Grok 4 Fast (Reasoning) vs Nemotron 3.5 Bolt 74B-A9B

Change models
IndexAll categories, out of 100.
45.2 ±4.3
45.8 ±7.9 best
GapIndex points below the top.
−0.6 · no clear gap
Top
CoverageIndex weight that has results.
95% best
70%
SpeedOutput tokens per second.
—
—
EloLMArena rating and rank.
1400
—
ReleasedMonth of release.
2025-09
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.
2M best
256K
AgenticMulti-step tasks with tools.
43.1 best
41.7
CodingCode writing and repair.
44.5
47.1 best
ReasoningLogic problems and puzzles.
47.4
49.5 best
MultimodalTasks with images and text.
42.5
—
KnowledgeFacts and expert knowledge.
46.7
52.5 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
36.3
—
MathMath problems.
54.7
—

Benchmarks

3 shared
Only Grok 4 Fast (Reasoning): 32Only Nemotron 3.5 Bolt 74B-A9B: 11
Grok 4 Fast (Reasoning)
Nemotron 3.5 Bolt 74B-A9B
19.1%112 / 216
24.7% best96 / 216
73.7% best95 / 211
69.7%108 / 211
2.9%95 / 207
4.3% best89 / 207