BenchLeader
Menu
Best LLMsChoose a modelLeaderboardsModelsBenchmarksProvidersReleases12
GoogleCompare with another model

Gemini 1.5 Flash

Gemini 1.5 Flash is a Google proprietary model, released 14 May 2024. Its best configuration ranks #541 of 785 on the BenchLeader Index at 44.3 ±3.5, in the lower half. The ± is the point: 288 other configurations score within that range, so they and this one cannot be told apart on quality alone — price and speed are what separate them. It scores highest in human preference (46) and lowest in composite (37). Last measured 22 Oct 2026.

Blended price
–
Output speed
–
First answer
–
Context
1M
Full answer
–
Cost per run
–
Released
14 May 2024
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Overall index44
  2. Reasoning44
  3. Coding43
  4. Maths45
  5. Human preference46
  6. Multimodal37
  7. Composite37

Versions

Google has shipped 12 models under this name. Each is ranked on its own results; a newer version often has fewer results so far, which holds its index nearer the average until more arrive.

ModelReleasedIndexRank
Gemini 3.8 Flashhigh2 Sept 202664.4#50
Gemini 3.7 Flashhigh13 Aug 202663.5#64
Gemini 3.6 Flashhigh21 Jul 202662.0#89
Gemini 3.5 Flashhigh19 May 202663.1#70
Gemini 3 Flashthinking17 Dec 202559.1#138
Gemini 2.5 Flash 09 2025thinking25 Sept 202551.1#351
Gemini 2.5 Flash17 Apr 202552.7#306
Gemini 2.0 Flash5 Feb 202543.2#574
Gemini 1.5 Flash 00224 Sept 202438.3#716
Gemini 1.5 Flash 00123 May 2024––
Gemini 1.5 Flashthis page14 May 202444.3#541
Gemini Flash 2.0–––

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmarknot statedSourceTrend
Arena Hard Prompts1303#260Arena (LMArena)
GPQA Diamond (AA)not in index46.3%#448Artificial Analysis
Humanity's Last Exam (AA)not in index4.4%#508Artificial Analysis

Coding

Benchmarknot statedSourceTrend
Arena Coding1316#263Arena (LMArena)

Maths

Benchmarknot statedSourceTrend
Arena Maths1289#237Arena (LMArena)

Knowledge

Benchmarknot statedSourceTrend
MMLUnot in index77.8%#30Epoch AI Benchmarking Hub

Instruction following

Benchmarknot statedSourceTrend
Arena Instruction Followingnot in index1290#248Arena (LMArena)

Human preference

Benchmarknot statedSourceTrend
Arena Text1309#246Arena (LMArena)
Arena Creative Writingnot in index1298#219Arena (LMArena)
Arena Multi-turnnot in index1277#263Arena (LMArena)
Arena Longer Queriesnot in index1324#238Arena (LMArena)

Multimodal

Benchmarknot statedSourceTrend
Arena Vision1141#120Arena (LMArena)
MMMU-Pro48.4%#246Artificial Analysis
MMMU (validation)56.1%#39MMMU

Composite

Benchmarknot statedSourceTrend
Epoch Capabilities Indexnot in index129.3#148Epoch AI Benchmarking Hub
AA Intelligence Index v4.3.27.1#496Artificial Analysis

Safety & honesty

Benchmarknot statedSourceTrend
FORTRESSnot in index50.6%#13Scale AI SEAL

More from Google

New this month

See also

All Google models

Questions people ask

What are Gemini 1.5 Flash's benchmark scores?
As of 24 Oct 2026, Gemini 1.5 Flash scores 44.3 ±3.5 on the BenchLeader Index, strongest in human preference (46) and weakest in composite (37). That rests on 8 independent benchmark results, and every score on this page links to its publisher.
How does Gemini 1.5 Flash rank?
Gemini 1.5 Flash is #541 of 785 ranked configurations on 24 Oct 2026. 288 other configurations score within its margin, so the exact position matters less than the band. The leader is Claude Opus 5.5 (max effort) at 72.6.
When was Gemini 1.5 Flash released?
Google released Gemini 1.5 Flash on 14 May 2024.

Data as of 24 Oct 2026. Compare with another model.

Cite as: BenchLeader, “Gemini 1.5 Flash: benchmarks, pricing, speed and rank”, data as of 24 Oct 2026, https://www.benchleader.com/models/gemini-1-5-flash.