Grok 4.3 vs Hy3 Preview

Change models
Hy3 PreviewTencent
IndexAll categories, out of 100.
52.6 ±3.6
52.7 ±7.4 best
GapIndex points below the top.
−0.1 · no clear gap
Top
CoverageIndex weight that has results.
95% best
75%
SpeedOutput tokens per second.
73/s
81/s best
EloLMArena rating and rank.
1397
1401 best
ReleasedMonth of release.
2026-04
2026-04
Input / 1MUS dollars per 1M input tokens.
$1.25
$0.18 best
Output / 1MUS dollars per 1M output tokens.
$2.50
$0.60 best
Batch output / 1MBatch price per 1M output tokens.
$2.00
—
1K chats2K tokens in, 500 out, each.
$3.75
$0.66 best
1K documents20K tokens in, 1K out, each.
$27.50
$4.20 best
1K agent tasks200K tokens in, 20K out, each.
$300.00
$48.00 best
ContextMaximum tokens in one request.
1M best
262K
AgenticMulti-step tasks with tools.
49.5
55.3 best
CodingCode writing and repair.
52.7
54.6 best
ReasoningLogic problems and puzzles.
48.6
49.1 best
MultimodalTasks with images and text.
56.1
—
KnowledgeFacts and expert knowledge.
56.7 best
53.8
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
58.4 best
47.5
MathMath problems.
56.6
—

Benchmarks

12 shared
Only Grok 4.3: 39Only Hy3 Preview: 3
Grok 4.3
Hy3 Preview
37.2% best58 / 216
33.5%68 / 216
64.3%131 / 211
66.7% best127 / 211
8.0% best74 / 207
4.9%82 / 207
90.1% best35 / 193
89.7%39 / 193
34.6% best71 / 170
31.5%77 / 170
90.1% best31 / 144
87.2%44 / 144
29.2%64 / 132
35.8% best49 / 132
21.0%111 / 120
39.3% best70 / 120
48.3%58 / 113
48.6% best55 / 113
35.0% best42 / 77
25.5%60 / 77
81.3% best8 / 57
63.1%43 / 57
47.3% best12 / 35
41.2%18 / 35