← Back to leaderboard

Google

Gemini 3.8 Flash (high)

Released: Sep 2, 2026
Tracked since: 2026-09-03

Intelligence index40.9Ranks 42 of 664 models with this metric

Coding index76.3Ranks 18 of 259 models with this metric

Agentic index40.2Ranks 43 of 156 models with this metric

Capability profile

5 axes vs. site average

Gemini 3.8 Flash (high)

Site average

Pricing

per 1M tokens

Input: $0.750
Output: $3.75
Cache read: $0.070
Cache write: $0.750

Performance

Output throughput: 338 tokens/sec
Time to first token: 22.57s
First answer token: 22.57s
End-to-end response: 24.05s

History

5

Intelligence index

58.7→40.9

Output

Unchanged across 62 days of records

Output throughput

305→338

Cheaper at this level

Models with a comparable intelligence index and a lower output price

Qwen3.8-Flash-NextAlibabaIntelligence 39.8$0.470−87%
GLM 5.3 FlashZ AIIntelligence 41.8$0.500−87%
MiMo-V2.6-ProXiaomiIntelligence 46.3$0.870−77%
DeepSeek V4.1 Flash (Reasoning, Max Effort)DeepSeekIntelligence 39.5$1.20−68%
Step 5 PreviewStepFunIntelligence 43.7$2.70−28%