CounterBench (1,200 questions)
Version 1,200 questions
Models answer counterfactual questions using the stated causal rules. This release adds 200 backdoor questions to the original 1,000.
The CaDO team used both question files and reserved 230 questions for testing. Its split groups questions by their underlying causal mechanism.
- Made by
- Rutgers University and Case Western Reserve University
- Released
- August 2025
- 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
- Another benchmark
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- CounterBench
- Strongest model tested
-
DeepSeek-V3 #155 on the capability index
- Last model added
- December 2024
- Scores refreshed
- November 20th, 2026
DeepSeek-V3 leads with 91.8% among models released by December 2024 DeepSeek-V3 leads with 91.8% among models released by December 2024
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 December 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
DeepSeek-V3 91.8%
- 2 Gemini-1.5-flash (snapshot unspecified) 89.9%
- 3 Claude 3 Sonnet 89.8%
- 4 GPT-4o (snapshot unspecified) 89.4%
- 5
Gemini 1.5 Flash 8B 83.9%
- 6 GPT-4o mini 79.9%
- 7 Claude 3.5 Haiku 79.1%
- 8 GPT-3.5 turbo (snapshot unspecified) 58.9%
- 9 davinci-002 Standard 51.9%
- 10 GPT-3 (Babbage-002) Standard 49.6%
Source: The CounterBench (1,200 questions) paper
- 1
DeepSeek-V3 91.8%
- 2 Claude 3 Sonnet 89.8%
- 3
Gemini 1.5 Flash 8B 83.9%
- 4 GPT-4o mini 79.9%
- 5 Claude 3.5 Haiku 79.1%
- 6 davinci-002 Standard 51.9%
Source: The CounterBench (1,200 questions) paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 91.8% | CoIn | Dec 2024 | Official leaderboard |
| 2 | Gemini-1.5-flash (snapshot unspecified) | 89.9% | CoIn | Official leaderboard | |
| 3 | Claude 3 Sonnet | 89.8% | CoIn | Feb 2024 | Official leaderboard |
| 4 | GPT-4o (snapshot unspecified) | 89.4% | CoIn | Official leaderboard | |
| 5 | | 83.9% | CoIn | Oct 2024 | Official leaderboard |
| 6 | GPT-4o mini | 79.9% | CoIn | Jul 2024 | Official leaderboard |
| 7 | Claude 3.5 Haiku | 79.1% | CoIn | Oct 2024 | Official leaderboard |
| 8 | GPT-3.5 turbo (snapshot unspecified) | 58.9% | CoIn | Official leaderboard | |
| 9 | davinci-002 | 51.9% | Standard | Mar 2022 | Official leaderboard |
| 10 | GPT-3 (Babbage-002) | 49.6% | Standard | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 91.8% | CoIn | Dec 2024 | Official leaderboard |
| 2 | Claude 3 Sonnet | 89.8% | CoIn | Feb 2024 | Official leaderboard |
| 3 | | 83.9% | CoIn | Oct 2024 | Official leaderboard |
| 4 | GPT-4o mini | 79.9% | CoIn | Jul 2024 | Official leaderboard |
| 5 | Claude 3.5 Haiku | 79.1% | CoIn | Oct 2024 | Official leaderboard |
| 6 | davinci-002 | 51.9% | Standard | Mar 2022 | Official leaderboard |
Rankings by part
We read 5 parts from the benchmark’s paper, each ranking models on one part of the test, such as Basic, Conditional and Joint. DeepSeek-V3 leads 4 of them, and Claude 3 Sonnet leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Basic
6 models we track have a score here.
- 1
DeepSeek-V3 99.6%
- 2 Claude 3 Sonnet 97.6%
- 3
Gemini 1.5 Flash 8B 94.8%
- 4 Claude 3.5 Haiku ↑1 88%
- 5 GPT-4o mini ↓1 82.8%
- 6 davinci-002 56.8%
Conditional
6 models we track have a score here.
- 1
DeepSeek-V3 90%
- 2 Claude 3 Sonnet 84.8%
- 3
Gemini 1.5 Flash 8B 80%
- 4 GPT-4o mini 79.2%
- 5 Claude 3.5 Haiku 76.8%
- 6 davinci-002 50.2%
Joint
6 models we track have a score here.
