Claude Sonnet 4.6 vs Qwen3.7 Plus

Change models
IndexAll categories, out of 100.
56.2 ±2.5
56.4 ±2.3 best
GapIndex points below the top.
−0.2 · no clear gap
Top
CoverageIndex weight that has results.
100%
100%
SpeedOutput tokens per second.
38/s
50/s best
EloLMArena rating and rank.
1458 best
1454
ReleasedMonth of release.
2026-02
2026-06
Input / 1MUS dollars per 1M input tokens.
$3.00
$0.32 best
Output / 1MUS dollars per 1M output tokens.
$15.00
$1.28 best
Batch output / 1MBatch price per 1M output tokens.
$7.50
$0.92 best
1K chats2K tokens in, 500 out, each.
$13.50
$1.28 best
1K documents20K tokens in, 1K out, each.
$75.00
$7.68 best
1K agent tasks200K tokens in, 20K out, each.
$900.00
$89.60 best
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
58.6 best
56.3
CodingCode writing and repair.
58.2 best
57.5
ReasoningLogic problems and puzzles.
55.6
56.8 best
MultimodalTasks with images and text.
53.3
61.6 best
KnowledgeFacts and expert knowledge.
56.7 best
54.2
MultilingualTasks in many languages.
56.5 best
53.3
InstructionTasks with strict prompt rules.
28.0
57.2 best
MathMath problems.
53.4 best
51.2

Benchmarks

29 shared
Only Claude Sonnet 4.6: 52Only Qwen3.7 Plus: 47
Claude Sonnet 4.6
Qwen3.7 Plus
78.8%96 / 220
81.8% best85 / 220
13.3%126 / 216
35.6% best61 / 216
68.3%117 / 211
73.0% best98 / 211
0.9%119 / 207
9.1% best69 / 207
71.1%101 / 203
80.0% best89 / 203
79.9%95 / 193
90.0% best36 / 193
89.9%33 / 144
90.3% best30 / 144
79.5%67 / 143
93.0% best31 / 143
41.2%95 / 140
78.0% best7 / 140
51.5% best72 / 130
46.4%81 / 130
79.6% best23 / 114
77.7%32 / 114
70.6%70 / 109
80.5% best19 / 109
38.5% best44 / 98
16.3%77 / 98
67.7% best22 / 97
66.2%36 / 97
25.8% best46 / 89
10.5%74 / 89
16.0%59 / 83
17.0% best54 / 83
51.0% best41 / 79
38.2%64 / 79
39.9% best30 / 77
12.9%61 / 77
49.0% best24 / 77
34.7%44 / 77
EMBFinance
60.2% best34 / 75
49.3%56 / 75