Skip to content
aiqbench

Google · model passport

Google: Gemini 3.5 Flash

gemini-3-5-flash
  • Cloud only
  • Proprietary licence
  • 1,048,576 context
  • Released 2026-09-13(first seen on LMArena)
18/27axes covered
Overall · LMArena
1,477#26 of 396
Best percentile
95.4SimpleBench
Cohort standing
80.3median 60.3

What the data says

Benchmarked on 18 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 95.4 pct — SimpleBench (76.7%)
  • 94.4 pct — IFBench (Artificial Analysis) (76.3%)
  • 93.8 pct — SWE-bench Verified (79.3%)

Uneven: 48 percentile points between its best and worst axis — 95.4 pct on SimpleBench versus 47.4 pct on Document Arena.

  • SimpleBench95.4 pct76.7%Verify →
  • IFBench (Artificial Analysis)94.4 pct76.3%Verify →
  • SWE-bench Verified93.8 pct79.3%Verify →
  • Overall93.7 pct1,477Verify →
  • LiveBench91.8 pct74.6%Verify →
  • GPQA Diamond91.4 pct92.8%Verify →
  • Factuality Arena91.3 pct1,477Verify →
  • Hard prompts91.2 pct1,495Verify →
  • Instruction following90.9 pct1,466Verify →
  • Vision Arena88 pct1,285Verify →
  • FrontierMath87 pct39.0%Verify →
  • SimpleQA Verified86.6 pct66.2%Verify →
  • SWE-bench Verified (live board)86.2 pct71.8%Verify →
  • Coding86.2 pct1,508Verify →
  • AIME (math)81.5 pct95.6%Verify →
  • ARC-AGI-278.7 pct72.1%Verify →
  • WebDev Arena61.9 pct1,499Verify →
  • Document Arena47.4 pct1,461Verify →
  • Search ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • Humanity's Last ExamNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • Terminal-BenchNot benchmarked

Percentiles are the model's standing within each board's own population. Axes marked "not benchmarked" have no published result for this model — that is an absence of data, not a low score.

How to run it

Use it hosted

API model IDgoogle/gemini-3.5-flash
Context length1,048,576 tokens
Max output65,536 tokens
Acceptstext, image, video, file, audio
Input price$1.50 per 1M tokens
Cached input price$0.15 per 1M tokens
Output price$9 per 1M tokens

API parameters this endpoint supports

Include reasoningMax tokensReasoningReasoning effortResponse formatSeedStop sequencesStructured outputsTemperatureTool choiceTool callingTop-p

Example request

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-3.5-flash","messages":[{"role":"user","content":"Hello"}]}'

View on OpenRouter →

Identifiers, limits and prices are synced from the upstream source shown above. Any field we haven't synced is left out entirely rather than guessed.

  • gemini-3.5-flash-high stands at 80.3 (raw mean 85.4) — measured on 18 of 27 axes.

    standingtemplateVerify →

  • gemini-3.5-flash-high stands at 80.3 versus a cohort median of 60.3 across 176 models released within 180 days — above the peer median.

    cohorttemplateVerify →

Every claim is a computed fact from the current board data, phrased by a low-temperature model call and rejected by a validation gate if any number is not in the source row. How the leaderboards work →