Qwen3.7 Plus vs Qwen3.8 Max Preview

Change models
IndexAll categories, out of 100.
57.7 ±2.3
64.2 ±7.1 best
GapIndex points below the top.
−6.5 · no clear gap
Top
CoverageIndex weight that has results.
100% best
80%
SpeedOutput tokens per second.
51/s
—
EloLMArena rating and rank.
1454
1485 best
ReleasedMonth of release.
2026-06
2026-07
Input / 1MUS dollars per 1M input tokens.
$0.32
—
Output / 1MUS dollars per 1M output tokens.
$1.28
—
Batch output / 1MBatch price per 1M output tokens.
$0.92
—
1K chats2K tokens in, 500 out, each.
$1.28
—
1K documents20K tokens in, 1K out, each.
$7.68
—
1K agent tasks200K tokens in, 20K out, each.
$89.60
—
ContextMaximum tokens in one request.
1M
—
AgenticMulti-step tasks with tools.
57.3
73.5 best
CodingCode writing and repair.
58.3
63.4 best
ReasoningLogic problems and puzzles.
57.7
66.8 best
MultimodalTasks with images and text.
62.6
62.9 best
KnowledgeFacts and expert knowledge.
54.8
59.3 best
MultilingualTasks in many languages.
54.0
—
InstructionTasks with strict prompt rules.
58.1
—
MathMath problems.
55.4
—

Benchmarks

8 shared
Only Qwen3.7 Plus: 69Only Qwen3.8 Max Preview: 2
Qwen3.7 Plus
Qwen3.8 Max Preview
35.6%61 / 222
43.1% best32 / 222
73.0%103 / 217
80.3% best40 / 217
9.1%70 / 214
17.7% best37 / 214
90.0%36 / 199
92.8% best14 / 199
13.3%90 / 133
58.3% best11 / 133
46.1%69 / 114
52.1% best42 / 114
80.5%18 / 113
82.8% best13 / 113
22.4%19 / 30
42.4% best2 / 30