Gemini 3.5 Flash-Lite vs GLM-5-Turbo
Change modelsGemini 3.5 Flash-LiteGoogle
GLM-5-TurboZ.AI
IndexAll categories, out of 100.
51.9 ±2.8 best
51.8 ±10.2
GapIndex points below the top.
Top
−0.1 · no clear gap
CoverageIndex weight that has results.
100% best
55%
SpeedOutput tokens per second.
130/s best
25/s
EloLMArena rating and rank.
1435
—
ReleasedMonth of release.
2026-07
2026-03
Input / 1MUS dollars per 1M input tokens.
$0.30 best
$1.20
Output / 1MUS dollars per 1M output tokens.
$2.50 best
$4.00
1K chats2K tokens in, 500 out, each.
$1.85 best
$4.40
1K documents20K tokens in, 1K out, each.
$8.50 best
$28.00
1K agent tasks200K tokens in, 20K out, each.
$110.00 best
$320.00
ContextMaximum tokens in one request.
1.05M best
203K
AgenticMulti-step tasks with tools.
54.6
56.9 best
CodingCode writing and repair.
54.3
—
ReasoningLogic problems and puzzles.
47.6 best
46.9
MultimodalTasks with images and text.
58.7
—
KnowledgeFacts and expert knowledge.
49.9
51.1 best
MultilingualTasks in many languages.
54.2
—
InstructionTasks with strict prompt rules.
62.5 best
57.4
MathMath problems.
46.4
—
Benchmarks
5 sharedOnly Gemini 3.5 Flash-Lite: 57Only GLM-5-Turbo: 3
Gemini 3.5 Flash-Lite
GLM-5-Turbo