Back to models
Intelligence Index
High setting
22.2#49 of 83measured models
Measured · Artificial Analysis v4.3.2- API price from
- $0.30 in / $2.50 out / 1M tokGoogle · direct API
- Maximum input
- 1.05M tok
Performance profile
ReasoningRank #42 of 107
83.8%
GPQA DiamondCodingRank #59 of 94
41.3%
SciCodeCost efficiencyRank #26 of 67
115.0pts / $
Intelligence ÷ eval costCapabilities
Maximum input
Modalities
Integration
Reasoning trade-offs
Source (opens in a new tab)Gemini 3.5 Flash-Lite
Cost per task (USD) · log scale
Gemini 3.5 Flash-LiteHigh
- Intelligence Index
- 22.2
- Cost / task
- $0.1927
- Evaluation time
- 37.7s
Pricing & access
API route
GoogleAPI
GoogleAPITier & contextStandard
USD per 1M tokens
- Input
- $0.30
- Output
- $2.50
- Cached input
- $0.03
Gemini API tool compatibility (opens in a new tab)
- Code execution
- Computer use (preview)
- File search
- Maps
- Web search
- URL context
Benchmarks
Full leaderboardSource (opens in a new tab)18.8%, rank 68 of 12641.3%, rank 59 of 941.0%, rank 39 of 8776.0%, rank 49 of 125983 Elo, rank 52 of 101
Humanity’s Last Exam
Frontier reasoning- 1Claude Opus 5.5Max61.4%
- 2Claude Fable 5.1Max59.1%
- 3Gemini 4 ArgonHigh57.1%
- 65GPT-5.5 Instant (June 2026)Reasoning19.9%
- 66gpt-oss-120bHigh19.6%
- 67Gemma 4 26B A4BReasoning19.3%
- 68Gemini 3.5 Flash-LiteHigh18.8%
- 69Quasar 438BMax18.7%
- 70K-EXAONE 2.0 0803Reasoning18.6%
- 71K2 Horizon 7BReasoning18.2%
Peers use their best measured result on this benchmark.
Alternatives
- Scores higherLing-3.0-flash-FinReasoning
- Intelligence Index
- 22.6+0.4
- Higher score, lower costGPT-6 LunaMax
- Intelligence Index
- 38.1+16.0
- Cost / task
- $0.068−65%
- More from GoogleGemma 4 31BReasoning
- Intelligence Index
- 14.7−7.5
- Cost / task
- $0.00−100%
Each model at its highest-scoring measured setting · Intelligence Index v4.3.2 and its evaluation cost per task.