- 1
DeepSeek-V3 90.4%
- 2 Claude 3 Sonnet 90%
- 3
Gemini 1.5 Flash 8B 88%
- 4 Claude 3.5 Haiku ↑1 81.2%
- 5 GPT-4o mini ↓1 80%
- 6 davinci-002 51.2%
Nested
6 models we track have a score here.
- 1 Claude 3 Sonnet ↑1 94%
- 2
DeepSeek-V3 ↓1 94%
- 3
Gemini 1.5 Flash 8B 88.4%
- 4 Claude 3.5 Haiku ↑1 83.2%
- 5 GPT-4o mini ↓1 80.4%
- 6 davinci-002 51.6%
Backdoor
6 models we track have a score here.
- 1
DeepSeek-V3 83%
- 2 Claude 3 Sonnet 80.5%
- 3 GPT-4o mini ↑1 76.5%
- 4
Gemini 1.5 Flash 8B ↓1 64.5%
- 5 Claude 3.5 Haiku 63%
- 6 davinci-002 52.5%
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 CounterBench (1,200 questions) paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| CoIn | 91.8% | ||||
| Claude 3 Sonnet | CoIn | 89.8% | |||
| CoIn | 83.9% | ||||
| GPT-4o mini | CoIn | 79.9% | |||
| Claude 3.5 Haiku | CoIn | 79.1% | |||
| CausalCoT | 74.2% | ||||
| CausalCoT | 64.8% | ||||
| Claude 3.5 Haiku | CausalCoT | 64.2% | |||
| GPT-4o mini | CausalCoT | 59.8% | |||
| Claude 3 Sonnet | CausalCoT | 59% | |||
| davinci-002 | Standard | 51.9% | |||
| Standard | 51.9% | ||||
| Claude 3 Sonnet | Solver | 51.8% | |||
| Claude 3 Sonnet | Standard | 51.6% | |||
| GPT-4o mini | Standard | 50.4% | |||
| Standard | 50.4% | ||||
| Solver | 50.3% | ||||
| davinci-002 | Solver | 50.1% | |||
| davinci-002 | CoIn | 49.6% | |||
| davinci-002 | CausalCoT | 49.3% | |||
| Solver | 49.3% | ||||
| Claude 3.5 Haiku | Solver | 48.3% | |||
| GPT-4o mini | Solver | 47.2% | |||
| Claude 3.5 Haiku | Standard | 39.8% |
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 CounterBench (1,200 questions) paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| CoIn | 91.8% | ||||
| Claude 3 Sonnet | CoIn | 89.8% | |||
| CoIn | 83.9% | ||||
| GPT-4o mini | CoIn | 79.9% | |||
| Claude 3.5 Haiku | CoIn | 79.1% | |||
| CausalCoT | 74.2% | ||||
| CausalCoT | 64.8% | ||||
| Claude 3.5 Haiku | CausalCoT | 64.2% | |||
| GPT-4o mini | CausalCoT | 59.8% | |||
| Claude 3 Sonnet | CausalCoT | 59% | |||
| davinci-002 | Standard | 51.9% | |||
| Standard | 51.9% | ||||
| Claude 3 Sonnet | Solver | 51.8% | |||
| Claude 3 Sonnet | Standard | 51.6% | |||
| GPT-4o mini | Standard | 50.4% | |||
| Standard | 50.4% | ||||
| Solver | 50.3% | ||||
| davinci-002 | Solver | 50.1% | |||
| davinci-002 | CoIn | 49.6% | |||
| davinci-002 | CausalCoT | 49.3% | |||
| Solver | 49.3% | ||||
| Claude 3.5 Haiku | Solver | 48.3% | |||
| GPT-4o mini | Solver | 47.2% | |||
| Claude 3.5 Haiku | Standard | 39.8% |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The CounterBench (1,200 questions) paper
Claude 3 Sonnet on the official leaderboard passed 85% in February 2024
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official CounterBench (1,200 questions) 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.
Versions
We switch the top row to each new version when it comes out. Open it for one row per version. An old version stays in play while people still test it, so whoever first takes it past 85% gets credit for closing it out.
Source: Official leaderboards
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 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (10 entries).
- Pass Models scored 6 models we track, plus 4 other entries on its leaderboard.
- Note Newest score The newest came 23 months ago, in December 2024, for DeepSeek-V3. That’s expected for a saturated test.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is DeepSeek-V3 (#155).
- Note Headroom Saturated. The best is 91.8%, past 85% since February 2024.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 24 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.