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 3.8 Flash

gemini-flash family · launched 2026-09-02

MultimodalReasoningToolsStructured
AITopic score74.0#16 overall

Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows

Evidence coverage100%9 evaluations · 3 institutions
Context / maximum output1M / 65.5ktokens
Cache / input / output$0.075 · $0.75 · $3.75USD per million tokens
Value / freshness69.4 / 84relative value · release freshness
Product profile

What this model supports

Inputtext, image, pdf
Outputtext
Knowledge cutoffNot disclosed
WeightsProprietary / hosted
Capability profile

Strengths by domain

Coding82.22 public results
Research & reasoning77.32 public results
Professional work56.22 public results
Knowledge & instruction73.82 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.

Coding2 results

LiveBench 2.0 · CodingLiveBench82.20 scoreReading 82.2

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
AIHOT · CodingAIHOT59.80 scoreReading 59.8

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Research & reasoning2 results

LiveBench 2.0 · ResearchLiveBench89.30 scoreReading 89.3

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
AIHOT · ResearchAIHOT65.20 scoreReading 65.2

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Professional work2 results

AIHOT · ProfessionalAIHOT65.40 scoreReading 65.4

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
LiveBench 2.0 · ProfessionalLiveBench47.08 scoreReading 47.1

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Professional = long-agentic, browser, data-analysis and design average.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Knowledge & instruction2 results

LiveBench 2.0 · KnowledgeLiveBench79.10 scoreReading 79.1

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized. Knowledge uses the published LiveBench research suite.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
AIHOT · KnowledgeAIHOT68.50 scoreReading 68.5

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence

Human preference & indices4 results

Arena TextLMArena1,498.5 EloReading 74.0

Direct LMArena text leaderboard result.

Open evidence
AA IndexArtificial Analysis69.55 indexReading 72.1

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

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
AIHOT aggregate leaderboardAIHOT63.40 scoreReading 63.4

Imported from AIHOT aggregate leaderboard. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
LiveBenchLiveBench62.70 scoreReading 62.7

Imported from LiveBench 2.0. The published 0–100 score is used directly; it is not z-score normalized.

Configuration: LiveBench 2.0, AIHOT aggregateOpen evidence
Same builder

More from Google