Gemini 3.7 Flash vs Qwen4 Max

Change models
Qwen4 MaxAlibaba
IndexAll categories, out of 100.
68.0 ±2.2
72.0 ±8.0 best
GapIndex points below the top.
−4.0 · no clear gap
Top
CoverageIndex weight that has results.
100% best
65%
SpeedOutput tokens per second.
98/s best
40/s
EloLMArena rating and rank.
1489
—
ReleasedMonth of release.
2026-08
2026-11
Input / 1MUS dollars per 1M input tokens.
$0.75 best
$1.50
Output / 1MUS dollars per 1M output tokens.
$3.75 best
$4.50
Batch output / 1MBatch price per 1M output tokens.
$1.88
—
1K chats2K tokens in, 500 out, each.
$3.38 best
$5.25
1K documents20K tokens in, 1K out, each.
$18.75 best
$34.50
1K agent tasks200K tokens in, 20K out, each.
$225.00 best
$390.00
ContextMaximum tokens in one request.
1.05M best
1M
AgenticMulti-step tasks with tools.
64.7
75.2 best
CodingCode writing and repair.
66.2
67.0 best
ReasoningLogic problems and puzzles.
68.3
—
MultimodalTasks with images and text.
67.5
72.1 best
KnowledgeFacts and expert knowledge.
70.9 best
70.7
MultilingualTasks in many languages.
71.9
—
InstructionTasks with strict prompt rules.
87.7
—
MathMath problems.
66.5
—

Benchmarks

8 shared
Only Gemini 3.7 Flash: 86Only Qwen4 Max: 11
Gemini 3.7 Flash
Qwen4 Max
55.3% best12 / 167
43.7%42 / 167
70.4%50 / 125
86.7% best14 / 125
34.6%51 / 92
41.3% best31 / 92
22.8%50 / 84
40.4% best12 / 84
12.1%44 / 63
48.5% best14 / 63
DeepSWEAgentic
65.3%35 / 61
75.7% best5 / 61
−9.044 / 56
8.4 best15 / 56
60.0% best1 / 26
46.3%15 / 26