Mercury 3 vs Ripple-65B Preview

Change models
Mercury 3Inception
Ripple-65B PreviewRicursive Intelligence
IndexAll categories, out of 100.
52.3 ±8.2
52.3 ±5.4
GapIndex points below the top.
Top
Top
CoverageIndex weight that has results.
75%
85% best
SpeedOutput tokens per second.
295/s best
63/s
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-10
2026-11
Input / 1MUS dollars per 1M input tokens.
$0.10 best
$0.20
Output / 1MUS dollars per 1M output tokens.
$0.35 best
$0.60
1K chats2K tokens in, 500 out, each.
$0.375 best
$0.70
1K documents20K tokens in, 1K out, each.
$2.35 best
$4.60
1K agent tasks200K tokens in, 20K out, each.
$27.00 best
$52.00
ContextMaximum tokens in one request.
1M
1.05M best
AgenticMulti-step tasks with tools.
44.4
49.5 best
CodingCode writing and repair.
64.2 best
55.3
ReasoningLogic problems and puzzles.
57.0
58.8 best
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
59.0 best
48.1
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
60.8
63.0 best
MathMath problems.
—
52.7

Benchmarks

4 shared
Only Mercury 3: 9Only Ripple-65B Preview: 13
Mercury 3
Ripple-65B Preview
89.2% best37 / 84
85.2%58 / 84
DeepSWEAgentic
46.3% best52 / 59
44.3%53 / 59
76.8%24 / 57
79.2% best17 / 57
30.2%25 / 32
31.3% best24 / 32