Claude Mythos 5 vs Step 5 Preview

Change models
IndexAll categories, out of 100.
70.8 ±8.6 best
68.4 ±3.7
GapIndex points below the top.
Top
−2.4 · no clear gap
CoverageIndex weight that has results.
65%
90% best
SpeedOutput tokens per second.
—
105/s
EloLMArena rating and rank.
—
1443
ReleasedMonth of release.
2026-06
2026-09
Input / 1MUS dollars per 1M input tokens.
$10.00
$1.00 best
Output / 1MUS dollars per 1M output tokens.
$50.00
$2.70 best
1K chats2K tokens in, 500 out, each.
$45.00
$3.35 best
1K documents20K tokens in, 1K out, each.
$250.00
$22.70 best
1K agent tasks200K tokens in, 20K out, each.
$3,000.00
$254.00 best
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
70.0 best
68.8
CodingCode writing and repair.
74.4 best
71.4
ReasoningLogic problems and puzzles.
—
67.4
MultimodalTasks with images and text.
70.8 best
62.2
KnowledgeFacts and expert knowledge.
74.9 best
63.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
—
61.7

Benchmarks

4 shared
Only Claude Mythos 5: 8Only Step 5 Preview: 58
Claude Mythos 5
Step 5 Preview
88.0% best11 / 86
85.0%20 / 86
64.5% best5 / 77
46.5%26 / 77
BrowseCompAgentic
88.0%13 / 63
88.7% best12 / 63
CyberGymAgentic
83.8%11 / 29
84.7% best8 / 29