Google · proprietary

Gemini 3.5 Flash

Gemini 3.5 Flash by Google appears in 1 source with Reasoning at 59.19. Best read for LLM, Long context, Low cost.

CreatorGoogle

Release date2026-05-19

Knowledge cutoffNot published

Context1M tokens

Input price$1.5/M tokens

Output price$9/M tokens

Modalitytext + vision

CountryUS

Metrics

All source-backed metrics

Open in leaderboard

LLM Stats Rank14ranking · source_rank

Reasoning59.19reasoning · index_reasoning

Math40.57math · index_math

Coding46.37coding · index_code

Vision40.09multimodal · index_vision

Tool calling42.18tool_calling · index_tool_calling

Long context14.31long_context · index_long_context

Finance33.8domain · index_finance

Legal37.44domain · index_legal

Code Arena1,507.03 %coding · coding_arena_score

Humanity Last Exam40.2 %reasoning · hle_score

ARC-AGI v272.1 %reasoning · arc_agi_v2_score

MMMU-Pro83.6 %multimodal · mmmu_pro_score

Toolathlon56.5 %tool_calling · toolathlon_score

MCP Atlas83.6 %tool_calling · mcp_atlas_score

MRCR v226.6 %long_context · mrcr_v2_score

SWE-bench Pro55.1 %coding · swe_bench_pro_score

CharXiv-R84.2 %multimodal · charxiv_r_score

Context1,048,576 tokenscontext · context

Speed188.94 c/sperformance · throughput

Latency4,492.42 msperformance · latency

Input price1.5 $/Mpricing · input_price

Output price9 $/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 3.5 Flash 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.