Gemini 3.5 Flash-Lite vs Qwen3.5-122B-A10B

Change models
IndexAll categories, out of 100.
51.8 ±2.8 best
51.6 ±4.3
GapIndex points below the top.
Top
−0.2 · no clear gap
CoverageIndex weight that has results.
100% best
90%
SpeedOutput tokens per second.
119/s best
107/s
EloLMArena rating and rank.
1435 best
1417
ReleasedMonth of release.
2026-07
2026-03
Input / 1MUS dollars per 1M input tokens.
$0.30
$0.26 best
Output / 1MUS dollars per 1M output tokens.
$2.50
$2.08 best
1K chats2K tokens in, 500 out, each.
$1.85
$1.56 best
1K documents20K tokens in, 1K out, each.
$8.50
$7.28 best
1K agent tasks200K tokens in, 20K out, each.
$110.00
$93.60 best
ContextMaximum tokens in one request.
1.05M best
262K
AgenticMulti-step tasks with tools.
54.5 best
51.2
CodingCode writing and repair.
54.2 best
50.2
ReasoningLogic problems and puzzles.
47.5
50.1 best
MultimodalTasks with images and text.
56.4 best
53.7
KnowledgeFacts and expert knowledge.
49.8
52.7 best
MultilingualTasks in many languages.
54.1 best
51.4
InstructionTasks with strict prompt rules.
62.4 best
55.3
MathMath problems.
46.3
—

Benchmarks

9 shared
Only Gemini 3.5 Flash-Lite: 54Only Qwen3.5-122B-A10B: 19
Gemini 3.5 Flash-Lite
Qwen3.5-122B-A10B
18.8%118 / 222
25.2% best99 / 222
76.0%88 / 217
76.3% best86 / 217
0.0%150 / 214
0.6% best132 / 214
83.8%87 / 199
85.7% best72 / 199
24.2% best76 / 133
15.7%86 / 133
41.3% best82 / 114
39.7%89 / 114
79.0% best29 / 113
75.0%53 / 113
19.0% best46 / 80
17.0%51 / 80
74.0% best18 / 37
58.0%33 / 37