Kimi K2.5 vs Ripple-65B Preview

Change models
Kimi K2.5Moonshot AI
Ripple-65B PreviewRicursive Intelligence
IndexAll categories, out of 100.
52.2 ±2.2
52.3 ±5.4 best
GapIndex points below the top.
−0.1 · no clear gap
Top
CoverageIndex weight that has results.
100% best
85%
SpeedOutput tokens per second.
36/s
63/s best
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-01
2026-11
Input / 1MUS dollars per 1M input tokens.
$0.532
$0.20 best
Output / 1MUS dollars per 1M output tokens.
$3.32
$0.60 best
1K chats2K tokens in, 500 out, each.
$2.73
$0.70 best
1K documents20K tokens in, 1K out, each.
$13.97
$4.60 best
1K agent tasks200K tokens in, 20K out, each.
$172.90
$52.00 best
ContextMaximum tokens in one request.
262K
1.05M best
AgenticMulti-step tasks with tools.
49.4
49.5 best
CodingCode writing and repair.
53.9
55.3 best
ReasoningLogic problems and puzzles.
51.6
58.8 best
MultimodalTasks with images and text.
52.4
—
KnowledgeFacts and expert knowledge.
53.7 best
48.1
MultilingualTasks in many languages.
52.7
—
InstructionTasks with strict prompt rules.
53.5
63.0 best
MathMath problems.
53.8 best
52.7

Benchmarks

11 shared
Only Kimi K2.5: 78Only Ripple-65B Preview: 6
Kimi K2.5
Ripple-65B Preview
78.0% best70 / 217
75.0%95 / 217
76.8% best38 / 114
76.5%41 / 114
87.6% best47 / 84
85.2%58 / 84
50.7%70 / 83
61.4% best29 / 83
87.1% best7 / 75
84.2%26 / 75
96.1%6 / 53
98.3% best2 / 53
MCP AtlasAgentic
29.5%52 / 52
71.7% best30 / 52
48.7% best9 / 35
39.4%22 / 35
95.8% best8 / 34
95.0%17 / 34
65.7% best13 / 32
31.3%24 / 32
87.1%13 / 27
90.5% best9 / 27