Scored 78.4 on OSWorld v1, matching GPT-5.5.

Scores 78.4 on OSWorld benchmark, matching GPT-5.5 (78.7)

Gemini 3.5 Flash generated a full web OS in one shot, demonstrating one-shot generation of complex UI.

Achieved 78.5% score on SWE-Bench coding benchmark

Observed autonomously optimizing an embedding model for Qualcomm NPU for three hours.

Research revealed its actual API cost is 22% higher than GPT-5.2 despite a 78% cheaper list price.

Achieved 100% resident identification accuracy in a safety evaluation for a care home smart speaker system.

Released as OpenAI's most capable frontier model with unified coding, reasoning, and computer operation capabilities

Demonstrated surpassing human baselines on OSWorld benchmark with 75% score

OpenAI releases GPT-5.4 with native computer use, tool search, and 1M token context window