Gemini 2.5 Flash-Lite vs Llama 3.1 405B
Change modelsGemini 2.5 Flash-LiteGoogle
Llama 3.1 405BMeta
IndexAll categories, out of 100.
27.1 ±5.2 best
27.0 ±8.9
GapIndex points below the top.
Top
−0.1 · no clear gap
CoverageIndex weight that has results.
95% best
65%
SpeedOutput tokens per second.
140/s best
29/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2025-07
2024-07
Input / 1MUS dollars per 1M input tokens.
$0.10
—
Output / 1MUS dollars per 1M output tokens.
$0.40
—
1K chats2K tokens in, 500 out, each.
$0.40
—
1K documents20K tokens in, 1K out, each.
$2.40
—
1K agent tasks200K tokens in, 20K out, each.
$28.00
—
ContextMaximum tokens in one request.
1.05M best
128K
AgenticMulti-step tasks with tools.
15.4
15.4
CodingCode writing and repair.
24.5
—
ReasoningLogic problems and puzzles.
33.1 best
30.8
MultimodalTasks with images and text.
33.2
—
KnowledgeFacts and expert knowledge.
27.1 best
26.3
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
18.5
33.5 best
MathMath problems.
26.0 best
18.9
Benchmarks
6 sharedOnly Gemini 2.5 Flash-Lite: 9Only Llama 3.1 405B: 4
Gemini 2.5 Flash-Lite
Llama 3.1 405B