CLadder
Models answer yes or no to questions about associations, interventions, and counterfactuals. A causal inference engine supplies the reference answers.
The makers’ repository has 149 stars. The CaDO team tested six models on a 1,989-question split that kept stories separate.
- Made by
- CausalNLP and collaborators
- Released
- May 2023
- Kind
- Language reasoning
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Mathematics
- Language
- English
- Interaction
- Single turn
- Items from
- Generated
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
- GPT-4 Turbo Nov 2023 #176 on the capability index
- Last model added
- November 2023
- Scores refreshed
- November 20th, 2026
GPT-4 Turbo leads with 70.4% among models released by November 2023 GPT-4 Turbo leads with 70.4% among models released by November 2023
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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 November 2023, 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 GPT-4 Turbo Nov 2023, v1.5, CausalCoT 70.4%
- 2 GPT-4 Mar 2023, v1.0, CausalCoT 66.6%
- 3 davinci-003 v1.0, Direct prompting 62.7%
- 4 GPT-3.5 Turbo (Mar 2023) v1.0, Direct prompting 61.7%
- 5 GPT-3 Instr. (text-davinci-001) v1.0, Direct prompting 57.1%
- 6 davinci-002 v1.0, Direct prompting 56.2%
- 7 GPT-3.5 (snapshot unspecified) v1.5, Direct prompting 52.2%
- 8 GPT-3 175B (davinci) v1.5, Direct prompting 49.9%
- 9 Alpaca v1.0, Direct prompting 45.5%
- 10
LLaMA-7B v1.0, Direct prompting 45.2%
Source: The CLadder paper
- 1 GPT-4 Turbo Nov 2023, v1.5, CausalCoT 70.4%
- 2 GPT-4 Mar 2023, v1.0, CausalCoT 66.6%
- 3 davinci-003 v1.0, Direct prompting 62.7%
- 4 GPT-3.5 Turbo (Mar 2023) v1.0, Direct prompting 61.7%
- 5 davinci-002 v1.0, Direct prompting 56.2%
- 6 GPT-3 175B (davinci) v1.5, Direct prompting 49.9%
- 7
LLaMA-7B v1.0, Direct prompting 45.2%
Source: The CLadder paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 Turbo Nov 2023 | 70.4% | v1.5, CausalCoT | Nov 2023 | Official leaderboard |
| 2 | GPT-4 Mar 2023 | 66.6% | v1.0, CausalCoT | Mar 2023 | Official leaderboard |
| 3 | davinci-003 | 62.7% | v1.0, Direct prompting | Nov 2022 | Official leaderboard |
| 4 | GPT-3.5 Turbo (Mar 2023) | 61.7% | v1.0, Direct prompting | Mar 2023 | Official leaderboard |
| 5 | GPT-3 Instr. (text-davinci-001) | 57.1% | v1.0, Direct prompting | Official leaderboard | |
| 6 | davinci-002 | 56.2% | v1.0, Direct prompting | Mar 2022 | Official leaderboard |
| 7 | GPT-3.5 (snapshot unspecified) | 52.2% | v1.5, Direct prompting | Official leaderboard | |
| 8 | GPT-3 175B (davinci) | 49.9% | v1.5, Direct prompting | May 2020 | Official leaderboard |
| 9 | Alpaca | 45.5% | v1.0, Direct prompting | Official leaderboard | |
| 10 | | 45.2% | v1.0, Direct prompting | Feb 2023 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4 Turbo Nov 2023 | 70.4% | v1.5, CausalCoT | Nov 2023 | Official leaderboard |
| 2 | GPT-4 Mar 2023 | 66.6% | v1.0, CausalCoT | Mar 2023 | Official leaderboard |
| 3 | davinci-003 | 62.7% | v1.0, Direct prompting | Nov 2022 | Official leaderboard |
| 4 | GPT-3.5 Turbo (Mar 2023) | 61.7% | v1.0, Direct prompting | Mar 2023 | Official leaderboard |
| 5 | davinci-002 | 56.2% | v1.0, Direct prompting | Mar 2022 | Official leaderboard |
| 6 | GPT-3 175B (davinci) | 49.9% | v1.5, Direct prompting | May 2020 | Official leaderboard |
| 7 | | 45.2% | v1.0, Direct prompting | Feb 2023 | Official leaderboard |
Rankings by part
We read 6 parts from the benchmark’s paper, each ranking models on one part of the test, such as Rung 1, Rung 2 and Rung 3. GPT-4 Turbo leads 4 of them, and GPT-4 leads the other 2. Arrows show how far a model moved from its overall rank among the models we track.
Rung 1
7 models we track have a score here.
- 1 GPT-4 Turbo Nov 2023 83.3%
- 2 GPT-3.5 Turbo (Mar 2023) ↑2 65.1%
- 3 GPT-3 175B (davinci) ↑3 63.9%
- 4
LLaMA-7B ↑3 63.3%
- 5 GPT-4 Mar 2023 ↓3 61.7%
- 6 davinci-003 ↓3 58%
- 7 davinci-002 ↓2 50.9%
Rung 2
7 models we track have a score here.
