Translate
Independent model intelligence

Find the right AI model,
not just the loudest one.

Compare current model capability, context, modalities, public preference and API economics in one continuously refreshed decision surface.

LiveBench 2.0 LMArena models.dev OpenRouter AIHOT cross-check
Back to leaderboard
Google · Active

Gemini 3 Pro

gemini-pro family · launched 2025-11-18

MultimodalReasoningTools
AITopic score66.4#36 overall

Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts

Evidence coverage5%1 evaluations · 1 institutions
Context / maximum output1M / 65.5ktokens
Cache / input / output$0.2 · $2 · $12USD per million tokens
Value / freshness50.4 / 46relative value · release freshness
Product profile

What this model supports

Inputtext, image, audio, video
Outputtext
Knowledge cutoff2025-11
WeightsProprietary / hosted
Capability profile

Strengths by domain

Coding—0 public results
Research & reasoning—0 public results
Professional work—0 public results
Knowledge & instruction—0 public results
Behind the score

Every result has a source

Raw results and standardized readings are shown together. Missing tests add neither points nor penalties.

Human preference & indices2 results

AA IndexArtificial Analysis67.65 indexReading 66.4

Imported from Artificial Analysis. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: Gemini 3 ProOpen evidence
Arena TextLMArena1,479.4 EloReading 66.4

Direct LMArena text leaderboard result.

Open evidence
Same builder

More from Google