Inkling vs Qwen3.6 Plus

Change models
InklingThinking Machines Lab
IndexAll categories, out of 100.
54.8 ±2.9 best
54.6 ±2.1
GapIndex points below the top.
Top
−0.2 · no clear gap
CoverageIndex weight that has results.
95%
100% best
SpeedOutput tokens per second.
85/s best
44/s
EloLMArena rating and rank.
1444 best
1436
ReleasedMonth of release.
2026-07
2026-04
Input / 1MUS dollars per 1M input tokens.
$1.00
$0.325 best
Output / 1MUS dollars per 1M output tokens.
$4.05
$1.95 best
1K chats2K tokens in, 500 out, each.
$4.03
$1.63 best
1K documents20K tokens in, 1K out, each.
$24.05
$8.45 best
1K agent tasks200K tokens in, 20K out, each.
$281.00
$104.00 best
ContextMaximum tokens in one request.
524K
1M best
AgenticMulti-step tasks with tools.
51.2
55.0 best
CodingCode writing and repair.
54.1
56.2 best
ReasoningLogic problems and puzzles.
56.1 best
51.2
MultimodalTasks with images and text.
55.0
56.1 best
KnowledgeFacts and expert knowledge.
57.1 best
54.1
MultilingualTasks in many languages.
—
54.1
InstructionTasks with strict prompt rules.
66.0 best
52.4
MathMath problems.
54.1
54.9 best

Benchmarks

47 shared
Only Inkling: 31Only Qwen3.6 Plus: 44
Inkling
Qwen3.6 Plus
31.9% best72 / 222
27.8%92 / 222
77.3%77 / 217
78.3% best63 / 217
88.3%56 / 217
88.4% best54 / 217
5.4% best81 / 214
2.9%98 / 214
88.9%63 / 200
93.3% best51 / 200
87.2%59 / 199
88.2% best52 / 199
39.3% best56 / 164
26.4%95 / 164
82.9%64 / 149
84.2% best37 / 149
TaxEval v2Finance
75.3% best19 / 143
74.7%31 / 143
85.5%30 / 142
86.0% best24 / 142
87.9%39 / 141
90.4% best27 / 141
87.1%40 / 135
87.4% best38 / 135
MMLU ProKnowledge
86.3%43 / 135
87.7% best24 / 135
28.6% best65 / 133
24.5%74 / 133
CorpFin v2Finance
68.6% best7 / 131
61.9%49 / 131
19.2%94 / 123
25.6% best84 / 123
77.6%33 / 114
78.8% best26 / 114
73.5%63 / 113
78.0% best39 / 113
MedScribeHealthcare
85.4% best28 / 109
77.0%73 / 109
MedCodeHealthcare
41.2% best56 / 106
36.9%76 / 106