Inspect vs OpenCompass: comparação

Inspect vs OpenCompass
Fato	Inspect	OpenCompass
Linguagem	Python	Python
Licença	MIT	Apache-2.0
Estrelas	3k	7.5k
Última release	0.3.281	0.5.4
Último push	2026-10-17	2026-10-16
Ritmo de releases	cerca de 2 dias entre releases	cerca de 89 dias entre releases
Contribuidores ativos	81+ autores de commits na branch padrão nos últimos 90 dias	26 autores de commits na branch padrão nos últimos 90 dias
Alertas	nenhum	nenhum

Como se relacionam

Os dois substituem LM Evaluation Harness. Alternativas a LM Evaluation Harness →
ParcialInspectRuns benchmark tasks, but is built around custom evals and agents.
Substituição completaOpenCompassRuns benchmark suites over local and API models from a config.

0.3.2812026-10-15v0.3.281
0.3.2802026-10-14v0.3.280
0.3.2792026-10-12v0.3.279
0.3.2782026-10-09Tasks and samples can carry a description of what they ask of the agent, recorded in the eval log and in evals_df() and…

0.5.42026-08-26✨ Multimodal Evaluation with VLMEvalKit: OpenCompass now integrates VLMEvalKit for native multimodal dataset loading, O…
0.5.32026-06-29✨ 🧪 Extensive New Benchmarks and Dataset Support: Added support for a wide range of new benchmarks and datasets, inclu…
0.5.22026-02-14✨ 🧪 Extensive New Benchmarks Support: We have introduced comprehensive support for Scientific and General Benchmarks,…
0.5.1.post12025-10-17✨ A New Method to quickly Integrate and Evaluate Your Datasets: Added a fast dataset integration and evaluation method…
0.5.02025-09-01✨ Comprehensive Scientific Benchmarks: Integrated 10+ specialized datasets (MedXpertQA, ClimaQA, SmolInstruct, etc.),…

✓ assinada A última release, 0.3.281, tem uma assinatura verificada pelo GitHub.

Carregando o relatório de segurança

✓ assinada A última release, 0.5.4, tem uma assinatura verificada pelo GitHub.

Carregando o relatório de segurança