CauGym
Models infer causal effects from descriptions and probabilities. Test questions vary the wording, add irrelevant facts, or remove information needed to answer.
The CaDO team tested six models on 1,400 questions pooled from CauGym’s deconfounding and redundant information sets.
- Released
- February 2026
- Kind
- Language reasoning
- Level
- University
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Subject
- Mathematics
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
CauGym-GRPO-14B tops the leaderboard with 88.5%
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 the headline is the plain mean of the five CauGym test-set accuracies. 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.
- 1 CauGym-GRPO-14B 88.5%
- 2 GRPO-no-think 83%
- 3 Realistic-GRPO 76.3%
- 4 DeepSeek-R1-Distill-Qwen-14B (SFT) 55.3%
Source: The CauGym paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | CauGym-GRPO-14B | 88.5% | Official leaderboard | ||
| 2 | GRPO-no-think | 83% | Official leaderboard | ||
| 3 | Realistic-GRPO | 76.3% | Official leaderboard | ||
| 4 | DeepSeek-R1-Distill-Qwen-14B (SFT) | 55.3% | Official 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
All 7 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 pass 4 notes
- Pass Independent runs Scores from the benchmark’s paper (4 entries).
- Note Models scored 4 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom No scores yet.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 4 entries at the last read, none a model we track.
- 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.