Artificial Analysis
#7of 12
Score 11.7. Best run: google/gemini-3.5-flash-lite.
Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.
Where Artificial Analysis, LiveBench, LMArena and Berkeley BFCL place Gemini 3.5 Flash Lite, what it costs through OpenRouter and Vercel AI Gateway, and the models either side of it on the consensus.
Read Nov 16, 2026
#45of 69
on the LLM leaderboard, with a consensus score of 42 across 3 leaderboards.
Source: Artificial Analysis, LiveBench, LMArena and Berkeley BFCL, combined by Rank.ai.
By leaderboard
Artificial Analysis
#7of 12
Score 11.7. Best run: google/gemini-3.5-flash-lite.
Intelligence Index: a composite of reasoning, knowledge, maths and coding evaluations.
LiveBench
#31of 32
Score 63.9. Best run: Gemini 3.5 Flash Lite High.
Contamination-limited questions refreshed each release: reasoning, maths, coding, data analysis, language.
LMArena
#21of 66
Score 1459. Best run: gemini-3.5-flash-lite.
Blind head-to-head human votes, style controlled.
Berkeley BFCL
Not measured by Berkeley BFCL.
Function calling and tool use, single turn to multi turn and web search.
Price and context
$0.85
OpenRouter: $0.30 in, $2.50 out. Vercel AI Gateway: $0.30 in, $2.50 out Context window 1.0M tokens. LiveBench cost per solved task $0.069.
Nearby
Enter your website. In about two minutes, Rank.ai asks ChatGPT, Claude and Gemini 12 questions your customers ask and grades how often they name you.