GPT-6.1 Terra vs Hy4

Change models
Hy4Tencent
IndexAll categories, out of 100.
77.1 ±3.8 best
72.0 ±7.8
GapIndex points below the top.
Top
−5.1 · no clear gap
CoverageIndex weight that has results.
90% best
65%
SpeedOutput tokens per second.
46/s
52/s best
EloLMArena rating and rank.
—
—
ReleasedMonth of release.
2026-10
2026-11
Input / 1MUS dollars per 1M input tokens.
$1.00
$0.417 best
Output / 1MUS dollars per 1M output tokens.
$5.00
$1.25 best
Batch output / 1MBatch price per 1M output tokens.
$2.50
—
1K chats2K tokens in, 500 out, each.
$4.50
$1.46 best
1K documents20K tokens in, 1K out, each.
$25.00
$9.59 best
1K agent tasks200K tokens in, 20K out, each.
$300.00
$108.41 best
ContextMaximum tokens in one request.
1.05M
1.05M
AgenticMulti-step tasks with tools.
78.6 best
74.5
CodingCode writing and repair.
74.4 best
68.4
ReasoningLogic problems and puzzles.
81.3
—
MultimodalTasks with images and text.
73.2 best
57.4
KnowledgeFacts and expert knowledge.
70.5
83.7 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
76.9
—

Benchmarks

10 shared
Only GPT-6.1 Terra: 40Only Hy4: 11
GPT-6.1 Terra
Hy4
84.0% best19 / 123
81.0%30 / 123
26.0%62 / 90
41.3% best30 / 90
17.1%58 / 82
34.4% best17 / 82
49.5% best11 / 61
39.4%15 / 61
16.6 best4 / 54
8.814 / 54
9.7 best11 / 54
6.712 / 54
85.5% best1 / 53
78.6%22 / 53
1.7%35 / 35
12.5% best17 / 35
60.0% best1 / 21
41.0%8 / 21
58.3% best6 / 11
19.8%11 / 11