Qwen3.7 Max vs Beam 1.0 501B-A23B
Change modelsQwen3.7 MaxAlibaba
Beam 1.0 501B-A23BReflection AI
IndexAll categories, out of 100.
60.4 ±3.2 best
60.1 ±4.6
GapIndex points below the top.
Top
−0.3 · no clear gap
CoverageIndex weight that has results.
90% best
85%
SpeedOutput tokens per second.
68/s
345/s best
EloLMArena rating and rank.
1475
—
ReleasedMonth of release.
2026-05
2026-10
Input / 1MUS dollars per 1M input tokens.
$1.48
—
Output / 1MUS dollars per 1M output tokens.
$4.43
—
1K chats2K tokens in, 500 out, each.
$5.16
—
1K documents20K tokens in, 1K out, each.
$33.93
—
1K agent tasks200K tokens in, 20K out, each.
$383.50
—
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
60.3 best
59.2
CodingCode writing and repair.
59.7
61.9 best
ReasoningLogic problems and puzzles.
60.3
63.2 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
58.4 best
56.4
MultilingualTasks in many languages.
57.0
—
InstructionTasks with strict prompt rules.
64.2 best
63.3
MathMath problems.
62.0 best
55.5
Benchmarks
13 sharedOnly Qwen3.7 Max: 69Only Beam 1.0 501B-A23B: 18
Qwen3.7 Max
Beam 1.0 501B-A23B