Inference
EN
Google

Gemini 2.5 Flash Lite Preview Thinking

Gemini 2.5 Flash Lite Preview Thinking is a model from Google. It has 5 scored results in 4 categories. It has no index.

  • Input: text
UnrankedEnough results for an index.
IndexAll categories, out of 100.UnrankedMedian 51.0
CoverageIndex weight that has results.55%
SpeedOutput tokens per second.—Median 67/s
First tokenSeconds to the first output token.—Median 1.3 s
Input / 1MUS dollars per 1M input tokens.—Median $0.60
Output / 1MUS dollars per 1M output tokens.—Median $2.55
ContextMaximum tokens in one request.—Median 262K
EloLMArena rating and rank.—Median 1422

Capabilities

Index per category, out of 100.
Out of 100
AgenticMulti-step tasks with tools.None counted——
CodingCode writing and repair.1 counted48.6—
ReasoningLogic problems and puzzles.None counted——
MultimodalTasks with images and text.1 counted53.3—
KnowledgeFacts and expert knowledge.2 counted42.9—
MultilingualTasks in many languages.None counted——
InstructionTasks with strict prompt rules.None counted——
MathMath problems.1 counted33.9—

Results

5 counted
BenchmarkThe benchmark name.ResultThe score from the source.PlacePlace among results on this benchmark.
MMMU ProMultimodal75.4% ±1.055 / 92
LiveCodeBenchCoding71.4% ±1.185 / 142
GPQA Diamond · Vals AIKnowledge70.2% ±2.392 / 135
AIMEMath42.1% ±1.668 / 95
MMLU ProKnowledge79.1% ±0.499 / 135
LegalBenchLegal82.0% ±0.477 / 149
MedQAHealthcare88.9% ±0.353 / 95
CorpFin v2Finance57.6% ±1.087 / 131
MGSMMultilingual88.4% ±1.952 / 74
MortgageTaxFinance57.6% ±1.073 / 97
MedCodeHealthcare34.2% ±1.780 / 106
TaxEval v2Finance64.7% ±0.9117 / 143
MedScribeHealthcare66.9% ±1.9100 / 109

Sources

BenchLMCC BY-NC 4.0Vals AINo licence stated

More from Google

All models
Gemini 4 Carbon82.7Gemini 4 Argon78.5Gemini 3.7 Flash68.5Gemini 3.8 Flash67.8Gemini 3.5 Flash64.2