BLUR
Models identify a remembered item from incomplete clues in several languages and media.
The paper reports model results.
- Made by
- Patronus AI
- Released
- March 2025
- Kind
- Questions that need search
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Interaction
- Agentic
- Environment
- Browser
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A host
- In views
- Agents, Vision, Audio and speech
- Strongest model tested
- o1 #118 on the capability index
- Last model added
- May 2025
- Scores refreshed
- November 20th, 2026
HuggingFace Agents + Claude 3.5 Sonnet tops the leaderboard with 56% OpenAI Computer-Using Agent (CUA) leads with 54% among models released by May 2025
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran on its own with several settings, we keep its best. Agents other companies built around a model get a pale shade of that model's lab color. Gray marks blends and entries not in our model list, such as fine-tunes and older models. None of these count toward leaders. The best model on its own is OpenAI Computer-Using Agent (CUA), at 54%. Agents built around a model, such as HuggingFace Agents + Claude 3.5 Sonnet, are their own entries. We don't count them as the model's score. This view shows only models we track, each at its best.
The newest model with a score here came out in May 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
- 1 HuggingFace Agents + Claude 3.5 Sonnet 56%
- 2 OpenAI Computer-Using Agent (CUA) 54%
- 3 DynaSaur + GPT-4o Mar 2025 50%
- 4 ChatGPT-4o 49%
- 5 o1 49%
- 6
DeepSeek-R1 May 2025 41%
- 7 Claude 3.5 Sonnet 40%
- 8 GPT-4o Nov 2024 38%
- 9 Mistral Le Chat 37%
- 10
Llama 3.1-405B 30%
- 11 Microsoft Copilot 27%
- 12 Perplexity Pro Search 27%
Source: Official BLUR leaderboard
- 1 OpenAI Computer-Using Agent (CUA) 54%
- 2 o1 49%
- 3
DeepSeek-R1 May 2025 41%
- 4 Claude 3.5 Sonnet 40%
- 5 GPT-4o Nov 2024 38%
- 6
Llama 3.1-405B 30%
Source: Official BLUR leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | HuggingFace Agents + Claude 3.5 Sonnet | 56% | Jun 2024 | Official leaderboard | |
| 2 | OpenAI Computer-Using Agent (CUA) | 54% | Jan 2025 | Official leaderboard | |
| 3 | DynaSaur + GPT-4o Mar 2025 | 50% | Mar 2025 | Official leaderboard | |
| 4 | ChatGPT-4o | 49% | Official leaderboard | ||
| 5 | o1 | 49% | Dec 2024 | Official leaderboard | |
| 6 | | 41% | May 2025 | Official leaderboard | |
| 7 | Claude 3.5 Sonnet | 40% | Jun 2024 | Official leaderboard | |
| 8 | GPT-4o Nov 2024 | 38% | Nov 2024 | Official leaderboard | |
| 9 | Mistral Le Chat | 37% | Official leaderboard | ||
| 10 | | 30% | Jul 2024 | Official leaderboard | |
| 11 | Microsoft Copilot | 27% | Official leaderboard | ||
| 12 | Perplexity Pro Search | 27% | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | OpenAI Computer-Using Agent (CUA) | 54% | Jan 2025 | Official leaderboard | |
| 2 | o1 | 49% | Dec 2024 | Official leaderboard | |
| 3 | | 41% | May 2025 | Official leaderboard | |
| 4 | Claude 3.5 Sonnet | 40% | Jun 2024 | Official leaderboard | |
| 5 | GPT-4o Nov 2024 | 38% | Nov 2024 | Official leaderboard | |
| 6 | | 30% | Jul 2024 | Official leaderboard |
Rankings by part
We read 5 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as Text-only queries, Queries with file inputs and Easy. OpenAI Computer-Using Agent (CUA) leads 4 of them, and o1 leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Text-only queries
6 models we track have a score here.
- 1 OpenAI Computer-Using Agent (CUA) 57%
- 2 o1 54%
- 3
DeepSeek-R1 May 2025 45%
- 4 Claude 3.5 Sonnet 44%
- 5 GPT-4o Nov 2024 42%
- 6
Llama 3.1-405B 34%
Queries with file inputs
6 models we track have a score here.
- 1 OpenAI Computer-Using Agent (CUA) 46%
- 2 o1 36%
- 3 Claude 3.5 Sonnet ↑1 28%
- 4 GPT-4o Nov 2024 ↑1 28%
- 5
DeepSeek-R1 May 2025 ↓2 27%
- 6
Llama 3.1-405B 17%
Easy
6 models we track have a score here.
- 1 o1 ↑1 56%
- 2 OpenAI Computer-Using Agent (CUA) ↓1 56%
- 3
DeepSeek-R1 May 2025 46%
- 4 Claude 3.5 Sonnet 42%
- 5 GPT-4o Nov 2024 39%
- 6
Llama 3.1-405B 35%
Medium
6 models we track have a score here.
- 1 OpenAI Computer-Using Agent (CUA) 56%
- 2 o1 52%
- 3
DeepSeek-R1 May 2025 44%
- 4 GPT-4o Nov 2024 ↑1 43%
- 5 Claude 3.5 Sonnet ↓1 42%
- 6
Llama 3.1-405B 32%
Hard
6 models we track have a score here.
- 1 OpenAI Computer-Using Agent (CUA) 52%
- 2 o1 44%
- 3 Claude 3.5 Sonnet ↑1 36%
- 4 GPT-4o Nov 2024 ↑1 35%
- 5
DeepSeek-R1 May 2025 ↓2 35%
- 6
Llama 3.1-405B 25%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official BLUR leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official BLUR 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 Knowledge
- MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects.
Intern-S2-397B 89.8%
- MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy.
Seed1.8 92.3%
- SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy.
Qwen 3.6 Max (Preview) 73.9%
- WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1.
Tencent Hy4 preview 83.9%
- BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly.
Gemma 4 31B IT 74.4%
- HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%
Data audit
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 18 months ago, in May 2025, for DeepSeek-R1. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- 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 18 months ago, in May 2025, for DeepSeek-R1.
- Note Frontier models None of the top 10 has a score. The strongest tested is o1 (#118).
- Pass Headroom The best is 54%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on huggingface.co: 8 rows for models we track and 4 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.