MiniMax M3.1 Flash vs Qwen4 Max

Change models
Qwen4 MaxAlibaba
IndexAll categories, out of 100.
69.0 ±5.4
72.0 ±8.0 best
GapIndex points below the top.
−3.0 · no clear gap
Top
CoverageIndex weight that has results.
80% best
65%
SpeedOutput tokens per second.
95/s best
40/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-10
2026-11
Input / 1MUS dollars per 1M input tokens.
$0.075 best
$1.50
Output / 1MUS dollars per 1M output tokens.
$0.30 best
$4.50
1K chats2K tokens in, 500 out, each.
$0.30 best
$5.25
1K documents20K tokens in, 1K out, each.
$1.80 best
$34.50
1K agent tasks200K tokens in, 20K out, each.
$21.00 best
$390.00
ContextMaximum tokens in one request.
1.05M best
1M
AgenticMulti-step tasks with tools.
71.5
75.2 best
CodingCode writing and repair.
69.0 best
67.0
ReasoningLogic problems and puzzles.
67.5
—
MultimodalTasks with images and text.
58.0
72.1 best
KnowledgeFacts and expert knowledge.
68.6
70.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
—
—

Benchmarks

9 shared
Only MiniMax M3.1 Flash: 27Only Qwen4 Max: 10
MiniMax M3.1 Flash
Qwen4 Max
45.1% best38 / 167
43.7%42 / 167
73.9%47 / 125
86.7% best14 / 125
34.1%52 / 92
41.3% best31 / 92
32.1%25 / 84
40.4% best12 / 84
25.3%30 / 63
48.5% best14 / 63
DeepSWEAgentic
73.7%14 / 61
75.7% best5 / 61
−3.137 / 56
8.4 best15 / 56
43.4%21 / 54
51.7% best8 / 54
7.5%26 / 37
21.3% best7 / 37