Skip to content
aiqbench

Google · model passport

Gemini 2 5 Flash Lite Preview 06 17 Thinking

gemini-2-5-flash-lite-preview-06-17-thinking
  • Cloud only
  • Proprietary licence
  • Released 2026-01-09(first seen on LMArena)
5/27axes covered
Overall · LMArena
1,375#178 of 396
Best percentile
56.8Instruction following
Cohort standing
50.3median 55.5

What the data says

Benchmarked on 5 of 27 tracked axes. Every figure below is the model's own published result on that board.

Uneven: 14.8 percentile points between its best and worst axis — 56.8 pct on Instruction following versus 42 pct on Vision Arena.

  • Instruction following56.8 pct1,369Verify →
  • Overall55.3 pct1,375Verify →
  • Hard prompts53.3 pct1,382Verify →
  • Coding45.3 pct1,382Verify →
  • Vision Arena42 pct1,188Verify →
  • WebDev ArenaNot benchmarked
  • Factuality ArenaNot benchmarked
  • Search ArenaNot benchmarked
  • Document ArenaNot benchmarked
  • Agent ArenaNot benchmarked
  • GPQA DiamondNot benchmarked
  • AIME (math)Not benchmarked
  • FrontierMathNot benchmarked
  • SimpleQA VerifiedNot benchmarked
  • ARC-AGI-2Not benchmarked
  • Humanity's Last ExamNot benchmarked
  • SimpleBenchNot benchmarked
  • LiveBenchNot benchmarked
  • BFCL v4 (function calling)Not benchmarked
  • SWE-bench Verified (live board)Not benchmarked
  • Terminal-Bench 4.0Not benchmarked
  • MMLU-Pro (Artificial Analysis)Not benchmarked
  • LiveCodeBench (Artificial Analysis)Not benchmarked
  • IFBench (Artificial Analysis)Not benchmarked
  • HHEM Hallucination (Vectara)Not benchmarked
  • SWE-bench VerifiedNot 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.

  • gemini-2.5-flash-lite-preview-06-17-thinking stands at 50.3 (raw mean 50.5) — measured on 5 of 27 axes.

    standingtemplateVerify →

  • gemini-2.5-flash-lite-preview-06-17-thinking stands at 50.3 versus a cohort median of 55.5 across 115 models released within 180 days — below 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 →