Inference
EN

GPT-6.1 Sol vs Hy4

Change models
GPT-6.1 SolOpenAI
Hy4Tencent
IndexAll categories, out of 100.
78.0 ±2.2 best
72.0 ±7.8
GapIndex points below the top.
Top
−6.0 · no clear gap
CoverageIndex weight that has results.
100% best
65%
SpeedOutput tokens per second.
34/s
52/s best
EloLMArena rating and rank.
1446
—
ReleasedMonth of release.
2026-09
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.
76.0 best
74.5
CodingCode writing and repair.
75.8 best
68.4
ReasoningLogic problems and puzzles.
81.8
—
MultimodalTasks with images and text.
72.2 best
57.4
KnowledgeFacts and expert knowledge.
78.0
83.7 best
MultilingualTasks in many languages.
73.2
—
InstructionTasks with strict prompt rules.
76.6
—
MathMath problems.
78.2
—

Benchmarks

11 shared
Only GPT-6.1 Sol: 87Only Hy4: 10
GPT-6.1 Sol
Hy4
Vibe Code Bench v1.1Coding
88.9% best10 / 123
81.0%30 / 123
Legal Research BenchLegal
38.5%39 / 90
41.3% best30 / 90
Tax Agent BenchFinance
21.8%49 / 82
34.4% best17 / 82
Terminal-Bench 4.0Agentic
55.1% best9 / 61
39.4%15 / 61
DeepSWEAgentic
71.9%18 / 59
74.9% best8 / 59
Agent Arena steerabilityAgentic
13.4 best8 / 54
8.814 / 54
Agent Arena task outcomeAgentic
11.7 best8 / 54
6.712 / 54
HLAB-Vals-1.1Legal
6.3%26 / 35
12.5% best17 / 35
AutomationBenchAgentic
36.1%22 / 32
56.2% best4 / 32
FrontierCode 2.0Coding
39.0% best6 / 27
31.0%9 / 27
Terminal-Bench-Science 0.1Agentic
57.0% best7 / 11
19.8%11 / 11