RankingIA v0.6.1
EN

Gemini 3.5 Flash

Google

75.8#24 of 427 overall
Input / output
US$ 1,50 / US$ 9,00
US$ per 1M tokens
Context
1.0M
tokens
Release
05/19/2026
release date
Weights
Closed
 
Speed
0 tok/s
first token in 0.00 s

Family history

The 8 versions of this family, from first to newest, by release date. Click a point to open that version.

See the data as a table
ModelReleasedScoreRankAA Intel.Elo Arena
Gemini 1.5 Flash05/14/202421.8#395—1287
Gemini 2.0 Flash Thinking Experimental01/21/202534.7#307—1354
Gemini 2.5 Flash06/17/202554.5#106—1417
Gemini 3 Flash Preview12/17/202570.8#36—1466
Gemini 3.5 Flash05/19/202675.8#24—1482
Gemini 3.6 Flash07/21/202676.4#22—1480
Gemini 3.7 Flash08/13/202681.8#13—1489
Gemini 3.8 Flash09/02/202664.5#6530.51498

Scores by source

Scores by sourcepercentile = % of ranked models it beats
MetricValuePercentileSource
Arena text (Elo) weight 2 1482 92% LMArena
Arena WebDev (Elo) weight 1 1499 53% LMArena
Arena vision (Elo) weight 0.5 1308 91% LMArena
Humanity's Last Exam weight 1 42.7 92% Artificial Analysis
Terminal-Bench weight 1 6.6 67% Artificial Analysis
GPQA Diamond 92.2 95% Artificial Analysis
Long-context reasoning 73.3 70% Artificial Analysis

By category

CategoryScoreRankMetrics
Agentic58.5#40Terminal-Bench
Coding51.7#52Arena WebDev (Elo)
Reasoning78.9#17Humanity's Last Exam, GPQA Diamond
Research59.8#99Long-context reasoning
Design51.7#50Arena WebDev (Elo)
Chat71.2#16Arena text (Elo)
Vision70.5#10Arena vision (Elo)

History

RankingIA score on each collection day (hover to see the rank).

Daily collection started on 10/30/2026. The chart appears from the second day the model is ranked.

Compare with other models

At the sources