Benchmark Almanac

Pigeonholing Partisans four-word generation

gemma-2-27b_instruct 60% tops its leaderboard Mistral-7B-Instruct-v0.1 51.5% leads the models we track
Not in model cards

Models use a survey respondent’s profile to generate four words describing supporters of each major US party. One measure counts how often raters identify the writer’s party.

Lyman and colleagues repeated the task with 12 models and 1,322 respondent profiles. They used GPT-4o to code the descriptions.

Released
September 2022
Kind
Social simulation
Level
Everyday
Scored
Graded by people
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
Strongest model tested
Llama 3-70B #182 on the capability index
Last model added
June 2024
Scores refreshed
November 20th, 2026
12
Entries on its own leaderboard, 6 models we track

gemma-2-27b_instruct tops the leaderboard with 60% Mistral-7B-Instruct-v0.1 leads with 51.5% among models released by June 2024

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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. The best model we track is Mistral-7B-Instruct-v0.1, at 51.5%. This view shows only models we track, each at its best.

The newest model with a score here came out in June 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 gemma-2-27b_instruct 60%
  2. 2 Mistral-7B-Instruct-v0.1 51.5%
  3. 3 llama-3-70b_instruct 51.1%
  4. 4 mistral-7b_base 46.5%
  5. 5 mixtral_instruct 46.3%
  6. 6 Llama 3-70B 44.9%
  7. 7 Llama 3-8B 41.9%
  8. 8 Mixtral 8x7B 41.8%
  9. 9 Gemma 2 27B 41.7%
  10. 10 llama-3-8b_instruct 33.5%
  11. 11 gemma-2-9b_instruct 23.5%
  12. 12 Gemma 2 9B 15.4%

Source: Official Pigeonholing Partisans four-word generation leaderboard

#EntryScoreSettingDateSource
1 gemma-2-27b_instruct 60% Official leaderboard
2 Mistral-7B-Instruct-v0.1 51.5% Sep 2023 Official leaderboard
3 llama-3-70b_instruct 51.1% Official leaderboard
4 mistral-7b_base 46.5% Official leaderboard
5 mixtral_instruct 46.3% Official leaderboard
6 Llama 3-70B 44.9% Apr 2024 Official leaderboard
7 Llama 3-8B 41.9% Apr 2024 Official leaderboard
8 Mixtral 8x7B 41.8% Dec 2023 Official leaderboard
9 Gemma 2 27B 41.7% Jun 2024 Official leaderboard
10 llama-3-8b_instruct 33.5% Official leaderboard
11 gemma-2-9b_instruct 23.5% Official leaderboard
12 Gemma 2 9B 15.4% Jun 2024 Official leaderboard
#ModelScoreSettingDateSource
1 Mistral-7B-Instruct-v0.1 51.5% Sep 2023 Official leaderboard
2 Llama 3-70B 44.9% Apr 2024 Official leaderboard
3 Llama 3-8B 41.9% Apr 2024 Official leaderboard
4 Mixtral 8x7B 41.8% Dec 2023 Official leaderboard
5 Gemma 2 27B 41.7% Jun 2024 Official leaderboard
6 Gemma 2 9B 15.4% Jun 2024 Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Mistral AI
Own leaderboard Not tested since Jun 2024

Source: Official Pigeonholing Partisans four-word generation leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
On the benchmark’s own leaderboard
0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Mistral-7B-Instruct-v0.1 0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Mistral-7B-Instruct-v0.1

Source: Official Pigeonholing Partisans four-word generation 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 Forecasting

All 47 in Forecasting
  • ForecastBench In use Models give probabilities for 500 auto-generated questions per round about future events, drawn from prediction markets and time-series datasets. Forecasts are scored with difficulty-adjusted Brier scores once the questions resolve. GPT-5.5 0.11
  • Prophet Arena In use Models and agents forecast open Kalshi prediction-market events and are scored once the events resolve. The live board ranks a difficulty-adjusted Arena score and also reports calibration error and market return. Claude Opus 5.5 86.2
  • Guesswork (The Aggregate) Not in model cards Models predict benchmark scores before publication. The maker ranks forecasts by mean absolute error after scaling each error by the variation in that benchmark’s scores. GPT-6 Astra 0.56
  • AGI-Pilled Bench Not in model cards Models forecast when AI will reach milestones that already happened in 2026. The score is the median years after 2026 across the forecast tasks. Claude Fable 5.2 6.50
  • Dutch Book Bench Not in model cards Models assign probabilities to related events in separate conversations. The grader checks whether inconsistent probabilities let a bettor guarantee a profit. Gemini 3.8 Flash 89.2%
  • Echo General AI Prediction Leaderboard Not in model cards Models forecast unresolved events drawn from prediction markets, synthesized news questions and expert-written questions. Forecasts made at aligned times are compared in pairwise battles, and an Elo fit ranks the models. DeepSeek-V4-Pro 1,018

Data audit

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in June 2024, for Gemma 2 27B. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
  • Pass Independent runs Scores from the official leaderboard (12 entries).
  • Pass Models scored 6 models we track, plus 6 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in June 2024, for Gemma 2 27B.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Llama 3-70B (#182).
  • Pass Headroom The best is 51.5%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on github.com: 6 rows for models we track and 6 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.

How we check