Grok 4.5 vs Grok Build 0.1
Change modelsGrok 4.5xAI
IndexAll categories, out of 100.
63.7 ±2.9 best
52.7 ±7.2
GapIndex points below the top.
Top
−11.0
CoverageIndex weight that has results.
95% best
85%
SpeedOutput tokens per second.
53/s
147/s best
EloLMArena rating and rank.
1448
—
ReleasedMonth of release.
2026-07
2026-05
Input / 1MUS dollars per 1M input tokens.
$2.00
$1.00 best
Output / 1MUS dollars per 1M output tokens.
$6.00
$2.00 best
1K chats2K tokens in, 500 out, each.
$7.00
$3.00 best
1K documents20K tokens in, 1K out, each.
$46.00
$22.00 best
1K agent tasks200K tokens in, 20K out, each.
$520.00
$240.00 best
ContextMaximum tokens in one request.
500K best
256K
AgenticMulti-step tasks with tools.
61.6 best
55.9
CodingCode writing and repair.
65.8 best
46.9
ReasoningLogic problems and puzzles.
63.3 best
56.9
MultimodalTasks with images and text.
47.7
—
KnowledgeFacts and expert knowledge.
65.8 best
56.5
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
71.3 best
58.6
MathMath problems.
61.8 best
49.1
Benchmarks
8 sharedOnly Grok 4.5: 66Only Grok Build 0.1: 1
Grok 4.5
Grok Build 0.1