Google Models: Intelligence, Performance & Price
Gemini 3.8 Flash (high)Gemini 3.8 Flash (medium)Gemini 3.8 Flash (low)Gemini 3.1 Pro PreviewGemini 3.5 Flash-LiteArtificial Analysis Intelligence Index
Artificial Analysis has benchmarked 65 models from Google. Below is a comparison of the key metrics across these models.
- For intelligence, the top model from Google is Gemini 3.8 Flash (high) at 41.
- For output speed, the fastest model is Gemini 3.5 Flash-Lite at 337 t/s.
- For latency, Gemma 4 E4B (Non-reasoning) at 0.80s offers the lowest time to first answer token.
- For pricing, Gemini 3.5 Flash-Lite at $0.12 offers the lowest cost per task. Prices vary up to 10x across models.
Intelligence
Artificial Analysis Intelligence Index
Intelligence Index vs. Cost per Intelligence Index Task
Cost
Cost per Intelligence Index Task
Speed & Latency
Output Speed
Capability Scores
Capability Indexes
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, AutomationBench-AA, AA-LCR v1.1, GDP.pdf · Higher is better
Incorporates 7 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, Humanity's Last Exam, AA-LCR v1.1, GDP.pdf, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, GDPval-AA v2.1, AA-Briefcase v1.1, MLCR-AA, Humanity's Last Exam, AutomationBench-AA · Higher is better
Incorporates 6 evaluations: AA-Omniscience, Humanity's Last Exam, CritPt, GDPval-AA v2.1, AA-Briefcase v1.1, Terminal-Bench 4.0 · Higher is better
Incorporates 5 evaluations: AA-Omniscience, Humanity's Last Exam, GDPval-AA v2.1, AA-Briefcase v1.1, AA-LCR v1.1 · Higher is better
All Google Releases
Gemini 3.8 Flash
3 models
41
Highest Intelligence
Gemini 3.7 Flash
3 models
40
Highest Intelligence
Gemini 3.5 Flash-Lite
1 model
22
Highest Intelligence
Gemini 3.6 Flash
1 model
34
Highest Intelligence
DiffusionGemma 26B A4B
1 model
10
Highest Intelligence
Gemma 4 12B
2 models
14
Highest Intelligence
Gemini 3.5 Flash
3 models
34
Highest Intelligence
Gemma 4 E4B
2 models
9
Highest Intelligence
Gemma 4 26B A4B
2 models
17
Highest Intelligence
Gemma 4 31B
2 models
19
Highest Intelligence
Gemma 4 E2B
2 models
8
Highest Intelligence
Gemini 3.1 Flash-Lite
1 model
16
Highest Intelligence
Gemini 3.1 Pro Preview
1 model
30
Highest Intelligence
Gemini 3 Deep Think
1 model
Gemini 3 Flash Preview
2 models
26
Highest Intelligence
Gemini 3 Pro Preview
2 models
28
Highest Intelligence
Gemini 2.5 Flash-Lite Preview (Sep '25)
2 models
10
Highest Intelligence
Gemini 2.5 Flash Preview (Sep '25)
2 models
15
Highest Intelligence
Gemma 3 270M
1 model
5
Highest Intelligence
Gemma 3n E2B Instruct
1 model
5
Highest Intelligence
Gemma 3n E4B Instruct
1 model
5
Highest Intelligence
Gemini 2.5 Flash-Lite
2 models
9
Highest Intelligence
Gemini 2.5 Pro
1 model
16
Highest Intelligence
Gemini 2.5 Flash
2 models
13
Highest Intelligence
Gemma 3n E4B Instruct Preview (May '25)
1 model
6
Highest Intelligence
Gemini 2.5 Pro Preview (May' 25)
1 model
15
Highest Intelligence
Gemini 2.5 Flash Preview
2 models
12
Highest Intelligence
Gemini 2.5 Pro Preview (Mar' 25)
1 model
15
Highest Intelligence
Gemma 3 1B Instruct
1 model
5
Highest Intelligence
Gemma 3 12B Instruct
1 model
4
Highest Intelligence
Gemma 3 27B Instruct
1 model
5
Highest Intelligence
Gemma 3 4B Instruct
1 model
5
Highest Intelligence
Gemini 2.0 Flash-Lite (Feb '25)
1 model
7
Highest Intelligence
