Beemo
Detectors distinguish human writing from model outputs, including texts revised by experts or other models.
- Made by
- Toloka and collaborators
- Released
- November 2024
- Kind
- Composite indices
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Interaction
- Single turn
- Items from
- Written by experts, Generated
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
Falcon-7B #246 on the capability index
- Last model added
- June 2024
- Scores refreshed
- November 20th, 2026
Qwen2-7B leads with 74.1% among models released by June 2024 Qwen2-7B leads with 74.1% among models released by June 2024
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 score, so this is the plain mean of its seven AUROC comparisons. Where a model ran with several settings or harnesses, we keep its best. Every run is in the next chart. 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 June 2024, 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
- 1
Qwen2-7B Log Probability 74.1%
- 2
Falcon-7B Log Probability 74%
- 3 Binoculars 71.1%
- 4
OPT-1.3B Log Probability 65.7%
- 5 MAGE 64.3%
- 6 AIGC MPU 62.4%
- 7 GPT-2 (1.5B) DetectGPT 62.4%
- 8 OpenAI RoBERTa-base 59.5%
- 9 OpenAI RoBERTa-large 57.5%
- 10 RADAR 49.8%
Source: The Beemo paper
- 1
Qwen2-7B Log Probability 74.1%
- 2
Falcon-7B Log Probability 74%
- 3
OPT-1.3B Log Probability 65.7%
- 4 GPT-2 (1.5B) DetectGPT 62.4%
Source: The Beemo paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 74.1% | Log Probability | Jun 2024 | Official leaderboard |
| 2 | | 74% | Log Probability | Apr 2023 | Official leaderboard |
| 3 | Binoculars | 71.1% | Official leaderboard | ||
| 4 | | 65.7% | Log Probability | May 2022 | Official leaderboard |
| 5 | MAGE | 64.3% | Official leaderboard | ||
| 6 | AIGC MPU | 62.4% | Official leaderboard | ||
| 7 | GPT-2 (1.5B) | 62.4% | DetectGPT | Nov 2019 | Official leaderboard |
| 8 | OpenAI RoBERTa-base | 59.5% | Official leaderboard | ||
| 9 | OpenAI RoBERTa-large | 57.5% | Official leaderboard | ||
| 10 | RADAR | 49.8% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 74.1% | Log Probability | Jun 2024 | Official leaderboard |
| 2 | | 74% | Log Probability | Apr 2023 | Official leaderboard |
| 3 | | 65.7% | Log Probability | May 2022 | Official leaderboard |
| 4 | GPT-2 (1.5B) | 62.4% | DetectGPT | Nov 2019 | Official leaderboard |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The Beemo paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Log Probability | 74.1% | ||||
| Log Probability | 74% | ||||
| Log-Rank | 73.5% | ||||
| Log-Rank | 73.1% | ||||
| DetectLLM Likelihood Log-Rank Ratio | 68.1% | ||||
| DetectGPT | 67.8% | ||||
| DetectLLM Likelihood Log-Rank Ratio | 66.9% | ||||
| DetectGPT | 66.6% | ||||
| DetectLLM Normalized Perturbed Log-Rank | 66% | ||||
| Log Probability | 65.7% | ||||
| Rank | 64.9% | ||||
| DetectGPT | 64.9% | ||||
| Rank | 64.6% | ||||
| Log-Rank | 64.3% | ||||
| DetectLLM Normalized Perturbed Log-Rank | 63.8% | ||||
| GPT-2 (1.5B) | DetectGPT | 62.4% | |||
| GPT-2 (1.5B) | Log-Rank | 62.4% | |||
| GPT-2 (1.5B) | Log Probability | 62.2% | |||
| DetectLLM Normalized Perturbed Log-Rank | 61.4% | ||||
| GPT-2 (1.5B) | DetectLLM Likelihood Log-Rank Ratio | 61% | |||
| GPT-2 (1.5B) | DetectLLM Normalized Perturbed Log-Rank | 60.2% | |||
| Rank | 59.6% | ||||
| DetectLLM Likelihood Log-Rank Ratio | 58.3% | ||||
| GPT-2 (1.5B) | Rank | 56.1% | |||
| GPT-2 (1.5B) | Entropy | 43.5% | |||
| Entropy | 42.6% | ||||
| Entropy | 31.3% | ||||
| Entropy | 24.3% |
Scores at each effort level
Models the leaderboard ran at two or more effort levels. We don’t have enough cost data here to say what the extra effort costs.
