ReasonZoo
Models solve tasks in logical reasoning, puzzles, and programming. The evaluation compares their answers with task solutions.
- Made by
- OpenCompass and collaborators
- Released
- August 2025
- Kind
- Abstract puzzles and logic
- Level
- University
- Scored
- Checked automatically
- Answers
- Short answer
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- Strongest model tested
-
DeepSeek-R1 May 2025 #122 on the capability index
- Last model added
- May 2025
- Scores refreshed
- November 20th, 2026
Qwen3-235B-A22B leads with 61% among models released by May 2025 Qwen3-235B-A22B leads with 61% among models released by May 2025
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 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
Qwen3-235B-A22B MT-TIR 61%
- 2
DeepSeek-R1 May 2025, MT-TIR 55.3%
- 3
Qwen3-32B PoT 49.9%
- 4
Qwen3-8B PoT 43%
- 5 ToRL TIT 18.7%
- 6 CIR TIT 16.9%
- 7 Qwen2.5-Math-7B No tools 4.80%
Source: The ReasonZoo paper
- 1
Qwen3-235B-A22B MT-TIR 61%
- 2
DeepSeek-R1 May 2025, MT-TIR 55.3%
- 3
Qwen3-32B PoT 49.9%
- 4
Qwen3-8B PoT 43%
Source: The ReasonZoo paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 61% | MT-TIR | Apr 2025 | Official leaderboard |
| 2 | | 55.3% | MT-TIR | May 2025 | Official leaderboard |
| 3 | | 49.9% | PoT | Apr 2025 | Official leaderboard |
| 4 | | 43% | PoT | Apr 2025 | Official leaderboard |
| 5 | ToRL | 18.7% | TIT | Official leaderboard | |
| 6 | CIR | 16.9% | TIT | Official leaderboard | |
| 7 | Qwen2.5-Math-7B | 4.80% | No tools | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 61% | MT-TIR | Apr 2025 | Official leaderboard |
| 2 | | 55.3% | MT-TIR | May 2025 | Official leaderboard |
| 3 | | 49.9% | PoT | Apr 2025 | Official leaderboard |
| 4 | | 43% | PoT | Apr 2025 | Official leaderboard |
Rankings by part
We read 9 parts from the benchmark’s paper, each ranking models on one part of the test, such as Number Calculation, Grade School Math and Puzzle. Qwen3-235B-A22B leads 5 of them, and 2 other models lead the rest. Arrows show how far a model moved from its overall rank among the models we track.
Number Calculation
4 models we track have a score here.
- 1
DeepSeek-R1 May 2025 ↑1 69.4%
- 2
Qwen3-32B ↑1 65.5%
- 3
Qwen3-235B-A22B ↓2 58.4%
- 4
Qwen3-8B 46%
Grade School Math
4 models we track have a score here.
- 1
Qwen3-235B-A22B 42%
- 2
Qwen3-32B ↑1 42%
- 3
DeepSeek-R1 May 2025 ↓1 40%
- 4
Qwen3-8B 36%
Puzzle
4 models we track have a score here.
- 1
Qwen3-235B-A22B 70.4%
- 2
Qwen3-32B ↑1 65.2%
- 3
DeepSeek-R1 May 2025 ↓1 55.4%
- 4
Qwen3-8B 46.4%
Cipher and Code
4 models we track have a score here.
- 1
Qwen3-235B-A22B 79.1%
- 2
Qwen3-32B ↑1 69.6%
- 3
DeepSeek-R1 May 2025 ↓1 66.8%
- 4
Qwen3-8B 57.4%
Boolean Logic
4 models we track have a score here.
- 1
Qwen3-32B ↑2 77.3%
- 2
DeepSeek-R1 May 2025 77.3%
- 3
Qwen3-8B ↑1 73.7%
- 4
Qwen3-235B-A22B ↓3 71.6%
Daily Logic
4 models we track have a score here.
- 1
DeepSeek-R1 May 2025 ↑1 82.4%
- 2
Qwen3-235B-A22B ↓1 77.6%
- 3
Qwen3-32B 71.9%
- 4
Qwen3-8B 65.7%
Operations Research
4 models we track have a score here.
- 1
Qwen3-235B-A22B 58%
- 2
Qwen3-32B ↑1 54%
- 3
DeepSeek-R1 May 2025 ↓1 51%
- 4
Qwen3-8B 48%
Physics
4 models we track have a score here.
- 1
DeepSeek-R1 May 2025 ↑1 41%
- 2
Qwen3-235B-A22B ↓1 40%
- 3
Qwen3-32B 27%
- 4
Qwen3-8B 22%
Formal Language
4 models we track have a score here.
- 1
Qwen3-235B-A22B 60.2%
- 2
DeepSeek-R1 May 2025 38.4%
- 3
Qwen3-32B 27.5%
- 4
Qwen3-8B 16.5%
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 ReasonZoo paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| MT-TIR | 61% | 14,066 | |||
| MT-TIR | 55.3% | 11,284 | |||
| PoT | 52.8% | 10,552 | |||
| PoT | 49.9% | 9,893 | |||
| MT-TIR | 47.3% | 11,899 | |||
| No tools | 45.8% | 9,160 | |||
| PoT | 43% | 10,855 | |||
| No tools | 42.4% | 9,160 | |||
| No tools | 41.9% | 8,278 | |||
| MT-TIR | 41% | 15,462 | |||
| No tools | 37.6% | 11,942 | |||
| PoT | 36.6% | 8,310 |
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 ReasonZoo paper
| Model | Effort | Harness | Score | Cost per task | Output tokens |
|---|---|---|---|---|---|
| MT-TIR | 61% | 14,066 | |||
| MT-TIR | 55.3% | 11,284 | |||
| PoT | 52.8% | 10,552 | |||
| PoT | 49.9% | 9,893 | |||
| MT-TIR | 47.3% | 11,899 | |||
| No tools | 45.8% | 9,160 | |||
| PoT | 43% | 10,855 | |||
| No tools | 42.4% | 9,160 | |||
| No tools | 41.9% | 8,278 | |||
| MT-TIR | 41% | 15,462 | |||
| No tools | 37.6% | 11,942 | |||
| PoT | 36.6% | 8,310 |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The ReasonZoo 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 ReasonZoo 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
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 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 (7 entries).
- Pass Models scored 4 models we track, plus 3 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 DeepSeek-R1 (#122).
- Pass Headroom The best is 61%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 12 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.