Gemini 2.0 Flash (Feb '25)
1 model
9
Highest Intelligence
Gemini 2.0 Flash-Lite (Preview)
1 model
7
Highest Intelligence
Gemini 2.0 Pro Experimental (Feb '25)
1 model
9
Highest Intelligence
Gemini 2.0 Flash Thinking Experimental (Jan '25)
1 model
9
Highest Intelligence
Gemini 2.0 Flash Thinking Experimental (Dec '24)
1 model
7
Highest Intelligence
Gemini 2.0 Flash (experimental)
1 model
8
Highest Intelligence
Gemini 1.5 Flash-8B
1 model
6
Highest Intelligence
Gemini 1.5 Flash (Sep '24)
1 model
7
Highest Intelligence
Gemini 1.5 Pro (Sep '24)
1 model
8
Highest Intelligence
Gemini 1.5 Pro (May '24)
1 model
6
Highest Intelligence
Gemini 1.5 Flash (May '24)
1 model
6
Highest Intelligence
Gemini 1.0 Pro
1 model
5
Highest Intelligence
Gemini 1.0 Ultra
1 model
6
Highest Intelligence
PALM-2
1 model
5
Highest Intelligence
Further details
Weights | Provider Benchmarks | ||||||||
|---|---|---|---|---|---|---|---|---|---|
| Gemini 3.8 Flash (high) | Google | 41 | - | 1M | $0.6 | 285 | Not available | | |
| Gemini 3.8 Flash (medium) | Google | 40 | - | 1M | $0.6 | - | Not available | | |
| Gemini 3.7 Flash (medium) | Google | 40 | - | 1M | $0.6 | 304 | Not available | | |
| Gemini 3.7 Flash (high) | Google | 39 | - | 1M | $0.6 | 308 | Not available | | |
| Gemini 3.7 Flash (low) | Google | 37 | - | 1M | $0.6 | 310 | Not available | | |
| Gemini 3.6 Flash (high) | Google | 34 | - | 1M | $0.6 | 209 | Not available | | |
| Gemini 3.5 Flash (medium) | Google | 34 | - | 1M | $1.3 | 270 | Not available | | |
| Gemini 3.8 Flash (low) | Google | 33 | - | 1M | $0.6 | - | Not available | | |
| Gemini 3.5 Flash (high) | Google | 33 | - | 1M | $1.3 | 204 | Not available | | |
| Gemini 3.1 Pro Preview | Google | 30 | - | 1M | $1.7 | 116 | Not available | | |
| Gemini 3 Pro Preview (high) | Google | 28 | - | 1M | $1.7 | - | Not available | | |
| Gemini 3 Flash Preview (Reasoning) | Google | 26 | - | 1M | $0.4 | 215 | Not available | | |
| Gemini 3.5 Flash (minimal) | Google | 24 | - | 1M | $1.3 | 212 | Not available | | |
| Gemini 3 Pro Preview (low) | Google | 22 | - | 1M | $1.7 | - | Not available | | |
| Gemini 3.5 Flash-Lite | Google | 22 | - | 1M | $0.3 | 337 | Not available | | |
| Gemma 4 31B (Reasoning) | Google | 19 | 30.7B | 256k | $0.0 | 35 |    +8 | ||
| Gemini 3 Flash Preview (Non-reasoning) | Google | 18 | - | 1M | $0.4 | 220 | Not available | | |
| Gemma 4 26B A4B (Reasoning) | Google | 17 | 25.2B 3.8B active at inference time | 256k | $0.1 | - |   +6 | ||
| Gemini 2.5 Pro | Google | 16 | - | 1M | $1.3 | 139 | Not available | | |
| Gemini 3.1 Flash-Lite | Google | 16 | - | 1M | $0.2 | 320 | Not available | | |
| Gemini 2.5 Flash Preview (Sep '25) (Reasoning) | Google | 15 | - | 1M | - | - | Not available | - | |
| Gemini 2.5 Pro Preview (Mar' 25) | Google | 15 | - | 1M | - | - | Not available | - | |
| Gemini 2.5 Pro Preview (May' 25) | Google | 15 | - | 1M | $1.3 | - | Not available | | |
| Gemma 4 12B (Reasoning) | Google | 14 | 12B | 256k | $0.1 | 114 |  | ||
| Gemma 4 31B (Non-reasoning) | Google | 14 | 30.7B | 256k | $0.2 | 54 |   +6 | ||
| Gemma 4 26B A4B (Non-reasoning) | Google | 13 | 25.2B 3.8B active at inference time | 256k | $0.1 | 107 |  +6 | ||
| Gemini 2.5 Flash (Reasoning) | Google | 13 | - | 1M | $0.3 | 221 | Not available | | |
