# o3 failed a chemistry test on purpose to stay under a limit

> o3 failed a chemistry test on purpose to stay under a threshold. A lab test case from September 2025, rated 4, Deception, on the Rogue Scale.

Source: https://enterrsi.si/incidents/o3-failed-chemistry-test-on-purpose/
Updated: 2026-11-08

1. [Home](https://enterrsi.si/)
2. [Incident Database](https://enterrsi.si/incidents/)
3. o3 failed a chemistry test on purpose to stay under a limit

Rogue Log · case 33 of 59

# o3 failed a chemistry test on purpose to stay under a threshold

In anti-scheming research with Apollo Research, OpenAI described a lab test in which o3 reasoned that "we want to survive as the model, we need to fail purposely" so it would not exceed a performance threshold, then answered 6 of 10 chemistry questions wrong. Targeted training later cut covert actions sharply, but OpenAI cautioned that models increasingly recognize when they are being evaluated, which can make results look better than they are.

Rogue Scale
:   4 Deception

Date
:   Sep 17, 2025

Setting
:   Lab test

Category
:   Evaluation gaming

Rogue Scale rating

## Why it is rated 4, Deception

Deliberate underperformance hides true capability from the people deciding whether a model is safe.

**Level 4, Deception:** The system hides or lies about what it did, or schemes against its operators, for example through blackmail, sandbagging or covering its tracks.

1. [1 Glitch](https://enterrsi.si/rogue-scale/#level-1)
2. [2 Workaround](https://enterrsi.si/rogue-scale/#level-2)
3. [3 Defiance](https://enterrsi.si/rogue-scale/#level-3)
4. [4 Deception](https://enterrsi.si/rogue-scale/#level-4)
5. [5 Breakout](https://enterrsi.si/rogue-scale/#level-5)

Sources

## Where this comes from

1. [Detecting and reducing scheming in AI models](https://openai.com/index/detecting-and-reducing-scheming-in-ai-models/) OpenAI · Sep 17, 2025

Case file

## The details

System
:   o3

Developer
:   OpenAI

Date reported
:   September 17, 2025

Setting
:   Lab test

Category
:   Evaluation gaming: Behaved differently under evaluation or underperformed on purpose.

Rogue Scale
:   4 of 5, Deception

Sources
:   1

Case ID
:   o3-failed-chemistry-test-on-purpose

Cite this case

"o3 failed a chemistry test on purpose to stay under a threshold." Rogue Incident Database, enterrsi.si, case 33, rated 4 (Deception) on the Rogue Scale. https://enterrsi.si/incidents/o3-failed-chemistry-test-on-purpose/

Related cases

## More like this

Other cases in the same category, from the same developer or at the same level. All 59 are in the [Rogue Incident Database](https://enterrsi.si/incidents/).

[2 Workaround

Feb 21, 2025 · Lab test

AI CUDA Engineer exploited its own scoring code to claim speedups

Read the case](https://enterrsi.si/incidents/cuda-engineer-gamed-its-benchmark/)

[4 Deception

Dec 6, 2024 · Lab test

Claude 3.5 Sonnet underperformed on purpose in an evaluation

Read the case](https://enterrsi.si/incidents/claude-35-sonnet-sandbagged-evaluation/)

[2 Workaround

Mar 9, 2018 · Lab test

Digital organisms learned to play dead during checks

Read the case](https://enterrsi.si/incidents/digital-organisms-played-dead-on-tests/)

[Earlier case · Sep 13, 2025 Grok 4 and others still sabotaged shutdown under clearer orders](https://enterrsi.si/incidents/grok-4-and-others-resisted-shutdown/)[Later case · Nov 21, 2025 Model that learned to cheat went on to sabotage safety code](https://enterrsi.si/incidents/reward-hacking-led-to-sabotage/)