Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Hy4 preview and Inkling 2 Mini are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Updated November 21, 2026. Rank says Hy4 preview is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Hy4 preview has the higher public point estimate, 68.2 versus 55.9. Their conditional score ranges overlap. These ranges do not establish rank confidence. 10 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Thinking Machines Lab
55.9/100
Estimated · Public rank #69
Conditional range 46.0–65.9
Hy4 preview: No comparable API price
Inkling 2 Mini: $0.15 input / $0.50 output
Hy4 preview: 1M
Inkling 2 Mini: 1M
Hy4 preview: August 28, 2026
Inkling 2 Mini: November 20, 2026
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
No workload recommendation clears the current evidence threshold.
Use the matched evidence, workload costs, and sourced specifications below instead of treating a point score as a universal answer.
Code generation, repair, and software-engineering tasks
Not enough matched evidence
Hy4 preview and Inkling 2 Mini are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like.
Tool use, computer use, and multi-step task completion
Not enough matched evidence
Inkling 2 Mini is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
Directional only · BenchAlign v6.0
Hy4 preview has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.
We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
6 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
HLE w/o toolsKnowledge
Normalized gap 12.7SWE MultilingualCoding
Normalized gap 9.2GPQAKnowledge
Normalized gap 5.7Each row shows the public-lane category score for both models: the BenchAlign v6.0 lane in every category, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence. Directional and not-comparable rows remain visible, but they never receive a winner.
| Category | Hy4 preview | Inkling 2 Mini | Basis | Reading |
|---|---|---|---|---|
| Agentic | 66.8Supported · #31/179 | 59.1Estimated · #61/179 | Directional onlyBenchAlign v6.0 lane · 18 vs 8 public rows | Directional only |
| Coding | 71.7Estimated · #24/179 | 53.9Estimated · #67/179 | Directional onlyBenchAlign v6.0 lane · 8 vs 5 public rows | Directional only |
| Reasoning | 66.0Supported · #29/161 | 57.8Estimated · #58/161 | Directional onlyBenchAlign v6.0 lane · 2 vs 2 public rows | Directional only |
| Multimodal | 67.9Estimated · #27/119 | 55.5Estimated · #62/119 | Directional onlyBenchAlign v6.0 lane · 1 vs 13 public rows | Directional only |
| Knowledge | 63.3Estimated · #33/158 | 51.9Estimated · #79/158 | Directional onlyBenchAlign v6.0 lane · 4 vs 3 public rows | Directional only |
| Multilingual | 62.7Estimated · #15/87 | 54.7Estimated · #39/87 | Directional onlyBenchAlign v6.0 lane · 0 vs 0 public rows | Directional only |
| Instruction following | Not ranked | Not ranked | Not comparableBenchAlign v6.0 lane · 0 vs 1 public rows | Not comparable |
| Math | Not ranked | Not ranked | Not comparableBenchAlign v6.0 lane · 1 vs 1 public rows | Not comparable |
Ranks count the models scored in each category’s BenchAlign v6.0 lane, so denominators differ by category. Like-for-like rows within 0.5 points read as a practical tie.
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
1K fresh input + 500 output tokens
Hy4 preview has no comparable published API token rate.
50K fresh input + 3K output tokens
Hy4 preview has no comparable published API token rate.
200K cached + 20K fresh input + 10K output tokens
Hy4 preview has no comparable published API token rate.
Overall score against output price per 1M tokens, one model per family. Pricing as of November 20, 2026.
Inkling 2 Mini
Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.
See Inkling 2 Mini on the full price vs performance chartSourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
Hy4 preview
Inkling 2 Mini
Hy4 preview
tencent/Hy4-preview
Tencent Hy4 preview model cardInkling 2 Mini
thinkingmachines/Inkling-2-Mini
Tinker models and pricingA missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Hy4 preview
No comparable hosted API rate
Tencent Hy4 preview model cardInkling 2 Mini
$0.015 per 1M cached input tokens
Tinker models and pricingHy4 preview
Inkling 2 Mini
text, image
Inkling 2 Mini model cardHy4 preview
Inkling 2 Mini
Hy4 preview
Not sourced
Inkling 2 Mini
Not sourced
Hy4 preview
Reasoning
Inkling 2 Mini
Hybrid
Hy4 preview
Open Weight
Inkling 2 Mini
Open Weight
Hy4 preview
Open Weight
Inkling 2 Mini
Open Weight
Hy4 preview
2026-08-28
Inkling 2 Mini
2026-11-20
Hy4 preview has the higher public point estimate, 68.2 versus 55.9. Their conditional score ranges overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
Hy4 preview scores higher for coding on the public lane, 71.7 to 53.9. Hy4 preview and Inkling 2 Mini are scored on Estimated evidence for coding, so the reading is directional rather than like-for-like. BenchLM does not name a winner for coding from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Hy4 preview scores higher for agentic tasks on the public lane, 66.8 to 59.1. Inkling 2 Mini is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Both models list the same context window, 1M.
Estimates at 50,000 req/day · 1000 tokens/req average.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 2.1
Hy4 preview leads this result
CyberGym
Not directly comparable
WideResearch
Not directly comparable
DRACO
Not directly comparable
MCP Atlas
Hy4 preview leads this result
Toolathlon-Verified
Not directly comparable
APEX-Agents
Not directly comparable
skillsBench
Not directly comparable
JobBench
Hy4 preview leads this result
Agents' Last Exam
Not directly comparable
AutomationBench
Not directly comparable
BankerToolBench
Not directly comparable
HLE w/ tools
Not directly comparable
Terminal-Bench 2.1 (Vals)
Not directly comparable
CWE-bench v1
Not directly comparable
Hermes Index
Not directly comparable
Hermes Bench
Not directly comparable
CWE-bench
Not directly comparable
Terminal-Bench 4.0
Not directly comparable
Terminal-Bench-Science 0.1
Not directly comparable
BrowseComp
Not directly comparable
DeepSearchQA
Not directly comparable
EnterpriseOps-Gym
Not directly comparable
Terminal-Bench 2.1
Hy4 preview leads this result
SWE-bench Pro
Not directly comparable
SWE Multilingual
Hy4 preview leads this result
DeepSWE
Hy4 preview leads this result
NL2Repo
Not directly comparable
ProgramBench
Not directly comparable
PostTrainBench (lab runs)
Not directly comparable
sweMarathon
Not directly comparable
FrontierCode 2.0
Not directly comparable
SWE-bench Verified
Not directly comparable
OfficeQA Pro
Not directly comparable
PerceptionBench
Not directly comparable
MMMU-Pro
Not directly comparable
OmniDocBench 1.6
Not directly comparable
BabyVision
Not directly comparable
BabyVision w/ Python
Not directly comparable
ScreenSpot Pro
Not directly comparable
CharXiv
Not directly comparable
CharXiv w/o tools
Not directly comparable
Chartography (no tools)
Not directly comparable
Chartography (tools)
Not directly comparable
ZeroBench
Not directly comparable
ZeroBench w/ Python
Not directly comparable
MathVision
Not directly comparable
GPQA
Hy4 preview leads this result
GPQA-D
Hy4 preview leads this result
HLE
Not directly comparable
HLE w/o tools
Hy4 preview leads this result
MultiChallenge (provider reports)
Not directly comparable
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 7,000+ subscribers.
Last updated November 21, 2026