Inference
EN

Inkling 2 Small vs Ling 3.1 Flash

Change models
Inkling 2 SmallThinking Machines Lab
Ling 3.1 FlashInclusionAI
IndexAll categories, out of 100.
66.3 ±3.7
67.0 ±7.2 best
GapIndex points below the top.
−0.7 · no clear gap
Top
CoverageIndex weight that has results.
90% best
70%
SpeedOutput tokens per second.
—
81/s
EloLMArena rating and rank.
1403
—
ReleasedMonth of release.
2026-11
2026-09
Input / 1MUS dollars per 1M input tokens.
$0.30
$0.045 best
Output / 1MUS dollars per 1M output tokens.
$1.00
$0.135 best
1K chats2K tokens in, 500 out, each.
$1.10
$0.158 best
1K documents20K tokens in, 1K out, each.
$7.00
$1.04 best
1K agent tasks200K tokens in, 20K out, each.
$80.00
$11.70 best
ContextMaximum tokens in one request.
1M
1M
AgenticMulti-step tasks with tools.
67.6 best
66.5
CodingCode writing and repair.
67.0 best
66.7
ReasoningLogic problems and puzzles.
68.5 best
67.8
MultimodalTasks with images and text.
63.1
—
KnowledgeFacts and expert knowledge.
61.3
70.2 best
MultilingualTasks in many languages.
—
—
InstructionTasks with strict prompt rules.
—
—
MathMath problems.
60.3
—

Benchmarks

8 shared
Only Inkling 2 Small: 50Only Ling 3.1 Flash: 10
Inkling 2 Small
Ling 3.1 Flash
Artificial Analysis Humanity's Last ExamKnowledge
44.1% best29 / 222
39.4%50 / 222
Artificial Analysis Long Context ReasoningReasoning
83.3% best13 / 217
83.0%18 / 217
Artificial Analysis SciCodeCoding
52.3%41 / 114
54.1% best36 / 114
Terminal-Bench 2.1 · BenchLMAgentic
85.1% best19 / 86
81.2%31 / 86
Humanity's Last ExamKnowledge
53.2% best16 / 77
37.4%37 / 77
BrowseCompAgentic
90.2%9 / 63
91.7% best5 / 63
DeepSWEAgentic
72.1% best17 / 59
59.7%42 / 59
MCP AtlasAgentic
85.0% best5 / 52
83.0%11 / 52