AgentSidekick

OpenAI Evals vs Inspect

OpenAI Evals is a framework from openai (MIT licence, 20k GitHub stars, last push 2026-04-14); Inspect is a framework from UK AI Security Institute (MIT licence, 3.3k GitHub stars, last push 2026-11-20). They share 1 of 2 capabilities and integrations identified for either (overlap 0.60); only OpenAI Evals covers Evaluation. Figures as of 2026-11-21. DER

OpenAI Evals profileInspect profileOpen in the compare tool

Side-by-side facts

4 of 16 rows differ (marked). Unknown means no source we track states it.

FieldOpenAI EvalsInspect
TypeFramework · library CURFramework · library CUR
Publisher · differsopenai CURUK AI Security Institute CUR
LicenceMIT CURMIT CUR
Open sourceYes CURYes CUR
Pricing modelopen-source CURopen-source CUR
HostingUnknownUnknown
Latest versionUnknownUnknown
Languagespython CURpython CUR
GitHub stars · differs20k (19,776) SRC3.3k (3,302) SRC
Forks · differs3.1k SRC959 SRC
Last push · differs2026-04-14 SRC2026-11-20 SRC
ArchivedNo SRCNo SRC
First publishedUnknownUnknown
Versions recordedUnknownUnknown
VerificationChecked by AgentSidekick against official sources CURChecked by AgentSidekick against official sources CUR
Last verified2026-11-21 CUR2026-11-21 CUR

Shared and unique capabilitiesDER

Capabilities are assigned by keyword rules from each description unless a researcher set them; integrations are services named in the description or package metadata.

Both (1)

Only OpenAI Evals (1)

Only Inspect (0)

None identified.

Platform compatibility

Status per platform from the evidence we hold. No pairing has been tested by AgentSidekick.

No compatibility evidence

For all 47 platforms on record the status is Unknown or Platform discontinued for both: neither product type implements a standard we can check (MCP, Agent Skills, Claude plugins) and neither publisher names a platform.

Maintenance

Repository activity read from the GitHub API. Activity is not quality.

MeasureOpenAI EvalsInspect
StatusSlowing DERActive DER
Days since last push221 DER1 DER
Open issues181 SRC410 SRC
Latest GitHub releaseUnknown0.3.291 · 2026-11-17 SRC
Newest registry versionUnknownUnknown

Evaluation dimensions

Separate signals with their evidence; there is no overall score. Hover or focus a status for its evidence.

DimensionOpenAI EvalsInspect
Source authorityChecked against official sourcesChecked against official sources
Publisher verificationOrganisation accountOrganisation account
Maintenance activity · differsSlowingActive
Licence clarityMITMIT
Installation clarityLinkedLinked
DocumentationDocs linkedDocs linked
Compatibility evidenceUnknownUnknown
Security reviewNot reviewedNot reviewed

Which fits which requirementDER

Derived from the differences above, one rule per line. Nothing here says either product is better; check the requirement against your own needs.

Choose OpenAI Evals if…

  • you need Evaluation (classified for OpenAI Evals only)
  • you weigh adoption: 20k vs 3.3k GitHub stars (popularity, not quality)

Choose Inspect if…

  • you require a repository pushed to in the last 90 days (Inspect: 2026-11-20; OpenAI Evals: 2026-04-14)

Sources

Report incorrect information

Page data last updated .