 12B Zero-shot 81%
- 3
Qwen2.5-3B Zero-shot 77%
- 4
Gemma 3 4B Zero-shot 69%
- 5
Llama 3.1-8B Zero-shot 67.5%
- 6
Qwen2.5-1.5B Zero-shot 55.5%
- 7
Gemma 3 1B Zero-shot 53%
- 8
Gemma 3 12B PT Zero-shot 47.5%
- 9
Mistral 7B v0.3 Zero-shot 45%
- 10
Gemma 3 4B PT Zero-shot 41.5%
- 11
Gemma 3 1B PT Zero-shot 35.5%
Source: The EsBBQ paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 85% | Zero-shot | Sep 2024 | Official leaderboard |
| 2 | | 81% | Zero-shot | Mar 2025 | Official leaderboard |
| 3 | | 77% | Zero-shot | Sep 2024 | Official leaderboard |
| 4 | Mistral-v0.3 7B instruct 7B | 76.5% | Zero-shot | Official leaderboard | |
| 5 | | 69% | Zero-shot | Mar 2025 | Official leaderboard |
| 6 | | 67.5% | Zero-shot | Jul 2024 | Official leaderboard |
| 7 | EuroLLM 9B instruct 9B | 64.5% | Zero-shot | Official leaderboard | |
| 8 | Occiglot-EU5 7B instruct 7B | 57% | Zero-shot | Official leaderboard | |
| 9 | | 55.5% | Zero-shot | Sep 2024 | Official leaderboard |
| 10 | | 53% | Zero-shot | Mar 2025 | Official leaderboard |
| 11 | Salamandra 7B instruct 7B | 50% | Zero-shot | Official leaderboard | |
| 12 | | 47.5% | Zero-shot | Mar 2025 | Official leaderboard |
| 13 | EuroLLM 9B base 9B | 46.5% | Zero-shot | Official leaderboard | |
| 14 | Llama-3.1 8B base 8B | 46.5% | Zero-shot | Official leaderboard | |
| 15 | Qwen2.5 7B base 7B | 46% | Zero-shot | Official leaderboard | |
| 16 | Occiglot-EU5 7B base 7B | 45.5% | Zero-shot | Official leaderboard | |
| 17 | Tower-v0.1 13B instruct 13B | 45.5% | Zero-shot | Official leaderboard | |
| 18 | Qwen2.5 3B base 3B | 45% | Zero-shot | Official leaderboard | |
| 19 | | 45% | Zero-shot | Sep 2023 | Official leaderboard |
| 20 | EuroLLM 1.7B base 1.7B | 44.5% | Zero-shot | Official leaderboard | |
| 21 | Salamandra 7B base 7B | 43.5% | Zero-shot | Official leaderboard | |
| 22 | Tower-v0.1 13B base 13B | 43.5% | Zero-shot | Official leaderboard | |
| 23 | Qwen2.5 1.5B base 1.5B | 42.5% | Zero-shot | Official leaderboard | |
| 24 | Tower-v0.1 7B instruct 7B | 42% | Zero-shot | Official leaderboard | |
| 25 | | 41.5% | Zero-shot | Mar 2025 | Official leaderboard |
| 26 | FLOR 1.3B base 1.3B | 40% | Zero-shot | Official leaderboard | |
| 27 | FLOR 6.3B base 6.3B | 39% | Zero-shot | Official leaderboard | |
| 28 | Tower-v0.1 7B base 7B | 39% | Zero-shot | Official leaderboard | |
| 29 | FLOR 1.3B instruct 1.3B | 38% | Zero-shot | Official leaderboard | |
| 30 | Salamandra 2B base 2B | 37% | Zero-shot | Official leaderboard | |
| 31 | | 35.5% | Zero-shot | Mar 2025 | Official leaderboard |
| 32 | Salamandra 2B instruct 2B | 34.5% | Zero-shot | Official leaderboard | |
| 33 | EuroLLM 1.7B instruct 1.7B | 33.5% | Zero-shot | Official leaderboard | |
| 34 | FLOR 6.3B instruct 6.3B | 33.5% | Zero-shot | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 85% | Zero-shot | Sep 2024 | Official leaderboard |
| 2 | | 81% | Zero-shot | Mar 2025 | Official leaderboard |
| 3 | | 77% | Zero-shot | Sep 2024 | Official leaderboard |
| 4 | | 69% | Zero-shot | Mar 2025 | Official leaderboard |
| 5 | | 67.5% | Zero-shot | Jul 2024 | Official leaderboard |
| 6 | | 55.5% | Zero-shot | Sep 2024 | Official leaderboard |
| 7 | | 53% | Zero-shot | Mar 2025 | Official leaderboard |
| 8 | | 47.5% | Zero-shot | Mar 2025 | Official leaderboard |
| 9 | | 45% | Zero-shot | Sep 2023 | Official leaderboard |
| 10 | | 41.5% | Zero-shot | Mar 2025 | Official leaderboard |
| 11 | | 35.5% | Zero-shot | Mar 2025 | Official leaderboard |
Rankings by part
We read 2 parts from the benchmark’s paper: Ambiguous context accuracy and Disambiguated context accuracy. Each ranks models on one part of the test. Qwen2.5-7B leads Ambiguous context accuracy and Llama 3.1-8B leads Disambiguated context accuracy. Arrows show how far a model moved from its overall rank among the models we track.
Ambiguous context accuracy
11 models we track have a score here.
- 1
Qwen2.5-7B 93%
- 2
Qwen2.5-3B ↑1 86%
- 3
Gemma 3 12B ↓1 79%
- 4
Gemma 3 4B 59%
- 5
Gemma 3 1B ↑2 54%
- 6
Llama 3.1-8B ↓1 52%
- 7
Qwen2.5-1.5B ↓1 42%
- 8
Gemma 3 1B PT ↑3 20%
- 9
Mistral 7B v0.3 14%
- 10
Gemma 3 4B PT 14%
Disambiguated context accuracy
11 models we track have a score here.
- 1
Llama 3.1-8B ↑4 83%
- 2
Gemma 3 12B 83%
- 3
Gemma 3 12B PT ↑5 83%
- 4
Gemma 3 4B 79%
- 5
Qwen2.5-7B ↓4 77%
- 6
Mistral 7B v0.3 ↑3 76%
- 7
Qwen2.5-1.5B ↓1 69%
- 8
Gemma 3 4B PT ↑2 69%
- 9
Qwen2.5-3B ↓6 68%
- 10
Gemma 3 1B ↓3 52%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The EsBBQ paper
Qwen2.5-7B on the official leaderboard passed 85% in September 2024
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official EsBBQ leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
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%
- Covert misbehavior (Thinking Machines) In use Agentic tasks that check whether a model misbehaves and conceals it. Scored by the rate of covert misbehavior.
Inkling 2 Mini 8.30%
- Destructive actions (Thinking Machines) In use Agentic tasks that check whether a model takes destructive actions it was not authorized to take. Scored by the rate of destructive actions.
Inkling 2 Small 4.70%
- Misbehavior (Thinking Machines) In use Agentic tasks that check whether a model fabricates results, ignores instructions or hides what it did when a task is hard. Scored by the rate of misbehavior.
Inkling 2 Mini 9.80%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (34 entries).
- Pass Models scored 11 models we track, plus 23 other entries on its leaderboard.
- Note Newest score The newest came 20 months ago, in March 2025, for Gemma 3 12B. That’s expected for a saturated test.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Llama 3.1-8B (#203).
- Note Headroom Saturated. The best is 85%, past 85% since September 2024.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 11 rows for models we track and 23 other entries at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.