Claude Opus 4.6 (Adaptive) vs Beam 1.0 501B-A23B
Change modelsClaude Opus 4.6 (Adaptive)Anthropic
Beam 1.0 501B-A23BReflection AI
IndexAll categories, out of 100.
60.0 ±4.7
60.2 ±4.6 best
GapIndex points below the top.
−0.2 · no clear gap
Top
CoverageIndex weight that has results.
95% best
85%
SpeedOutput tokens per second.
—
345/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-02
2026-10
Input / 1MUS dollars per 1M input tokens.
—
—
Output / 1MUS dollars per 1M output tokens.
—
—
1K chats2K tokens in, 500 out, each.
—
—
1K documents20K tokens in, 1K out, each.
—
—
1K agent tasks200K tokens in, 20K out, each.
—
—
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
63.5 best
59.3
CodingCode writing and repair.
60.0
62.0 best
ReasoningLogic problems and puzzles.
61.0
63.2 best
MultimodalTasks with images and text.
58.8
—
KnowledgeFacts and expert knowledge.
62.6 best
56.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
38.6
63.4 best
MathMath problems.
57.3 best
55.6
Benchmarks
4 sharedOnly Claude Opus 4.6 (Adaptive): 23Only Beam 1.0 501B-A23B: 26
Claude Opus 4.6 (Adaptive)
Beam 1.0 501B-A23B