Highest BrowseComp score reported. Pro variant with maximum reasoning.

New SOTA. Uses 4.9x fewer tokens than Opus 4.6 while scoring higher.

Up from 59.2% on Gemini 3 Pro. Strong autonomous web research capability.

Multi-agent web search coordination across hours-long sessions. 86.8% with harness.

Up from 65.8% on GPT-5.2. Native computer-use model with 1M context.

With aggressive context-folding strategy. Outperforms every US frontier model on web browsing.

With Agent Swarm. Base score 60.6, with context management 74.9. Competitive with GPT-5.4 (82.7).

Multi-agent swarm configuration. 72.7% on WideSearch.

Strong browsing agent performance. Competitive with Claude Opus 4.6 (84.0%).

With context management strategy. Baseline without CM: 62.0%. Highest open-model BrowseComp score reported.

Single-agent config. Corrected after cheating detection pipeline update (was 74.72%, adjusted to 74.01%). Multi-agent variant scores 82.07%.

Score with Context Manager agent framework. Base score 51.6. Strong browsing for an open model.

Top open-model score on BrowseComp. 79.3 with context management variant.

Small model (27B params) with competitive browsing ability. Below frontier but strong for open-weight.

Single-agent mode. Agent Swarm achieves 78.4%.

India's first domestically-trained 105B model. MoE with 10.3B active params. Apache 2.0.

Lightweight flash variant browser capability score.