Claude Opus 4.5 Thinking vs Qwen3.7 Plus

Change models
IndexAll categories, out of 100.
55.7 ±4.2
56.3 ±2.3 best
GapIndex points below the top.
−0.6 · no clear gap
Top
CoverageIndex weight that has results.
95%
100% best
SpeedOutput tokens per second.
—
50/s
EloLMArena rating and rank.
—
1454
ReleasedMonth of release.
2025-11
2026-06
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.
200K
1M best
AgenticMulti-step tasks with tools.
59.2 best
56.0
CodingCode writing and repair.
53.8
57.4 best
ReasoningLogic problems and puzzles.
53.5
56.7 best
MultimodalTasks with images and text.
56.6
61.5 best
KnowledgeFacts and expert knowledge.
58.6 best
54.2
MultilingualTasks in many languages.
—
53.4
InstructionTasks with strict prompt rules.
43.0
57.1 best
MathMath problems.
56.4 best
51.1

Benchmarks

10 shared
Only Claude Opus 4.5 Thinking: 27Only Qwen3.7 Plus: 67
Claude Opus 4.5 Thinking
Qwen3.7 Plus
30.1%77 / 216
35.6% best61 / 216
77.3% best76 / 211
73.0%98 / 211
4.6%85 / 207
9.1% best69 / 207
86.6%60 / 193
90.0% best36 / 193
89.5%41 / 143
93.0% best31 / 143
58.0%62 / 140
78.0% best7 / 140
20.6%96 / 130
46.4% best81 / 130
74.0%58 / 109
80.5% best19 / 109
67.7% best22 / 97
66.2%36 / 97
47.0%11 / 22
47.0%11 / 22