GPT-5.4 mini vs Qwen3.6 Plus

Change models
IndexAll categories, out of 100.
54.5 ±2.4
54.6 ±2.1 best
GapIndex points below the top.
−0.1 · no clear gap
Top
CoverageIndex weight that has results.
100%
100%
SpeedOutput tokens per second.
95/s best
44/s
EloLMArena rating and rank.
1412
1436 best
ReleasedMonth of release.
2026-03
2026-04
Input / 1MUS dollars per 1M input tokens.
$0.75
$0.325 best
Output / 1MUS dollars per 1M output tokens.
$4.50
$1.95 best
Batch output / 1MBatch price per 1M output tokens.
$2.25
—
1K chats2K tokens in, 500 out, each.
$3.75
$1.63 best
1K documents20K tokens in, 1K out, each.
$19.50
$8.45 best
1K agent tasks200K tokens in, 20K out, each.
$240.00
$104.00 best
ContextMaximum tokens in one request.
400K
1M best
AgenticMulti-step tasks with tools.
56.1 best
55.0
CodingCode writing and repair.
55.1
56.2 best
ReasoningLogic problems and puzzles.
52.2 best
51.2
MultimodalTasks with images and text.
54.8
56.1 best
KnowledgeFacts and expert knowledge.
53.7
54.1 best
MultilingualTasks in many languages.
57.6 best
54.1
InstructionTasks with strict prompt rules.
52.6 best
52.4
MathMath problems.
53.9
54.9 best

Benchmarks

52 shared
Only GPT-5.4 mini: 23Only Qwen3.6 Plus: 39
GPT-5.4 mini
Qwen3.6 Plus
28.1% best91 / 222
27.8%92 / 222
77.0%82 / 217
78.3% best63 / 217
86.9%65 / 217
88.4% best54 / 217
10.0% best65 / 214
2.9%98 / 214
88.9%63 / 200
93.3% best51 / 200
87.5%56 / 199
88.2% best52 / 199
37.5% best63 / 164
26.4%95 / 164
93.4%31 / 149
97.7% best9 / 149
73.3%29 / 146
75.2% best25 / 146
TaxEval v2Finance
71.2%80 / 143
74.7% best31 / 143
81.5%60 / 142
86.0% best24 / 142
88.0%38 / 141
90.4% best27 / 141
83.1%57 / 135
87.4% best38 / 135
MMLU ProKnowledge
84.6%60 / 135
87.7% best24 / 135
25.6% best71 / 133
24.5%74 / 133
CorpFin v2Finance
60.9%62 / 131
61.9% best49 / 131
48.0% best70 / 123
25.6%84 / 123
73.3%65 / 113
78.0% best39 / 113
63.5%52 / 97
68.0% best20 / 97
AIMEMath
95.6% best8 / 95
94.6%13 / 95