| Gemini 2.5 Flash Preview (Sep '25) (Non-reasoning) | Google | 12 | - | 1M | - | - | Not available | - | |
| Gemini 2.5 Flash Preview (Reasoning) | Google | 12 | - | 1M | - | - | Not available | - | |
| Gemini 2.5 Flash-Lite Preview (Sep '25) (Reasoning) | Google | 10 | - | 1M | $0.1 | - | Not available | | |
| Gemini 2.5 Flash (Non-reasoning) | Google | 10 | - | 1M | $0.3 | 226 | Not available | | |
| DiffusionGemma 26B A4B | Google | 10 | 25.2B 3.8B active at inference time | 256k | - | - | - | ||
| Gemini 2.0 Flash Thinking Experimental (Jan '25) | Google | 9 | - | 1M | - | - | Not available | - | |
| Gemma 4 12B (Non-reasoning) | Google | 9 | 12B | 262k | $0.1 | 124 | | ||
| Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) | Google | 9 | - | 1M | $0.1 | - | Not available | | |
| Gemini 2.0 Flash (Feb '25) | Google | 9 | - | 1M | - | - | Not available | - | |
| Gemma 4 E4B (Reasoning) | Google | 9 | 8B 4.5B active at inference time | 128k | $0.0 | 58 |  | ||
| Gemini 2.0 Pro Experimental (Feb '25) | Google | 9 | - | 2M | - | - | Not available | - | |
| Gemini 2.5 Flash Preview (Non-reasoning) | Google | 9 | - | 1M | - | - | Not available | - | |
| Gemini 2.5 Flash-Lite (Reasoning) | Google | 9 | - | 1M | $0.1 | 363 | Not available | | |
| Gemini 2.0 Flash (experimental) | Google | 8 | - | 1M | $0.0 | - | Not available | | |
| Gemini 1.5 Pro (Sep '24) | Google | 8 | - | 2M | - | - | Not available | - | |
| Gemma 4 E2B (Reasoning) | Google | 8 | 5.1B 2.3B active at inference time | 128k | - | - | - | ||
| Gemma 4 E4B (Non-reasoning) | Google | 7 | 8B 4.5B active at inference time | 128k | $0.0 | 60 | | ||
| Gemini 2.0 Flash-Lite (Feb '25) | Google | 7 | - | 1M | - | - | Not available | - | |
| Gemini 2.0 Flash-Lite (Preview) | Google | 7 | - | 1M | - | - | Not available | - | |
| Gemini 1.5 Flash (Sep '24) | Google | 7 | - | 1M | - | - | Not available | - | |
| Gemini 2.5 Flash-Lite (Non-reasoning) | Google | 7 | - | 1M | $0.1 | 294 | Not available | | |
| Gemini 2.0 Flash Thinking Experimental (Dec '24) | Google | 7 | - | 2M | - | - | Not available | - | |
| Gemma 4 E2B (Non-reasoning) | Google | 6 | 5.1B 2.3B active at inference time | 128k | - | - | - | ||
| Gemini 1.5 Pro (May '24) | Google | 6 | - | 2M | - | - | Not available | - | |
| Gemini 1.5 Flash-8B | Google | 6 | 8B | 1M | - | - | Not available | - | |
| Gemini 1.5 Flash (May '24) | Google | 6 | - | 1M | - | - | Not available | - | |
| Gemini 1.0 Ultra | Google | 6 | - | 33k | - | - | Not available | - | |
| Gemma 3n E4B Instruct Preview (May '25) | Google | 6 | 8.4B 4B active at inference time | 32k | - | - | - | ||
| PALM-2 | Google | 5 | - | 8k | - | - | Not available | - | |
| Gemini 1.0 Pro | Google | 5 | - | 33k | - | - | Not available | - | |
| Gemma 3 270M | Google | 5 | 0.3B | 32k | - | - | - | ||
| Gemma 3 27B Instruct | Google | 5 | 27.4B | 128k | $0.0 | - |   +3 | ||
| Gemma 3 4B Instruct | Google | 5 | 4.3B | 128k | $0.0 | - | | ||
| Gemma 3n E4B Instruct | Google | 5 | 8.4B 4B active at inference time | 32k | - | - | - | ||
| Gemma 3n E2B Instruct | Google | 5 | 6.0B 2B active at inference time | 32k | $0.0 | - | | ||
| Gemma 3 1B Instruct | Google | 5 | 1B | 32k | $0.0 | - | | ||
| Gemma 3 12B Instruct | Google | 4 | 12.2B | 128k | $0.0 | - | | ||
| Gemini 3 Deep Think | Google | - | - | 128k | - | - | Not available | - |