Source: The Beemo paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| Log Probability | 74.1% | ||||
| Log Probability | 74% | ||||
| Log-Rank | 73.5% | ||||
| Log-Rank | 73.1% | ||||
| DetectLLM Likelihood Log-Rank Ratio | 68.1% | ||||
| DetectGPT | 67.8% | ||||
| DetectLLM Likelihood Log-Rank Ratio | 66.9% | ||||
| DetectGPT | 66.6% | ||||
| DetectLLM Normalized Perturbed Log-Rank | 66% | ||||
| Log Probability | 65.7% | ||||
| Rank | 64.9% | ||||
| DetectGPT | 64.9% | ||||
| Rank | 64.6% | ||||
| Log-Rank | 64.3% | ||||
| DetectLLM Normalized Perturbed Log-Rank | 63.8% | ||||
| GPT-2 (1.5B) | DetectGPT | 62.4% | |||
| GPT-2 (1.5B) | Log-Rank | 62.4% | |||
| GPT-2 (1.5B) | Log Probability | 62.2% | |||
| DetectLLM Normalized Perturbed Log-Rank | 61.4% | ||||
| GPT-2 (1.5B) | DetectLLM Likelihood Log-Rank Ratio | 61% | |||
| GPT-2 (1.5B) | DetectLLM Normalized Perturbed Log-Rank | 60.2% | |||
| Rank | 59.6% | ||||
| DetectLLM Likelihood Log-Rank Ratio | 58.3% | ||||
| GPT-2 (1.5B) | Rank | 56.1% | |||
| GPT-2 (1.5B) | Entropy | 43.5% | |||
| Entropy | 42.6% | ||||
| Entropy | 31.3% | ||||
| Entropy | 24.3% |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The Beemo paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official Beemo 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 Other
- Artificial Analysis Intelligence Index v5 In use Version 5 of Artificial Analysis's index: nine evaluations in four equal categories, most with private test sets, run three times each in its own agent harness. Claude Fable 5.2 64.6
- Personal Superintelligence Index (Meta) In use Meta's composite of seven personal and knowledge-work evals: Agents' Last Exam, AutomationBench-AA, FocusBench, JobBench, GDP.pdf, VBT and DRACO.
- Vals Science Index In use Agents are scored on the equal average of BioMysteryBench, MysteryMechanism and Terminal-Bench-Science. GPT-6.2 Astra 68.4%
- Decision Index Public v0.3 In use Decision models return probabilities over labeled options in public tasks covering knowledge, language, retrieval, tools, and arts. A chance-corrected weighted aggregate combines the task scores. Granite Switch 4.1 30B 51.3
- SAGE v1.1 (Vals) In use Models grade handwritten undergraduate math and computer science work against rubrics. Scored by class-balanced accuracy of each rubric check against expert grading. Claude Opus 5.5 91.3%
- MTEB Fading Massive Text Embedding Benchmark: retrieval, clustering, classification across languages and modalities.
Qwen3-Embedding-8B 72.2%
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 Qwen2-7B. 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 benchmark’s paper (10 entries).
- Pass Models scored 4 models we track, plus 6 other entries on its leaderboard.
- Warning Newest score The newest came 2 years ago, in June 2024, for Qwen2-7B.
- Note Frontier models None of the top 10 has a score. The strongest tested is Falcon-7B (#246).
- Pass Headroom The best is 74.1%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on aclanthology.org: 28 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.