GPT-6 Luna vs Hy4 flash

Change models
Hy4 flashTencent
IndexAll categories, out of 100.
64.7 ±2.1 best
64.5 ±8.4
GapIndex points below the top.
Top
−0.2 · no clear gap
CoverageIndex weight that has results.
100% best
65%
SpeedOutput tokens per second.
76/s best
69/s
EloLMArena rating and rank.
1390
—
ReleasedMonth of release.
2026-09
2026-11
Input / 1MUS dollars per 1M input tokens.
$0.10
$0.035 best
Output / 1MUS dollars per 1M output tokens.
$0.50
$0.14 best
Batch output / 1MBatch price per 1M output tokens.
$0.25
—
1K chats2K tokens in, 500 out, each.
$0.45
$0.14 best
1K documents20K tokens in, 1K out, each.
$2.50
$0.841 best
1K agent tasks200K tokens in, 20K out, each.
$30.00
$9.81 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
65.9
67.2 best
CodingCode writing and repair.
65.5 best
59.6
ReasoningLogic problems and puzzles.
63.4
—
MultimodalTasks with images and text.
64.2 best
53.3
KnowledgeFacts and expert knowledge.
63.7
78.0 best
MultilingualTasks in many languages.
53.3
—
InstructionTasks with strict prompt rules.
40.2
—
MathMath problems.
67.4
—

Benchmarks

7 shared
Only GPT-6 Luna: 96Only Hy4 flash: 8
GPT-6 Luna
Hy4 flash
81.6% best31 / 130
74.8%49 / 130
30.3%61 / 98
38.5% best44 / 98
19.9%61 / 89
23.3% best52 / 89
13.6%46 / 68
15.2% best44 / 68
DeepSWEAgentic
66.6% best34 / 64
64.6%37 / 64
15.2% best38 / 52
11.8%44 / 52
4.2%37 / 42
5.4% best32 / 42