GPT-4.1 vs Inkling-Small

Updated October 29, 2026. Rank says Inkling-Small is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.

Decision reading

Inkling-Small has the higher public score estimate, 49.5 versus 36.8, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 3 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.

Model A

GPT-4.1

OpenAI

36.8/100

Supported · Public rank #153

90% interval 20.4–53.2

Model B

Inkling-Small

Thinking Machines Lab

49.5/100

Supported · Public rank #96

90% interval 32.4–66.6

Shared results: 3
GPT-4.1 only: 4
Inkling-Small only: 25
Like-for-like categories: 1 / 8

Supported: GPT-4.1 and Inkling-SmallHow the comparison works

Which one for your work

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.

Chat turn cost
1K fresh input + 500 output tokens
Inkling-Small
Inkling-Small has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
Inkling-Small
Inkling-Small has the lower estimated token cost for this stated workload. GPT-4.1 has no published cached-input rate, so cached tokens use its listed input rate.
Confidence: rate-fallback

Show secondary and unsupported calls

Repository review cost
50K fresh input + 3K output tokens
Inkling-Small
Inkling-Small has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Coding work
Code generation, repair, and software-engineering tasks
Not enough matched evidence
GPT-4.1 is not ranked on the public lane for coding, so no winner is named for coding.
Confidence: limited
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
GPT-4.1 is not ranked on the public lane for agentic, so no winner is named for agentic.
Confidence: limited
Long documents
Prompts that approach the documented context limit
No clear pick
The documented context windows are equal.
Confidence: documented

Which one for a specific job

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.

Pick the job you would use them for

The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.

—GPT-4.136.9Inkling-Small

Not comparable · BenchAlign v5.8

The coding row is not comparable on the public lane: at least one model is not measured or not ranked there.

Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.

Open the coding leaderboard Shortlist models for this job

Same basis rules as the category table below

Shape of the matched evidence

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.

FrontierMath v2 (Tiers 1-3)Math
Normalized gap 40.4
GPT-4.1:5.965%
Inkling-Small:46.316%
Shared source
SWE-bench VerifiedCoding
Normalized gap 25.6
GPT-4.1:54.6%
Inkling-Small:80.2%
GPT-4.1 source Inkling-Small source
GPQAKnowledge
Normalized gap 23.2
GPT-4.1:66.3%
Inkling-Small:89.5%
GPT-4.1 source Inkling-Small source

Bars run 0–100 on each benchmark’s normalized display scale

Category results, on a stated basis

Each row shows the public-lane category score for both models: the BenchAlign v5.8 lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.

Knowledge

Like-for-like

GPT-4.1: 34.4; Supported · #137/179
Inkling-Small: 50.6; Supported · #75/179
Basis: BenchAlign v5.8 lane · 2 vs 6 public rows
Reading: Inkling-Small leads · intervals overlap

Instruction following

Directional only

GPT-4.1: 50.3; #99/157
Inkling-Small: 93.3; #10/157
Basis: Provisional lane · 0 vs 1 weighted rows
Reading: Directional only

Agentic

Not comparable

GPT-4.1: Not ranked
Inkling-Small: 36.1; Supported · #86/135
Basis: BenchAlign v5.8 lane · 1 vs 5 public rows
Reading: Not comparable

Coding

Not comparable

GPT-4.1: Not ranked
Inkling-Small: 36.9; Supported · #77/156
Basis: BenchAlign v5.8 lane · 1 vs 6 public rows
Reading: Not comparable

Reasoning

Not comparable

GPT-4.1: 71.9; Unranked · 2 rankable rows
Inkling-Small: 55.0; Unranked · 4 rankable rows
Basis: Provisional lane · 0 vs 1 weighted rows
Reading: Not comparable

Multimodal

Not comparable

GPT-4.1: 55.3; Unranked · 1 rankable row
Inkling-Small: 67.3; #41/58
Basis: Provisional lane · 0 vs 2 weighted rows
Reading: Not comparable

Multilingual

Not comparable

GPT-4.1: 61.5; #14/17
Inkling-Small: Not ranked
Basis: Provisional lane · 1 vs 0 weighted rows
Reading: Not comparable

Math

Not comparable

GPT-4.1: 27.0; Unranked · 1 rankable row
Inkling-Small: 69.8; #5/12
Basis: Provisional lane · 1 vs 4 weighted rows
Reading: Not comparable

