Gemma 3 27B vs GPT-4o mini
Change modelsGemma 3 27BGoogle
GPT-4o miniOpenAI
IndexAll categories, out of 100.
25.3 ±4.5
26.2 ±4.3 best
GapIndex points below the top.
−0.9 · no clear gap
Top
CoverageIndex weight that has results.
100% best
95%
SpeedOutput tokens per second.
31/s
56/s best
EloLMArena rating and rank.
—
1286
ReleasedMonth of release.
2025-03
2024-07
Input / 1MUS dollars per 1M input tokens.
—
$0.15
Output / 1MUS dollars per 1M output tokens.
—
$0.60
1K chats2K tokens in, 500 out, each.
—
$0.60
1K documents20K tokens in, 1K out, each.
—
$3.60
1K agent tasks200K tokens in, 20K out, each.
—
$42.00
ContextMaximum tokens in one request.
32K
128K best
AgenticMulti-step tasks with tools.
21.9
34.0 best
CodingCode writing and repair.
26.2 best
19.5
ReasoningLogic problems and puzzles.
24.6
41.1 best
MultimodalTasks with images and text.
17.6
19.0 best
KnowledgeFacts and expert knowledge.
24.9
25.7 best
MultilingualTasks in many languages.
43.7
—
InstructionTasks with strict prompt rules.
18.7 best
18.0
MathMath problems.
28.5 best
22.0
Benchmarks
8 sharedOnly Gemma 3 27B: 11Only GPT-4o mini: 19
Gemma 3 27B
GPT-4o mini