Gemini 3.6 Flash

Gemini 3.6 Flash is a reasoning model from Google. 41 benchmarks count toward its score, in 8 categories.

availableShows if the model has enough results for an index.
IndexOverall score. 50 is the middle.66.8 ±2.5
CoverageShare of the index weight with results.100%
SpeedOutput tokens per second.133/s
Input / 1MUS dollars per 1M input tokens.$0.75 batch $0.375
Output / 1MUS dollars per 1M output tokens.$3.75 batch $1.88 US dollars per 1M output tokens in a batch.
ContextMaximum tokens in one request.1.05M
EloLMArena rating and rank.1476 (#18)

50 is the middle of the board. The range shows the doubt in the index. Batch work costs less.

26,445 votes. Elo shows what people prefer. It does not change the score.

CapabilitiesScore per category. 50 is the middle.

50 is the middle
AgenticMulti-step tasks with tools.
63.1
CodingCode writing and repair.
64.9
ReasoningLogic problems and puzzles.
65.1
MultimodalTasks with images and text.
70.0
KnowledgeFacts and expert knowledge.
69.2
MultilingualTasks in many languages.
92.4
InstructionTasks with strict rules in the prompt.
78.9
MathMath problems.
62.7

Results

41 counted
BenchmarkThe test name.CategoryThe capability that the test measures.ResultThe score from the publisher.IndexThis result on the index scale.RunThe settings of the run.DateDate of the result.Published byThe source of the result.
OTIS Mock AIME 2024-2025Math94.2%64.2high effortEpoch AI
GPQA diamondKnowledge94.1%65.1high effortEpoch AI
GPQA DiamondKnowledge93.4%64.51 Sept 2026Vals AI
Artificial Analysis GPQA DiamondKnowledge92.8%63.7Artificial Analysis
ARC-AGI-1 (semi-private)Reasoning91.2%70.3high effortARC Prize Foundation
MMLU ProKnowledge89.3%61.21 Sept 2026Vals AI
MMMU ProMultimodal88.4%71.21 Sept 2026Vals AI
LiveCodeBenchCoding88.1%64.41 Sept 2026Vals AI
LiveBench MathematicsMath86.4%63.3high effort25 Jun 2026LiveBench
LiveBench ReasoningReasoning85.1%74.2high effort25 Jun 2026LiveBench
LiveBench LanguageKnowledge83.9%71.8high effort25 Jun 2026LiveBench
Artificial Analysis MMMU-ProMultimodal83.2%68.8Artificial Analysis
OSWorld-VerifiedAgentic83.0%71.0Tianbao Xie et al.
Artificial Analysis Long Context ReasoningReasoning80.0%63.6Artificial Analysis
SWE-benchCoding79.6%61.41 Sept 2026Vals AI
LiveBench CodingCoding77.9%66.9high effort25 Jun 2026LiveBench
EuroEval SwedishMultilingual75.9%95.0EuroEval
EuroEval FrenchMultilingual75.6%95.0EuroEval
LiveBench Instruction FollowingInstruction75.4%78.9high effort25 Jun 2026LiveBench
EuroEval ItalianMultilingual75.1%95.0EuroEval
Terminal-Bench 2.1Agentic73.8%67.621 Sept 2026Vals AI
EuroEval PortugueseMultilingual72.6%92.9EuroEval
EuroEval DutchMultilingual71.8%91.9EuroEval
Artificial Analysis Coding IndexCoding69.2%67.7Artificial Analysis
EuroEval SpanishMultilingual66.8%85.7EuroEval
SimpleQA VerifiedKnowledge66.2%82.8high effortEpoch AI
EuroEval GermanMultilingual66.0%84.6EuroEval
EuroEval PolishMultilingual65.9%84.5EuroEval
Vibe Code Bench v1.1Coding64.0%68.8OpenHands21 Sept 2026Vals AI
LiveBench Data AnalysisReasoning63.0%43.4high effort25 Jun 2026LiveBench
ARC-AGI-2 (semi-private)Reasoning60.4%70.2high effortARC Prize Foundation
FrontierMath-Tiers-1-3-v2-PrivateMath58.9%64.6high effortEpoch AI
cursorBench32Coding53.5%62.4Benchmark authors
Artificial Analysis SciCodeCoding53.4%67.0Artificial Analysis
Artificial Analysis Omniscience AccuracyKnowledge50.0%75.7Artificial Analysis
DeepSWEAgentic49.0%59.4Datacurve AI
LiveBench Agentic CodingAgentic43.4%57.6high effort25 Jun 2026LiveBench
Artificial Analysis Humanity's Last ExamKnowledge40.8%68.8Artificial Analysis
Chess PuzzlesReasoning40.0%75.2high effortEpoch AI
GDPval-AA normalizedAgentic38.2%64.9Artificial Analysis
IOICoding35.1%60.921 Sept 2026Vals AI
Artificial Analysis Intelligence IndexKnowledge34.0%64.9Artificial Analysis
Code MigrationCoding30.9%64.721 Sept 2026Vals AI
Artificial Analysis Agentic IndexAgentic30.1%61.8Artificial Analysis
Mystery Game PuzzlesReasoning30.0%65.8high effortEpoch AI
Furniture AssemblyReasoning23.3%56.1high effortEpoch AI
FrontierMath-Tier-4-v2-PrivateMath22.0%58.5high effortEpoch AI
Critical Physics TasksReasoning10.6%60.6Artificial Analysis
Terminal-Bench 4.0Agentic4.5%62.721 Sept 2026Vals AI
ProgramBenchCoding0.0%21 Sept 2026Vals AI
Agent Arena steerabilityAgentic-3.463.6high effort15 Sept 2026LMArena
Agent Arena task outcomeAgentic-6.859.7high effort15 Sept 2026LMArena
Agent Arena command recoveryAgentic-12.453.4high effort15 Sept 2026LMArena

41 benchmarks count, from 52 of 53 results. A grey row does not count. Too few models took that benchmark.

Sources

BenchLM benchmark aggregationUsed with attribution; per-benchmark results credited to their original authorsOpenRouter, collected directlyNo licence statedEpoch AI, collected directlyCC BY — free to use and redistribute with attributionVals AI, collected directlyNo licence stated. Read from the public leaderboard and credited to Vals AIARC Prize Foundation, collected directlyNo licence stated. Their terms ask for written permission before commercial useLiveBench, collected directlyNo licence stated for the leaderboard. The site repo serving these CSVs has no LICENSE; the harness repo carries upstream Apache-2.0 and MIT copies that cover code, not resultsEuroEval, collected directlyMIT — the leaderboard site and its CSV routes are in the licensed repositoryLMArena, collected directlyCC BY 4.0 (lmarena-ai/leaderboard-dataset on Hugging Face)

Same level, lower price

Qwen3.8-Flash-Next66.4 · Freedots3-note Preview65.5 · FreeDeepSeek V4 Flash 073164.6 · $0.28

More from Google

Gemini 3.7 Flash72.3Gemini 3.8 Flash72.1Gemini 3.5 Flash67.3Gemini 3.1 Pro64.7Gemini 3 Pro60.5