Category scores with the server-provided evidence basis for GPT-4.1 and Inkling-Small
Category	GPT-4.1	Inkling-Small	Basis	Reading
Knowledge	34.4Supported · #137/179	50.6Supported · #75/179	Like-for-likeBenchAlign v5.8 lane · 2 vs 6 public rows	Inkling-Small leads · intervals overlap
Instruction following	50.3#99/157	93.3#10/157	Directional onlyProvisional lane · 0 vs 1 weighted rows	Directional only
Agentic	Not ranked	36.1Supported · #86/135	Not comparableBenchAlign v5.8 lane · 1 vs 5 public rows	Not comparable
Coding	Not ranked	36.9Supported · #77/156	Not comparableBenchAlign v5.8 lane · 1 vs 6 public rows	Not comparable
Reasoning	71.9Unranked · 2 rankable rows	55.0Unranked · 4 rankable rows	Not comparableProvisional lane · 0 vs 1 weighted rows	Not comparable
Multimodal	55.3Unranked · 1 rankable row	67.3#41/58	Not comparableProvisional lane · 0 vs 2 weighted rows	Not comparable
Multilingual	61.5#14/17	Not ranked	Not comparableProvisional lane · 1 vs 0 weighted rows	Not comparable
Math	27.0Unranked · 1 rankable row	69.8#5/12	Not comparableProvisional lane · 1 vs 4 weighted rows	Not comparable

Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.

Supported evidence per lane · bars run 0–100Methodology

What each workload costs

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.

Chat turn

1K fresh input + 500 output tokens

GPT-4.1: $0.006; Fits in one request
Inkling-Small: $0.0013; Fits in one request

Inkling-Small has the lower modeled cost

Costs use the listed standard API rates.

Repository review

50K fresh input + 3K output tokens

GPT-4.1: $0.124; Fits in one request
Inkling-Small: $0.03332; Fits in one request

Inkling-Small has the lower modeled cost

Costs use the listed standard API rates.

Cache-heavy agent loop

200K cached + 20K fresh input + 10K output tokens

GPT-4.1: $0.52; Fits in one request; Cached input priced at the published list-input rate
Inkling-Small: $0.0492; Fits in one request

Inkling-Small has the lower modeled cost

GPT-4.1 has no published cached-input rate, so cached tokens use its listed input rate.

Cached input falls back to the list input rate only where a cached rate is unpublished

Specification differences

Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.

SpecificationGPT-4.1Inkling-Small

Context window

Maximum documented context; output-token limits may be lower.

GPT-4.1

Inkling-Small

API model ID

GPT-4.1

Not sourced

Inkling-Small

Not sourced

Cached-input rate

A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.

GPT-4.1

Not published

Inkling-Small

$0.116 per 1M cached input tokens

Documented inputs

GPT-4.1

Not sourced

Inkling-Small

Not sourced

Documented outputs

GPT-4.1

Not sourced

Inkling-Small

Not sourced

Provider availability

GPT-4.1

Not sourced

Inkling-Small

Not sourced

Reasoning profile

GPT-4.1

Non-Reasoning

Inkling-Small

Hybrid

Weight access

GPT-4.1

Proprietary

Inkling-Small

Open Weight

License

GPT-4.1

Proprietary

Inkling-Small

Open Weight

Release date

GPT-4.1

2025-04-14

Inkling-Small

2026-07-30

If you already use one of these models

Deployment change: The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
Quality signal: Inkling-Small has the higher public score estimate, 49.5 versus 36.8, but the 90% score intervals overlap.
Workload cost: Repository review: $0.124 vs $0.03332. Cache-heavy agent loop: $0.52 vs $0.0492.
Context tradeoff: Both models list 1M.

Run the same representative tasks against both endpoints before changing production traffic.

Questions

Which is better, GPT-4.1 or Inkling-Small?

Inkling-Small has the higher public score estimate, 49.5 versus 36.8, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.

Which is better for coding, GPT-4.1 or Inkling-Small?

GPT-4.1 is not ranked on the public lane for coding, so no winner is named for coding.

Which is better for agentic tasks, GPT-4.1 or Inkling-Small?

GPT-4.1 is not ranked on the public lane for agentic tasks, so no winner is named for agentic tasks.

Which costs less, GPT-4.1 or Inkling-Small?

For the stated presets, chat costs $0.006 on GPT-4.1 and $0.0013 on Inkling-Small; repository review costs $0.124 and $0.03332; the cache-heavy agent loop costs $0.52 and $0.0492. GPT-4.1 has no published cached-input rate, so cached tokens use its listed input rate.

Which has the larger context window, GPT-4.1 or Inkling-Small?

Both models list the same context window, 1M.

Benchmark evidence

The full public result ledger is available for audit without forcing a wide desktop table onto a phone.

