Grok 4 Fast (Reasoning) vs Mercury 2.5
Change models
Mercury 2.5Inception
IndexAll categories, out of 100.
45.3 ±4.3
46.2 ±5.4 best
GapIndex points below the top.
−0.9 · no clear gap
Top
CoverageIndex weight that has results.
95% best
85%
SpeedOutput tokens per second.
—
125/s
EloLMArena rating and rank.
1400
—
ReleasedMonth of release.
2025-09
2026-09
Input / 1MUS dollars per 1M input tokens.
—
$0.04
Output / 1MUS dollars per 1M output tokens.
—
$0.15
1K chats2K tokens in, 500 out, each.
—
$0.155
1K documents20K tokens in, 1K out, each.
—
$0.95
1K agent tasks200K tokens in, 20K out, each.
—
$11.00
ContextMaximum tokens in one request.
2M best
260K
AgenticMulti-step tasks with tools.
42.9
49.3 best
CodingCode writing and repair.
44.9 best
44.5
ReasoningLogic problems and puzzles.
47.8 best
45.4
MultimodalTasks with images and text.
42.7
—
KnowledgeFacts and expert knowledge.
46.6 best
41.4
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
36.2
61.0 best
MathMath problems.
55.4 best
48.2
Benchmarks
8 sharedOnly Grok 4 Fast (Reasoning): 27Only Mercury 2.5: 20
Grok 4 Fast (Reasoning)
Mercury 2.5