Gemini 3.5 Flash (high)

May 19, 2026Last synced Aug 1, 2026, 12:19 AM1049K context

Human Frontier

89.2

Human-calibrated frontier signal, backed by Arena-style preference evidence and separate from raw AgMoBench benchmark composite scores.

Blended Price

$3.38/M

Input Price

$1.50/M

Output Price

$9.00/M

Speed

221 tok/s

TTFT

10.95s

Benchmark Scores

Intelligence Index

Performance Radar

Gemini 3.5 Flash (high)

Field Average

External Benchmarks

AA-Omniscience Index

How Gemini 3.5 Flash (high) Compares

Axes

X Axis

Y Axis

Bubble Size

Filters

Blended Price (USD)$0.00 – $37.5

AgMoBench Overall≥ 1.8

Providers

ai2ai21-labsalibabaanthropicarceeawsazurebaidu

Show quadrants

anthropic

openai

mistral

azure

cohere

meta

ai21-labs

inclusionai

google

ai2

ibm

alibaba

upstage

nvidia

aws

kimi

nous-research

thinking-machines

minimax

stepfun

tencent

deepseek

zai

multiversecomputing

xiaomi

xai

deepcogito

sarvam

kwaikat

baidu

swiss-ai-initiative

bytedance_seed

inception

reka-ai

arcee

perplexity

Bubble size = Context Window

8191.00

2000000.00

Compare with other models

GPQA Diamond

92.2 / 100

LiveCodeBench

— / 100

Terminal-Bench Hard

40.9 / 100

τ²-Bench

95.3 / 100

ARC-AGI-1arc_agi

92.5 / 100

ARC-AGI-1 Cost per Taskarc_agi

0.4

ARC-AGI-2arc_agi

72.1 / 100

ARC-AGI-2 Cost per Taskarc_agi

0.9

BullshitBenchbullshitbench

20.0 / 100

Arena ELO: Codingchatbot_arena

1492.0

arena_elo_documentchatbot_arena

1481.0

Chatbot Arena ELOchatbot_arena

1476.0

arena_elo_visionchatbot_arena

1277.0

Ale Benchepoch_ai

566.2

Apex Agentsepoch_ai

3.3

Arc Agi 2epoch_ai

0.7

Chess Puzzlesepoch_ai

0.5

Enigma Evalepoch_ai

0.3

Epoch Capabilities Indexepoch_ai

154.6

Mystery Game Puzzlesepoch_ai

0.3

OTIS Mock AIME 2024–2025epoch_ai

1.0

Proofbenchepoch_ai

0.3

SimpleQA Verified (Epoch)epoch_ai

0.7

FrontierMathfrontiermath

39.0 / 100

LegalBenchlegalbench

83.6 / 100

LiveBench Codinglivebench

78.2 / 100

LiveBench Data Analysislivebench

64.9 / 100

LiveBench Instruction Followinglivebench

75.6 / 100

LiveBench Languagelivebench

84.6 / 100

LiveBench Mathlivebench

88.2 / 100

LiveBench Overalllivebench

75.0 / 100

LiveBench Reasoninglivebench

82.0 / 100

AIME 2026matharena

95.0

OpenRouter Token Volumeopenrouter_rankings

470000000000.0

OpenRouter Weekly Trendopenrouter_rankings

3.0

SimpleBenchsimplebench

76.7 / 100

WeirdMLweirdml

62.6 / 100

Senior SWE-Bench v2026.06senior_swe_bench

v2026.06 · official-100-task · Gemini 3.5 Flash (high) · harness mini-swe-agent · effort high · 1 attempt · pass@1 · harbor:snorkel-ai/senior-swe-bench-v2026.06 · provider google/gemini-3.5-flash · record gemini-3-5-flash-mini-swe · run 81a3966a96064929ee903c851f910db97c925b6374c977b4e44de27195ae9c35

View run source

Source metadata

{
  "taskCount": 100,
  "agentGroup": "mini-swe-agent:gemini-3.5-flash",
  "basicPassAt1": 22.105263157894736,
  "basicPassAt3": 38.94736842105263,
  "datasetPackage": "snorkel-ai/senior-swe-bench-v2026.06",
  "publicTaskCount": 50,
  "tastefulPassAt1": 6.315789473684211,
  "tastefulPassAt3": 17.894736842105264,
  "agentDescription": "Google Gemini 3.5 Flash via mini-swe-agent harness (Portkey→Google)",
  "privateTaskCount": 50,
  "upstreamProvider": "google",
  "upstreamRunCount": 80,
  "averageAgentSteps": 230.83870967741936,
  "averageOutputTokens": 70372.86021505376,
  "averageTotalCostUsd": 4.368946809032258,
  "averageOutputCostUsd": 0.6333557419354838,
  "basicAllThreePassRate": 13.684210526315791,
  "tastefulAllThreePassRate": 2.1052631578947367
}

Evidence observed 2026-07-29

6.3 / 100

SWE-rebenchswe_rebench

vcontinuous-leaderboard · tasks-created:2026-03-01:2026-05-15 · Gemini 3.5 Flash · harness swe-rebench-react@tools · 5 attempts · pass@1 · swe-rebench:standardized:128k-or-model-limit · provider Gemini 3.5 Flash__tools · record Gemini 3.5 Flash__tools:1772323200000:1778803200000

View run source

Source metadata

{
  "passAt5": 61.81818181818181,
  "developer": "google",
  "instanceType": "model",
  "contextPolicy": "128k unless the model supports less",
  "attemptsPerTask": 5,
  "totalTokenUsage": 1848593.0709090908,
  "modelReleaseDate": "2026-05-19",
  "scoreStandardError": 0.9791208740244552,
  "cachedTokenPercentage": 75.66134999998506,
  "modelReleaseTimestamp": 1779148800000,
  "standardContextTokens": 128000,
  "averageInstanceCostUsd": 0.7666600170000002,
  "potentialContamination": true,
  "aggregateTaskRangeTimestamp": {
    "to": 1778803200000,
    "from": 1772323200000
  },
  "publishedTaskRangeTimestamp": {
    "to": 1778803200000,
    "from": 1772323200000
  }
}

Evidence observed 2026-05-15

49.5 / 100