GPT-6.2 Sol vs Hy4

Change models
Hy4Tencent
IndexAll categories, out of 100.
76.0 ±4.6 best
71.3 ±7.2
GapIndex points below the top.
Top
−4.7 · no clear gap
CoverageIndex weight that has results.
85% best
65%
SpeedOutput tokens per second.
56/s
91/s best
EloLMArena rating and rank.
1414
—
ReleasedMonth of release.
2026-11
2026-11
Input / 1MUS dollars per 1M input tokens.
$2.00
$0.417 best
Output / 1MUS dollars per 1M output tokens.
$10.00
$1.25 best
Batch output / 1MBatch price per 1M output tokens.
$5.00
—
1K chats2K tokens in, 500 out, each.
$9.00
$1.46 best
1K documents20K tokens in, 1K out, each.
$50.00
$9.59 best
1K agent tasks200K tokens in, 20K out, each.
$600.00
$108.41 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
72.9
73.2 best
CodingCode writing and repair.
78.6 best
68.4
ReasoningLogic problems and puzzles.
78.8
—
MultimodalTasks with images and text.
73.2 best
63.3
KnowledgeFacts and expert knowledge.
75.7
81.8 best
MultilingualTasks in many languages.
71.9
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
—
—

Benchmarks

11 shared
Only GPT-6.2 Sol: 37Only Hy4: 15
GPT-6.2 Sol
Hy4
87.6% best16 / 130
81.0%35 / 130
37.0%52 / 98
41.3% best34 / 98
24.8%49 / 89
34.4% best20 / 89
60.6% best7 / 68
39.4%20 / 68
13.4 best10 / 59
8.515 / 59
10.9 best12 / 59
6.317 / 59
61.5% best7 / 52
37.9%23 / 52
12.1%21 / 42
12.5% best20 / 42
43.8% best6 / 32
31.0%13 / 32
66.0% best8 / 20
64.1%11 / 20
68.0% best4 / 15
19.8%14 / 15