Gemini 2.5 Flash-Lite vs Mistral Medium 3
Change modelsGemini 2.5 Flash-LiteGoogle
Mistral Medium 3Mistral
IndexAll categories, out of 100.
27.1 ±5.2
27.1 ±5.2
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
95%
95%
SpeedOutput tokens per second.
140/s best
94/s
EloLMArena rating and rank.
—
1370
ReleasedMonth of release.
2025-07
2025-05
Input / 1MUS dollars per 1M input tokens.
$0.10 best
$0.40
Output / 1MUS dollars per 1M output tokens.
$0.40 best
$2.00
1K chats2K tokens in, 500 out, each.
$0.40 best
$1.80
1K documents20K tokens in, 1K out, each.
$2.40 best
$10.00
1K agent tasks200K tokens in, 20K out, each.
$28.00 best
$120.00
ContextMaximum tokens in one request.
1.05M best
131K
AgenticMulti-step tasks with tools.
15.4
18.9 best
CodingCode writing and repair.
24.5 best
9.3
ReasoningLogic problems and puzzles.
33.1 best
32.8
MultimodalTasks with images and text.
33.2 best
24.1
KnowledgeFacts and expert knowledge.
27.1
31.1 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
18.5
25.7 best
MathMath problems.
26.0
32.2 best
Benchmarks
8 sharedOnly Gemini 2.5 Flash-Lite: 7Only Mistral Medium 3: 6
Gemini 2.5 Flash-Lite
Mistral Medium 3