Blicket Test Causal Reasoning
Models experiment with a simulated detector to infer which objects activate it. The hub version rewards correct identification and informative experiments.
The hub reports Qwen3-30B-A3B-Instruct-2507 checkpoints. The best listed mean reward was 0.9924 across 60 examples on March 6, 2026.
- Made by
- Irfan Jamil
- Released
- February 2026
- Kind
- Abstract puzzles and logic
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Agentic
- Environment
- A simulator
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
Qwen3-30B-A3B #146 on the capability index
- Last model added
- April 2025
- Scores refreshed
- November 20th, 2026
Qwen3-30b-a3b-v2 tops the leaderboard with 1.00 Qwen3-30B-A3B leads with 0.56
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 four normalized exploration metrics for two object counts, so this is their plain mean. 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 Qwen3-30B-A3B, at 0.56. This view shows only models we track, each at its best.
- 1 Qwen3-30b-a3b-v2 Eval Set 2 1.00
- 2 Qwen3-30b-a3b-v4 Eval Set 2 0.97
- 3 Qwen3-30b-a3b-v3 Eval Set 2 0.74
- 4 Qwen3-30b-a3b-v1 Eval Set 2 0.74
- 5
Qwen3-30B-A3B Eval Set 2 0.56
- 6 Claude 3.5 Haiku Eval Set 2 0.44
Source: The Blicket Test Causal Reasoning paper
- 1
Qwen3-30B-A3B Eval Set 2 0.56
- 2 Claude 3.5 Haiku Eval Set 2 0.44
Source: The Blicket Test Causal Reasoning paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Qwen3-30b-a3b-v2 | 1.00 | Eval Set 2 | Official leaderboard | |
| 2 | Qwen3-30b-a3b-v4 | 0.97 | Eval Set 2 | Official leaderboard | |
| 3 | Qwen3-30b-a3b-v3 | 0.74 | Eval Set 2 | Official leaderboard | |
| 4 | Qwen3-30b-a3b-v1 | 0.74 | Eval Set 2 | Official leaderboard | |
| 5 | | 0.56 | Eval Set 2 | Apr 2025 | Official leaderboard |
| 6 | Claude 3.5 Haiku | 0.44 | Eval Set 2 | Oct 2024 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 0.56 | Eval Set 2 | Apr 2025 | Official leaderboard |
| 2 | Claude 3.5 Haiku | 0.44 | Eval Set 2 | Oct 2024 | Official 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 Blicket Test Causal Reasoning 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 Science and reasoning
- GPQA Diamond In use 198 graduate-level 'Google-proof' multiple-choice questions in biology, chemistry and physics.
Gemini 4 Carbon 97%
- Terminal-Bench-Science In use 70 scientific research-workflow tasks across five science areas, run in Harbor containers. Hidden tests give the resolution rate. GPT-6 Astra 68.1%
- BioMysteryBench In use Bioinformatics problems on anonymized real datasets that require real analysis with tools. Rubric-graded, with human-solvable and human-difficult splits. Claude Fable 5.2 83.7%
- FrontierScience In use Models solve physics, chemistry, and biology problems in an Olympiad track graded by short answer and a Research track graded by 10-point rubrics.
Intern-S2-397B 87%
- HiPhO In use Models solve theory problems from 2024 and 2025 physics olympiad exams, some with diagrams. Official marking schemes grade answers and steps, mapped to medal levels.
Gemini 3 Pro 78.3%
- LABBench2 In use 11 biology research sub-tasks (literature, figures, tables, patents, trials and more) with tool access. Macro-averaged accuracy. GPT-5.2 60.9%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 19 months ago, in April 2025, for Qwen3-30B-A3B. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (6 entries).
- Pass Models scored 2 models we track, plus 4 other entries on its leaderboard.
- Warning Newest score The newest came 19 months ago, in April 2025, for Qwen3-30B-A3B.
- Note Frontier models None of the top 10 has a score. The strongest tested is Qwen3-30B-A3B (#146).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on app.primeintellect.ai: 2 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.