Gemini 2.5 Flash vs Gemma 3 27B

Change models
IndexAll categories, out of 100.
35.0 ±5.0 best
25.3 ±4.5
GapIndex points below the top.
Top
−9.7
CoverageIndex weight that has results.
95%
100% best
SpeedOutput tokens per second.
95/s best
31/s
EloLMArena rating and rank.
1417
—
ReleasedMonth of release.
2025-06
2025-03
Input / 1MUS dollars per 1M input tokens.
$0.30
—
Output / 1MUS dollars per 1M output tokens.
$2.50
—
Batch output / 1MBatch price per 1M output tokens.
$1.25
—
1K chats2K tokens in, 500 out, each.
$1.85
—
1K documents20K tokens in, 1K out, each.
$8.50
—
1K agent tasks200K tokens in, 20K out, each.
$110.00
—
ContextMaximum tokens in one request.
1.05M best
32K
AgenticMulti-step tasks with tools.
12.7
21.9 best
CodingCode writing and repair.
31.9 best
26.2
ReasoningLogic problems and puzzles.
40.5 best
24.6
MultimodalTasks with images and text.
40.4 best
17.6
KnowledgeFacts and expert knowledge.
37.5 best
24.9
MultilingualTasks in many languages.
—
43.7
InstructionTasks with strict prompt rules.
25.5 best
18.7
MathMath problems.
44.1 best
28.5

Benchmarks

9 shared
Only Gemini 2.5 Flash: 7Only Gemma 3 27B: 10
Gemini 2.5 Flash
Gemma 3 27B
4.7% best183 / 222
4.4%189 / 222
49.9% best156 / 217
7.3%200 / 217
1.4% best113 / 214
0.0%150 / 214
71.9% best97 / 200
22.5%143 / 200
68.3% best135 / 199
42.8%184 / 199
26.1% best98 / 164
13.0%158 / 164
14.9% best140 / 149
10.5%145 / 149
39.0% best108 / 146
31.8%130 / 146
65.5% best81 / 113
48.0%105 / 113