InteractiveBench Logic
A model asks restricted questions to recover the hidden explanation of a situation puzzle. It solves an item only if a judge accepts its final explanation within 20 rounds.
The task set contains 46 puzzles. The judge knows the annotated explanation and returns restricted feedback. The paper revision adds UI2Html as another task outside this record.
- Made by
- InteractiveBench and Princeton University
- Released
- March 2026
- Kind
- Abstract puzzles and logic
- Level
- Everyday
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Multi-turn
- Refresh
- One fixed set
- Run by
- Anyone
- Based on
- InteractiveBench
- Strongest model tested
-
Gemini 3 Flash #60 on the capability index
- Last model added
- December 2025
- Scores refreshed
- November 19th, 2026
Gemini 3 Flash leads with 30.4% among models released by December 2025
Best score per model from the benchmark's own leaderboard, read on November 19th, 2026. Where a model ran with several settings or harnesses, we keep its best.
The newest model with a score here came out in December 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
Gemini 3 Flash 30.4%
- 2 GPT-5 mini 17.4%
- 3 Grok 4.1 Fast 15.2%
- 4
DeepSeek-V3.2 15.2%
- 5 Kimi K2 Thinking 6.50%
- 6
Qwen3-Max 4.30%
Source: Official InteractiveBench Logic leaderboard
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 30.4% | Dec 2025 | Official leaderboard | |
| 2 | GPT-5 mini | 17.4% | Aug 2025 | Official leaderboard | |
| 3 | Grok 4.1 Fast | 15.2% | Nov 2025 | Official leaderboard | |
| 4 | | 15.2% | Dec 2025 | Official leaderboard | |
| 5 | Kimi K2 Thinking | 6.50% | Nov 2025 | Official leaderboard | |
| 6 | | 4.30% | Sep 2025 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official InteractiveBench Logic 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 InteractiveBench Logic 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 11 months ago, in December 2025, for Gemini 3 Flash. 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 official leaderboard (6 entries).
- Pass Models scored 6 models we track.
- Warning Newest score The newest came 11 months ago, in December 2025, for Gemini 3 Flash.
- Note Frontier models None of the top 10 has a score. The strongest tested is Gemini 3 Flash (#60).
- Pass Headroom The best is 30.4%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on interactivebench.org: 6 rows for models we track at the last read.
- Pass Last read November 19th, 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.