Browse raw public benchmark evidence32 rows

Agentic

Gert Labs
GPT-4.125.65%
Source
Inkling-Small—
Not directly comparable
Terminal-Bench 2.1
GPT-4.1—
Inkling-Small64.7%
Source
Not directly comparable
BrowseComp
GPT-4.1—
Inkling-Small77.4%
Source
Not directly comparable
MCP Atlas
GPT-4.1—
Inkling-Small79.6%
Source
Not directly comparable
Toolathlon-Verified
GPT-4.1—
Inkling-Small54.4%
Source
Not directly comparable
Terminal-Bench 2.1 (Vals)
GPT-4.1—
Inkling-Small55.1%
Source
Not directly comparable

Coding

SWE-bench Verified
GPT-4.154.6%
Source
Inkling-Small80.2%
Source
Inkling-Small leads this result
SWE-bench Pro
GPT-4.1—
Inkling-Small55.9%
Source
Not directly comparable
Terminal-Bench 2.1
GPT-4.1—
Inkling-Small64.7%
Source
Not directly comparable
SciCode
GPT-4.1—
Inkling-Small48.7%
Source
Not directly comparable
LiveCodeBench (Vals)
GPT-4.1—
Inkling-Small85.9%
Source
Not directly comparable
SWE-bench (Vals)
GPT-4.1—
Inkling-Small82.2%
Source
Not directly comparable

Reasoning

ARC-AGI-2
GPT-4.1—
Inkling-Small40.1%
Source
Not directly comparable
CritPt
GPT-4.1—
Inkling-Small8.3%
Source
Not directly comparable
ARC-AGI-1
GPT-4.1—
Inkling-Small84.00%
Source
Not directly comparable

Multimodal

MMMU-Pro
GPT-4.1—
Inkling-Small74%
Source
Not directly comparable
CharXiv
GPT-4.1—
Inkling-Small81.3%
Source
Not directly comparable
CharXiv w/o tools
GPT-4.1—
Inkling-Small77.4%
Source
Not directly comparable

Knowledge

MMLU
GPT-4.190.2%
Source
Inkling-Small—
Not directly comparable
GPQA
GPT-4.166.3%
Source
Inkling-Small89.5%
Source
Inkling-Small leads this result
GPQA-D
GPT-4.1—
Inkling-Small89.5%
Source
Not directly comparable
HLE
GPT-4.1—
Inkling-Small47.8%
Source
Not directly comparable
HLE w/o tools
GPT-4.1—
Inkling-Small31.6%
Source
Not directly comparable
GPQA Diamond (Vals)
GPT-4.1—
Inkling-Small83.6%
Source
Not directly comparable
MMLU-Pro (Vals)
GPT-4.1—
Inkling-Small85.6%
Source
Not directly comparable

Multilingual

MMLU-ProX
GPT-4.172.7%
Source
Inkling-Small—
Not directly comparable

Instruction following

IFEval
GPT-4.187.4%
Source
Inkling-Small—
Not directly comparable
IFBench
GPT-4.1—
Inkling-Small82.2%
Source
Not directly comparable

Math

FrontierMath v2 (Tiers 1-3)
Shared source
GPT-4.15.965%
Inkling-Small46.316%
Inkling-Small leads this result
AIME26
GPT-4.1—
Inkling-Small95.5%
Source
Not directly comparable
HMMT Feb 2026
GPT-4.1—
Inkling-Small90.2%
Source
Not directly comparable
FrontierMath v2 (Tier 4)
GPT-4.1—
Inkling-Small17.073%
Source
Not directly comparable

32 public results · 3 shared

Related comparisons

Compare API pricing Read the methodology Open the model selector

Watch GPT-4.1 vs Inkling-Small

One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.

Read a sample issue

Join 6,100+ subscribers.

Last updated October 29, 2026

GPT-4.1 vs Inkling-Small

Decision reading

Which one for your work

Chat turn cost

Cache-heavy agent loop cost

Repository review cost

Coding work

Agentic work

Long documents

Which one for a specific job

What is actually comparable

Shape of the matched evidence

Category results, on a stated basis

Knowledge

Instruction following

Agentic

Coding

Reasoning

Multimodal

Multilingual

Math

What each workload costs

Chat turn

Repository review

Cache-heavy agent loop

Specification differences

Context window

API model ID

Cached-input rate

Documented inputs

Documented outputs

Provider availability

Reasoning profile

Weight access

License

Release date

If you already use one of these models

Questions

Which is better, GPT-4.1 or Inkling-Small?

Which is better for coding, GPT-4.1 or Inkling-Small?

Which is better for agentic tasks, GPT-4.1 or Inkling-Small?

Which costs less, GPT-4.1 or Inkling-Small?

Which has the larger context window, GPT-4.1 or Inkling-Small?

Benchmark evidence

Agentic

Coding

Reasoning

Multimodal

Knowledge

Multilingual

Instruction following

Math

Related comparisons

Watch GPT-4.1 vs Inkling-Small