Google · proprietary

Gemini 3.1 Flash-Lite

Gemini 3.1 Flash-Lite by Google appears in 1 source with Reasoning at 41.75. Best read for LLM, Long context, Low cost.

CreatorGoogle

Release date2026-03-03

Knowledge cutoffNot published

Context1M tokens

Input price$0.25/M tokens

Output price$1.5/M tokens

Modalitytext + vision

CountryUS

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank47ranking · source_rank

LLM Stats Code Index (estimated from arena)21.29 scoremetric

Reasoning41.75reasoning · index_reasoning

Math31.77math · index_math

Vision25.11multimodal · index_vision

Long context30.64long_context · index_long_context

Healthcare39.95domain · index_healthcare

GPQA86.9 %reasoning · gpqa_score

Code Arena976.94 %coding · coding_arena_score

Humanity Last Exam16 %reasoning · hle_score

MMMLU88.9 %reasoning · mmmlu_score

MMMU-Pro76.8 %multimodal · mmmu_pro_score

SimpleQA43.3 %knowledge · simpleqa_score

MRCR v260.1 %long_context · mrcr_v2_score

CharXiv-R73.2 %multimodal · charxiv_r_score

Context1,000,000 tokenscontext · context

Speed611.9 c/sperformance · throughput

Latency2,421 msperformance · latency

Input price0.25 $/Mpricing · input_price

Output price1.5 $/Mpricing · output_price

Evidence

Citations and source overlap

LLM StatsPublic full LLM leaderboard advanced explorer snapshot, including ranking, benchmark indexes, pricing, speed, context, license, and model metadata.Retrieved 2026-06-01

FAQ

How should I read this profile?

Treat this as a source-backed model dossier, not an EvalKit-run verification. The public values are replicated from linked sources and kept source-scoped.

Is Gemini 3.1 Flash-Lite verified by EvalKit?

No. EvalKit currently shows 0 verified rows until real run evidence exists.

Why can metrics disagree?

Different sources test different tasks, dates, prompts, and aggregation methods. EvalKit keeps those differences visible instead of merging them into a fake universal score.