Skip to main content

Model comparison

Inkling vs MAI-Thinking-1

Data verified

Head-to-head evidence from 8 shared benchmark results across 5 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Thinking Machines Lab
69/100
Margin
11.0pts
← winning
58/100
3 category wins2 category wins

Verified leaderboard positions: Inkling #17; MAI-Thinking-1 #28

Evidence parity. Inkling and MAI-Thinking-1 share 8 comparable benchmark results. 5 of 8 categories are comparable. 8 results are unique to Inkling; 6 to MAI-Thinking-1.

Updated July 15, 2026
Shared results
8
Inkling only
8
MAI-Thinking-1 only
6
Comparable categories
5 / 8

Pick Inkling if you want the stronger benchmark profile. MAI-Thinking-1 only becomes the better choice if knowledge is the priority or you want the stronger reasoning-first profile.

Confidence note. This is a partial-evidence comparison with 8 shared benchmark results across 5 evidence categories; 5 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Inkling is clearly ahead on the provisional aggregate, 69 to 58. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Inkling's sharpest advantage is in agentic, where it averages 69.4 against 46. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 63.8% to 46%. MAI-Thinking-1 does hit back in knowledge, so the answer changes if that is the part of the workload you care about most.

MAI-Thinking-1 is the reasoning model in the pair, while Inkling is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. Inkling gives you the larger context window at 1M, compared with 256K for MAI-Thinking-1.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for Inkling and MAI-Thinking-1
CategoryInklingΔMAI-Thinking-1
AgenticInkling69.4Margin 23.4MAI-Thinking-146.0
KnowledgeInkling51.7Margin 20.8MAI-Thinking-172.5
MathInkling97.1Margin 7.4MAI-Thinking-189.7
Inst. FollowingInkling79.8Margin 5.2MAI-Thinking-185.0
CodingInkling68.6Margin 3.1MAI-Thinking-165.5
MultimodalInkling76.5MarginNo overlapMAI-Thinking-1Not measured

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · InklingB · MAI-Thinking-1
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 63.8%B 46%
    Winner: InklingΔ 17.8
    Terminal-Bench 2.0: Inkling scored 63.8%; MAI-Thinking-1 scored 46%. Inkling wins this benchmark.
  2. IFBench

    Inst. Following
    Source ↗
    A 79.8%B 85%
    Winner: MAI-Thinking-1Δ 5.2
    IFBench: Inkling scored 79.8%; MAI-Thinking-1 scored 85%. MAI-Thinking-1 wins this benchmark.
  3. SWE-bench Verified

    Coding
    Source ↗
    A 77.6%B 73.5%
    Winner: InklingΔ 4.1
    SWE-bench Verified: Inkling scored 77.6%; MAI-Thinking-1 scored 73.5%. Inkling wins this benchmark.
  4. GPQA

    Knowledge
    Source ↗
    A 87.9%B 84.2%
    Winner: InklingΔ 3.7
    GPQA: Inkling scored 87.9%; MAI-Thinking-1 scored 84.2%. Inkling wins this benchmark.
  5. AIME26

    Math
    Source ↗
    A 97.1%B 94.5%
    Winner: InklingΔ 2.6
    AIME26: Inkling scored 97.1%; MAI-Thinking-1 scored 94.5%. Inkling wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricInklingMAI-Thinking-1Comparison
Input / output priceUSD per 1M tokensInkling$1.87 input / $4.68 outputMAI-Thinking-1Not availableA complete price comparison is not available.
Generation speedtokens per secondInklingNot availableMAI-Thinking-1Not availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenInklingNot availableMAI-Thinking-1Not availableA complete latency comparison is not available.
Context windowmaximum listed tokensInkling1MMAI-Thinking-1256KInkling lists the larger context window.

Benchmark Deep Dive

AgenticInkling wins
BenchmarkInklingMAI-Thinking-1Result
Terminal-Bench 2.0Source 63.8%46%Inkling leads
BrowseCompSource 77.1%Not comparable
MCP AtlasSource 74.1%Not comparable
Design Arena Agentic Web DevSource 1258Not comparable
CodingInkling wins
BenchmarkInklingMAI-Thinking-1Result
SWE-bench VerifiedSource 77.6%73.5%Inkling leads
SWE-bench ProSource 54.3%52.8%Inkling leads
Terminal-Bench 2.0Source 63.8%46.0%Inkling leads
LiveCodeBench v6Source 87.7%Not comparable
Reasoning
BenchmarkInklingMAI-Thinking-1Result
Graphwalks BFS 128KSource 90%Not comparable
KnowledgeMAI-Thinking-1 wins
BenchmarkInklingMAI-Thinking-1Result
GPQASource 87.9%84.2%Inkling leads
GPQA-DSource 87.9%84.2%Inkling leads
HLESource 46%Not comparable
HLE w/o toolsSource 30%Not comparable
MMLU-ProSource 85%Not comparable
SimpleQASource 31%Not comparable
MathInkling wins
BenchmarkInklingMAI-Thinking-1Result
AIME26Source 97.1%94.5%Inkling leads
AIME 2025Source 97%Not comparable
HMMT Feb 2026Source 84.9%Not comparable
Multimodal
BenchmarkInklingMAI-Thinking-1Result
MMMU-ProSource 73.5%Not comparable
CharXivSource 82%Not comparable
CharXiv w/o toolsSource 78.1%Not comparable
Inst. FollowingMAI-Thinking-1 wins
BenchmarkInklingMAI-Thinking-1Result
IFBenchSource 79.8%85%MAI-Thinking-1 leads
Frequently Asked Questions (6)

Which is better, Inkling or MAI-Thinking-1?

Inkling is ahead on BenchLM's provisional leaderboard, 69 to 58. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 63.8% and 46%.

Which is better for knowledge tasks, Inkling or MAI-Thinking-1?

MAI-Thinking-1 has the edge for knowledge tasks in this comparison, averaging 72.5 versus 51.7. Inside this category, GPQA is the benchmark that creates the most daylight between them.

Which is better for coding, Inkling or MAI-Thinking-1?

Inkling has the edge for coding in this comparison, averaging 68.6 versus 65.5. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for math, Inkling or MAI-Thinking-1?

Inkling has the edge for math in this comparison, averaging 97.1 versus 89.7. Inside this category, AIME26 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Inkling or MAI-Thinking-1?

Inkling has the edge for agentic tasks in this comparison, averaging 69.4 versus 46. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for instruction following, Inkling or MAI-Thinking-1?

MAI-Thinking-1 has the edge for instruction following in this comparison, averaging 85 versus 79.8. Inside this category, IFBench is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 15, 2026

The AI models change fast. We track them for you.

A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.

Free. No spam. Unsubscribe anytime.