Gemini 3.5 Flash-Lite vs o3

Change models
o3OpenAI
IndexAll categories, out of 100.
51.2 ±2.7
51.2 ±3.9
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
100% best
95%
SpeedOutput tokens per second.
115/s
115/s
EloLMArena rating and rank.
1435 best
1410
ReleasedMonth of release.
2026-07
2025-04
Input / 1MUS dollars per 1M input tokens.
$0.30 best
$2.00
Output / 1MUS dollars per 1M output tokens.
$2.50 best
$8.00
Batch output / 1MBatch price per 1M output tokens.
—
$4.00
1K chats2K tokens in, 500 out, each.
$1.85 best
$8.00
1K documents20K tokens in, 1K out, each.
$8.50 best
$48.00
1K agent tasks200K tokens in, 20K out, each.
$110.00 best
$560.00
ContextMaximum tokens in one request.
1.05M best
200K
AgenticMulti-step tasks with tools.
52.7 best
52.4
CodingCode writing and repair.
53.8 best
50.5
ReasoningLogic problems and puzzles.
47.2
52.0 best
MultimodalTasks with images and text.
55.8 best
52.5
KnowledgeFacts and expert knowledge.
49.9
53.0 best
MultilingualTasks in many languages.
54.0
—
InstructionTasks with strict prompt rules.
61.7 best
54.9
MathMath problems.
46.0
48.6 best

Benchmarks

24 shared
Only Gemini 3.5 Flash-Lite: 40Only o3: 22
Gemini 3.5 Flash-Lite
o3
83.3% best80 / 220
81.8%85 / 220
18.8%114 / 216
20.1% best108 / 216
76.0% best86 / 211
74.7%92 / 211
0.0%145 / 207
1.1% best113 / 207
71.1%101 / 203
83.9% best81 / 203
83.8% best83 / 193
82.7%87 / 193
84.1% best39 / 149
83.8%47 / 149
TaxEval v2Finance
72.6%60 / 143
74.6% best34 / 143
79.0%74 / 142
83.9% best44 / 142
10.3% best72 / 137
6.5%77 / 137
83.8%54 / 135
84.1% best52 / 135
MMLU ProKnowledge
85.8% best53 / 135
85.6%55 / 135
53.5%78 / 132
60.8% best72 / 132
CorpFin v2Finance
60.7% best65 / 131
59.7%74 / 131
7.9% best65 / 127
2.9%84 / 127
66.4% best65 / 116
64.3%67 / 116
MedScribeHealthcare
70.9%95 / 111
76.7% best76 / 111
79.0% best30 / 109
70.1%71 / 109
MedCodeHealthcare
43.5%45 / 108
47.3% best34 / 108
68.7% best11 / 97
65.7%40 / 97