Gemini 3 Flash vs Qwen3.5 397B (Reasoning)

Change models
IndexAll categories, out of 100.
55.2 ±3.9 best
55.1 ±6.9
GapIndex points below the top.
Top
−0.1 · no clear gap
CoverageIndex weight that has results.
95% best
85%
SpeedOutput tokens per second.
198/s
—
EloLMArena rating and rank.
1466
—
ReleasedMonth of release.
2025-12
2026-02
Input / 1MUS dollars per 1M input tokens.
$0.50 best
$0.60
Output / 1MUS dollars per 1M output tokens.
$3.00 best
$3.60
1K chats2K tokens in, 500 out, each.
$2.50 best
$3.00
1K documents20K tokens in, 1K out, each.
$13.00 best
$15.60
1K agent tasks200K tokens in, 20K out, each.
$160.00 best
$192.00
ContextMaximum tokens in one request.
1M best
128K
AgenticMulti-step tasks with tools.
48.3
59.1 best
CodingCode writing and repair.
56.7 best
53.9
ReasoningLogic problems and puzzles.
50.6 best
50.0
MultimodalTasks with images and text.
67.5 best
55.5
KnowledgeFacts and expert knowledge.
60.5 best
56.0
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
40.5
62.5 best
MathMath problems.
57.0
—

Benchmarks

7 shared
Only Gemini 3 Flash: 25Only Qwen3.5 397B (Reasoning): 2
Gemini 3 Flash
Qwen3.5 397B (Reasoning)
15.0%127 / 222
29.0% best85 / 222
55.3%147 / 217
77.3% best77 / 217
1.4%113 / 214
1.7% best109 / 214
81.2%95 / 199
89.3% best45 / 199
43.3%103 / 149
95.6% best18 / 149
55.1%72 / 146
78.8% best6 / 146
78.6% best32 / 113
77.3%40 / 113