- 1 GPT-4 Mar 2023 ↑1 86.1%
- 2 davinci-003 ↑1 80.8%
- 3 GPT-3.5 Turbo (Mar 2023) ↑1 69.9%
- 4 davinci-002 ↑1 69.5%
- 5 GPT-4 Turbo Nov 2023 ↓4 67.5%
- 6 GPT-3 175B (davinci) 49.8%
- 7
LLaMA-7B 31.1%
Rung 3
7 models we track have a score here.
- 1 GPT-4 Mar 2023 ↑1 63.1%
- 2 GPT-4 Turbo Nov 2023 ↓1 62%
- 3 davinci-002 ↑2 55%
- 4 davinci-003 ↓1 55%
- 5 GPT-3.5 Turbo (Mar 2023) ↓1 54.1%
- 6
LLaMA-7B ↑1 52.7%
- 7 GPT-3 175B (davinci) ↓1 50%
Commonsensical
7 models we track have a score here.
- 1 GPT-4 Turbo Nov 2023 69.3%
- 2 GPT-4 Mar 2023 67.6%
- 3 GPT-3.5 Turbo (Mar 2023) ↑1 64.5%
- 4 davinci-003 ↓1 62%
- 5 davinci-002 55.3%
- 6 GPT-3 175B (davinci) 49.1%
- 7
LLaMA-7B 45.1%
Nonsensical
7 models we track have a score here.
- 1 GPT-4 Turbo Nov 2023 71.6%
- 2 GPT-4 Mar 2023 63%
- 3 davinci-003 62.1%
- 4 davinci-002 ↑1 59.6%
- 5 GPT-3.5 Turbo (Mar 2023) ↓1 55.1%
- 6 GPT-3 175B (davinci) 50%
- 7
LLaMA-7B 45.2%
Anti-commonsensical
7 models we track have a score here.
- 1 GPT-4 Turbo Nov 2023 70.1%
- 2 GPT-4 Mar 2023 69.3%
- 3 GPT-3.5 Turbo (Mar 2023) ↑1 65.4%
- 4 davinci-003 ↓1 63.9%
- 5 davinci-002 54.8%
- 6 GPT-3 175B (davinci) 50.7%
- 7
LLaMA-7B 45.3%
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 CLadder paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-4 Turbo Nov 2023 | v1.5, CausalCoT | 70.4% | |||
| GPT-4 Mar 2023 | v1.0, CausalCoT | 66.6% | |||
| GPT-4 Mar 2023 | v1.0, Direct prompting | 64.3% | |||
| davinci-003 | v1.0, Direct prompting | 62.7% | |||
| GPT-4 Turbo Nov 2023 | v1.5, Direct prompting | 62% | |||
| GPT-3.5 Turbo (Mar 2023) | v1.0, Direct prompting | 61.7% | |||
| davinci-003 | v1.5, Direct prompting | 56.3% | |||
| davinci-002 | v1.0, Direct prompting | 56.2% | |||
| davinci-002 | v1.5, Direct prompting | 53.1% | |||
| GPT-3 175B (davinci) | v1.5, Direct prompting | 49.9% | |||
| GPT-3 175B (davinci) | v1.0, Direct prompting | 47.4% | |||
| v1.0, Direct prompting | 45.2% | ||||
| v1.5, Direct prompting | 44% |
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 CLadder paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| GPT-4 Turbo Nov 2023 | v1.5, CausalCoT | 70.4% | |||
| GPT-4 Mar 2023 | v1.0, CausalCoT | 66.6% | |||
| GPT-4 Mar 2023 | v1.0, Direct prompting | 64.3% | |||
| davinci-003 | v1.0, Direct prompting | 62.7% | |||
| GPT-4 Turbo Nov 2023 | v1.5, Direct prompting | 62% | |||
| GPT-3.5 Turbo (Mar 2023) | v1.0, Direct prompting | 61.7% | |||
| davinci-003 | v1.5, Direct prompting | 56.3% | |||
| davinci-002 | v1.0, Direct prompting | 56.2% | |||
| davinci-002 | v1.5, Direct prompting | 53.1% | |||
| GPT-3 175B (davinci) | v1.5, Direct prompting | 49.9% | |||
| GPT-3 175B (davinci) | v1.0, Direct prompting | 47.4% | |||
| v1.0, Direct prompting | 45.2% | ||||
| v1.5, Direct prompting | 44% |
2 models have held number one in the benchmark’s paper since its release in May 2023
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The CLadder 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 CLadder 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 3 years ago, in November 2023, for GPT-4 Turbo. 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 7 models we track, plus 3 other entries on its leaderboard.
- Warning Newest score The newest came 3 years ago, in November 2023, for GPT-4 Turbo.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-4 Turbo (#176).
- Pass Headroom The best is 70.4%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 13 rows for models we track and 3 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.