Inkling (Xhigh)
Thinking MachinesOpen WeightApache 2.0 · Commercial OK
Description
Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs.
Release Date
2026-07-15
Parameters
975.0B
Context Length
262K
Modalities
audio, image, text
Capability Radar
26
general
51
coding
87
reasoning
62
science
50
agents
80
multimodal
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Agentic Capability | 40 | 52.0 | LS |
| Code Ranking | 107 | 72.0 | AA |
| General Ranking | 260 | 40.0 | AA |
| Math Reasoning | 37 | 88.0 | LB |
| Multimodal Ranking | 90 | 49.0 | LS |
| Reasoning | 42 | 78.0 | LB |
| Science | 87 | 69.0 | AA |
Benchmark Scores (LLM Stats)
(LLM Stats (zeroeval))Agents
Tau3 Banking
23.7%SR
Audio
MMAU
77.2%SR
Chat
VoiceBench Avg
91.4%SR
Factuality
SimpleQA Verified
43.9%SR
General
GDPval-AA
1238.00 / 3000SR
Global-MMLU-Lite
88.7%SR
Instruction Following
IFBench
79.8%SR
Knowledge
AA-Omniscience Index
2.10 / 200SR
Math
AIME 2026
97.1%SR
Reasoning
CharXiv-R
78.1%SR
SWE-Bench Verified
77.6%SR
MCP Atlas
76.0%SR
Terminal-Bench 2.1
63.8%SR
Humanity's Last Exam (with tools, text-only)
46.0%SR
Humanity's Last Exam (no tools, text-only)
29.7%SR
Vision
MMMU-Pro
73.5%SR
AA Evaluation Indices
(Artificial Analysis)Gpqa(NYU + Cohere + Anthropic (2023))87.2
Lcr(Artificial Analysis)77.3
Terminalbench V2 155.1
Coding Index(Artificial Analysis)52.1
Scicode(UIUC + Argonne National Lab (2024))47.0
Hle(Center for AI Safety + Scale AI (2025))31.9
Tau Banking29.1
Intelligence Index(Artificial Analysis)25.0
Terminalbench V4 01.0
LLM Stats Category Scores
(LLM Stats (zeroeval))Legal100
Finance100
Agents100
Reasoning83
General78
Knowledge2
Science2
Chat90
Language90
Safety90
Speech To Text90
Communication90
Instruction Following80
Multimodal80
Frontend Development80
Audio80
Vision80
Code70
Math60
Tool Calling50
Factuality40
Pricing
Input Price$1 / 1M tokens
Output Price$4.05 / 1M tokens
Blended Price (3:1)$1.762 / 1M tokens
Cache Read Price$0.17 / 1M tokens
Speed
Tokens/sec220.0
Time to First Token2.06s
Time to Answer11.15s
Provider Price Ranking
Provider Price Ranking
19 providers
Cheapest: DeepInfraMost Expensive: Abacus
ProviderInputOutput
1DeepInfraCheapest
$0
$0
2Venice AI
$0.5625
$1.5
3Deep Infra
$0.95
$4.05
4Thinking MachinesPRIMARY
$1
$4.05
5NanoGPT
$1
$4.05
6OpenRouter
$1
$4.05
7Hugging Face
$1
$4.05
8Kilo Gateway
$1
$4.05
9Vercel AI Gateway
$1
$4.05
10Together AI
$1
$4.05
11Merge Gateway
$1
$4.05
12Neon
$1
$4.05
13CommandCode
$1
$4.05
14AI/ML API
$1.058
$4.2849
15Charm Hyper
$1.0888
$4.40964
16Requesty
$1.87
$4.68
17LLMTR
$1.87
$4.68
18Impossibl
$1.87
$4.68
19Abacus
$3.74
$9.36
Compare pricing across different API providers for this model.