Gemini 2.5 Pro vs Gemma 3 27B

Change models
IndexAll categories, out of 100.
46.6 ±4.1 best
25.3 ±4.5
GapIndex points below the top.
Top
−21.3
CoverageIndex weight that has results.
95%
100% best
SpeedOutput tokens per second.
91/s best
31/s
EloLMArena rating and rank.
1458
—
ReleasedMonth of release.
2025-03
2025-03
Input / 1MUS dollars per 1M input tokens.
$1.25
—
Output / 1MUS dollars per 1M output tokens.
$10.00
—
Batch output / 1MBatch price per 1M output tokens.
$5.00
—
1K chats2K tokens in, 500 out, each.
$7.50
—
1K documents20K tokens in, 1K out, each.
$35.00
—
1K agent tasks200K tokens in, 20K out, each.
$450.00
—
ContextMaximum tokens in one request.
1.05M best
32K
AgenticMulti-step tasks with tools.
40.4 best
21.9
CodingCode writing and repair.
48.8 best
26.2
ReasoningLogic problems and puzzles.
48.3 best
24.6
MultimodalTasks with images and text.
52.6 best
17.6
KnowledgeFacts and expert knowledge.
53.0 best
24.9
MultilingualTasks in many languages.
—
43.7
InstructionTasks with strict prompt rules.
34.5 best
18.7
MathMath problems.
46.0 best
28.5

Benchmarks

10 shared
Only Gemini 2.5 Pro: 23Only Gemma 3 27B: 9
Gemini 2.5 Pro
Gemma 3 27B
22.5% best105 / 222
4.4%189 / 222
69.0% best120 / 217
7.3%200 / 217
2.6% best102 / 214
0.0%150 / 214
84.4% best82 / 199
42.8%184 / 199
39.1% best57 / 164
13.0%158 / 164
54.1% best92 / 149
10.5%145 / 149
48.7% best81 / 146
31.8%130 / 146
0.0%101 / 133
0.0%101 / 133
46.3% best68 / 114
23.3%111 / 114
74.9% best56 / 113
48.0%105 / 113