Gemini 3.6 Flash vs Qwen3.8-Flash-Next

Change models
IndexAll categories, out of 100.
62.7 ±2.6
63.0 ±3.3 best
GapIndex points below the top.
−0.3 · no clear gap
Top
CoverageIndex weight that has results.
100% best
95%
SpeedOutput tokens per second.
117/s best
74/s
EloLMArena rating and rank.
1480
—
ReleasedMonth of release.
2026-07
2026-08
Input / 1MUS dollars per 1M input tokens.
$0.75
—
Output / 1MUS dollars per 1M output tokens.
$3.75
—
Batch output / 1MBatch price per 1M output tokens.
$1.88
—
1K chats2K tokens in, 500 out, each.
$3.38
—
1K documents20K tokens in, 1K out, each.
$18.75
—
1K agent tasks200K tokens in, 20K out, each.
$225.00
—
ContextMaximum tokens in one request.
1.05M best
262K
AgenticMulti-step tasks with tools.
58.8
66.8 best
CodingCode writing and repair.
61.0
61.1 best
ReasoningLogic problems and puzzles.
61.1
61.2 best
MultimodalTasks with images and text.
67.0 best
63.4
KnowledgeFacts and expert knowledge.
66.9 best
55.1
MultilingualTasks in many languages.
69.8
—
InstructionTasks with strict prompt rules.
77.3 best
72.2
MathMath problems.
59.8 best
58.6

Benchmarks

17 shared
Only Gemini 3.6 Flash: 50Only Qwen3.8-Flash-Next: 32
Gemini 3.6 Flash
Qwen3.8-Flash-Next
40.8% best44 / 216
38.0%55 / 216
80.0% best43 / 211
79.7%45 / 211
10.6%62 / 207
11.1% best60 / 207
92.8% best14 / 193
92.3%19 / 193
50.0% best24 / 170
23.5%113 / 170
39.2%46 / 132
56.4% best13 / 132
53.4% best39 / 113
50.6%49 / 113
83.2% best12 / 109
78.6%33 / 109
63.0%70 / 80
74.2% best43 / 80
85.1%40 / 80
87.4% best28 / 80
43.4%56 / 66
61.6% best12 / 66
77.9% best33 / 66
72.6%53 / 66
75.4%9 / 66
77.1% best5 / 66
83.9% best16 / 66
74.6%49 / 66
86.4% best47 / 66
85.8%50 / 66
DeepSWEAgentic
49.0%55 / 64
58.7% best48 / 64
−18.246 / 50
−2.6 best39 / 50