List your company

Dynamic Task Success on DynaCU-Bench

82Success RateClaude Sonnet 4.6
0.8821.944364.06Jun 28, 2026

Evaluation results

MethodLinks
Claude Sonnet 4.6Observation Interface=AOI (full), Model Source=Closed-source2026.068273.3441.3
Gemini 2.5 FlashObservation Interface=AOI (full), Model Source=Closed-source2026.066959.4482.9
Grok-4.3Observation Interface=AOI (full), Model Source=Closed-source2026.066555.3408.2
GPT-5.4Observation Interface=AOI (full), Model Source=Closed-source2026.065747.2208.8
EvoCUA-32BObservation Interface=AOI (full), Model Source=Open-source2026.065545.2373
Grok-4-fast-reasoningObservation Interface=AOI (full), Model Source=Closed-source2026.064737.5284.9
Gemini 3 FlashObservation Interface=AOI (full), Model Source=Closed-source2026.064535.690.18
Claude Sonnet 4.6Observation Interface=Standard, Model Source=Closed-source2026.063829.1——
GPT-5.4Observation Interface=Standard, Model Source=Closed-source2026.063728.2——
Gemini 3 FlashObservation Interface=Standard, Model Source=Closed-source2026.063627.3——
Fara-7BObservation Interface=AOI (full), Model Source=Open-source2026.063425.5174.9
Grok-4Observation Interface=AOI (full), Model Source=Closed-source2026.062517.5213
Grok-4.3Observation Interface=Standard, Model Source=Closed-source2026.062517.5——
Gemini 2.5 FlashObservation Interface=Standard, Model Source=Closed-source2026.062114.2——
Grok-4-fast-reasoningObservation Interface=Standard, Model Source=Closed-source2026.061912.5——
EvoCUA-32BObservation Interface=Standard, Model Source=Open-source2026.061811.7——
Fara-7BObservation Interface=Standard, Model Source=Open-source2026.061710.9——
Grok-4Observation Interface=Standard, Model Source=Closed-source2026.0641.6——