Skip to content
aiqbench

Google · model passport

Google: Gemini 2.5 Flash

gemini-2-5-flash
  • Cloud only
  • Proprietary licence
  • 1,048,576 context
  • Released 2025-06-05(curated)
14/27axes covered
Overall · LMArena
1,409#138 of 396
Best percentile
85.4BFCL v4 (function calling)
Cohort standing
55.5median 50.8

What the data says

Benchmarked on 14 of 27 tracked axes. Every figure below is the model's own published result on that board.

Strongest axes

  • 85.4 pct — BFCL v4 (function calling) (56.2%)

Weakest axes

  • 6.8 pct — Terminal-Bench (17.1%)

Uneven: 78.6 percentile points between its best and worst axis — 85.4 pct on BFCL v4 (function calling) versus 6.8 pct on Terminal-Bench.

  • BFCL v4 (function calling)Dormant board85.4 pct56.2%Verify →
  • MMLU-Pro (Artificial Analysis)84.6 pct83.2%Verify →
  • LiveCodeBench (Artificial Analysis)77.1 pct69.5%Verify →
  • Instruction following66.2 pct1,399Verify →
  • Overall65.4 pct1,409Verify →
  • HHEM Hallucination (Vectara)63.8 pct92.2%Verify →
  • Hard prompts62.9 pct1,419Verify →
  • IFBench (Artificial Analysis)57.4 pct50.3%Verify →
  • Coding55.2 pct1,424Verify →
  • Vision Arena52.7 pct1,215Verify →
  • Factuality Arena47.7 pct1,436Verify →
  • SimpleBench35.6 pct41.2%Verify →
  • FrontierMath33.3 pct4.8%Verify →
  • Terminal-Bench6.8 pct17.1%Verify →
  • WebDev ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • LiveBenchNot benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • SWE-bench VerifiedNot 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-2.5-flash
Context length1,048,576 tokens
Max output65,535 tokens
Acceptsfile, image, text, audio, video
Input price$0.30 per 1M tokens
Cached input price$0.03 per 1M tokens
Output price$2.50 per 1M tokens

API parameters this endpoint supports

Include reasoningMax tokensReasoningResponse 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-2.5-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-2.5-flash stands at 55.5 (raw mean 56.7) — measured on 14 of 27 axes.

    standingtemplateVerify →

  • gemini-2.5-flash stands at 55.5 versus a cohort median of 50.8 across 141 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 →