Gemini 3.0
Mainline Gemini 3 cost leader — capable general model when Pro's science edge is not required.
When to use it
Balanced Google Cloud apps needing solid quality at lower spend.
Watch-outs
Prefer 3.1 Pro for GPQA-class science and hardest reasoning.
Benchmarks
Human preference ranking from blind pairwise chats. Higher is better; top frontier models cluster within ~50–80 Elo.
Artificial Analysis composite across agents, coding, science, and general evaluations (v4.1 weighting).
Percent of real GitHub issues resolved end-to-end. Strong signal for agentic coding usefulness.
PhD-level science questions. Separates frontier reasoning models better than saturated knowledge tests.
Harder multi-choice knowledge/reasoning suite than classic MMLU.
Frontier closed-ended academic difficulty across many domains.
More from Google
- Gemini 3.1 ProAA 54
Scientific reasoning, huge document corpora, and Google Cloud / Workspace stacks.
- Gemini 3 FlashAA 42
High-throughput apps, classification, and cost-sensitive Google stack workloads.