Gemini 2.5 Flash-Lite vs Gemini 3 Pro

Change models
IndexAll categories, out of 100.
27.1 ±5.2
57.9 ±2.7 best
GapIndex points below the top.
−30.8
Top
CoverageIndex weight that has results.
95%
100% best
SpeedOutput tokens per second.
140/s best
109/s
EloLMArena rating and rank.
—
1480
ReleasedMonth of release.
2025-07
2025-11
Input / 1MUS dollars per 1M input tokens.
$0.10 best
$2.00
Output / 1MUS dollars per 1M output tokens.
$0.40 best
$12.00
1K chats2K tokens in, 500 out, each.
$0.40 best
$10.00
1K documents20K tokens in, 1K out, each.
$2.40 best
$52.00
1K agent tasks200K tokens in, 20K out, each.
$28.00 best
$640.00
ContextMaximum tokens in one request.
1.05M
2M best
AgenticMulti-step tasks with tools.
15.4
56.2 best
CodingCode writing and repair.
24.5
56.4 best
ReasoningLogic problems and puzzles.
33.1
57.2 best
MultimodalTasks with images and text.
33.2
54.8 best
KnowledgeFacts and expert knowledge.
27.1
66.1 best
MultilingualTasks in many languages.
—
60.1
InstructionTasks with strict prompt rules.
18.5
54.8 best
MathMath problems.
26.0
58.2 best

Benchmarks

11 shared
Only Gemini 2.5 Flash-Lite: 4Only Gemini 3 Pro: 64
Gemini 2.5 Flash-Lite
Gemini 3 Pro
3.7%208 / 222
39.7% best48 / 222
32.0%177 / 217
76.0% best88 / 217
0.0%150 / 214
9.1% best70 / 214
47.4%179 / 199
90.8% best30 / 199
15.4%151 / 164
55.8% best11 / 164
19.0%134 / 149
87.1% best48 / 149
31.5%131 / 146
70.4% best42 / 146
54.0%98 / 113
80.2% best22 / 113
MedScribeHealthcare
72.8% best86 / 109
72.0%91 / 109
MedCodeHealthcare
27.1%101 / 106
52.2% best14 / 106
72.9%16 / 28
87.2% best1 / 28