Skip to main content

Model comparison

Inkling vs LFM2.5-8B-A1B

Data verified

Head-to-head evidence from 2 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Thinking Machines Lab
69/100
Margin
27.8pts
← winning
41.25/100
2 category wins0 category wins

Verified leaderboard positions: Inkling #17; LFM2.5-8B-A1B unranked

BenchAlign evidence: Inkling not scored; LFM2.5-8B-A1B estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Inkling and LFM2.5-8B-A1B share 2 comparable benchmark results. 2 of 8 categories are comparable. 14 results are unique to Inkling; 16 to LFM2.5-8B-A1B.

Updated July 15, 2026
Shared results
2
Inkling only
14
LFM2.5-8B-A1B only
16
Comparable categories
2 / 8

Pick Inkling if you want the stronger benchmark profile. LFM2.5-8B-A1B only becomes the better choice if you want the cheaper token bill or you want the stronger reasoning-first profile.

Confidence note. This is a partial-evidence comparison with 2 shared benchmark results across 2 evidence categories; 2 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 37. 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 mathematics, where it averages 97.1 against 50. The single biggest benchmark swing on the page is AIME26, 97.1% to 50.0%.

Inkling is also the more expensive model on tokens at $1.87 input / $4.68 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for LFM2.5-8B-A1B. That is roughly Infinityx on output cost alone. LFM2.5-8B-A1B 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 128K for LFM2.5-8B-A1B.

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 LFM2.5-8B-A1B
CategoryInklingΔLFM2.5-8B-A1B
MathInkling97.1Margin 47.1LFM2.5-8B-A1B50.0
Inst. FollowingInkling79.8Margin 11.0LFM2.5-8B-A1B68.8
AgenticInkling69.4MarginNo overlapLFM2.5-8B-A1BNot measured
CodingInkling68.6MarginNo overlapLFM2.5-8B-A1BNot measured
KnowledgeInkling51.7MarginNo overlapLFM2.5-8B-A1BNot measured
MultimodalInkling76.5MarginNo overlapLFM2.5-8B-A1BNot measured

Decisive benchmark drivers

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

More
A · InklingB · LFM2.5-8B-A1B
  1. AIME26

    Math
    Source ↗
    A 97.1%B 50.0%
    Winner: InklingΔ 47.1
    AIME26: Inkling scored 97.1%; LFM2.5-8B-A1B scored 50.0%. Inkling wins this benchmark.
  2. IFBench

    Inst. Following
    Source ↗
    A 79.8%B 56.5%
    Winner: InklingΔ 23.3
    IFBench: Inkling scored 79.8%; LFM2.5-8B-A1B scored 56.5%. Inkling wins this benchmark.

Operational comparison

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

MetricInklingLFM2.5-8B-A1BComparison
Input / output priceUSD per 1M tokensInkling$1.87 input / $4.68 outputLFM2.5-8B-A1B$0 input / $0 outputLFM2.5-8B-A1B has the lower combined listed price.
Generation speedtokens per secondInklingNot availableLFM2.5-8B-A1BNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenInklingNot availableLFM2.5-8B-A1BNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensInkling1MLFM2.5-8B-A1B128KInkling lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkInklingLFM2.5-8B-A1BResult
Terminal-Bench 2.0Source 63.8%Not comparable
BrowseCompSource 77.1%Not comparable
MCP AtlasSource 74.1%Not comparable
Design Arena Agentic Web DevSource 1258Not comparable
BFCL v4Source 49.7%Not comparable
τ²-bench resultsSource 88.1%Not comparable
Coding
BenchmarkInklingLFM2.5-8B-A1BResult
SWE-bench VerifiedSource 77.6%Not comparable
SWE-bench ProSource 54.3%Not comparable
Terminal-Bench 2.0Source 63.8%Not comparable
Terminal-Bench HardSource 4.5%Not comparable
AA-SciCodeSource 7.8%Not comparable
Reasoning
BenchmarkInklingLFM2.5-8B-A1BResult
AA-LCRSource 0.0%Not comparable
CritPtSource 0.0%Not comparable
Knowledge
BenchmarkInklingLFM2.5-8B-A1BResult
GPQASource 87.9%Not comparable
GPQA-DSource 87.9%Not comparable
HLESource 46%Not comparable
HLE w/o toolsSource 30%Not comparable
AA-GPQA DiamondSource 51.3%Not comparable
AA-HLESource 6.9%Not comparable
AA-Omniscience IndexSource -33.3%Not comparable
AA-Omniscience AccuracySource 9.4%Not comparable
AA-Omniscience Hallucination RateSource 47.0%Not comparable
Artificial Analysis Intelligence IndexSource 8.3%Not comparable
MathInkling wins
BenchmarkInklingLFM2.5-8B-A1BResult
AIME26Source 97.1%50.0%Inkling leads
MATH-500Source 88.8%Not comparable
AIME 2025Source 42.5%Not comparable
Multimodal
BenchmarkInklingLFM2.5-8B-A1BResult
MMMU-ProSource 73.5%Not comparable
CharXivSource 82%Not comparable
CharXiv w/o toolsSource 78.1%Not comparable
Inst. FollowingInkling wins
BenchmarkInklingLFM2.5-8B-A1BResult
IFBenchSource 79.8%56.5%Inkling leads
IFEvalSource 91.8%Not comparable
AA-IFBenchSource 55.6%Not comparable
Frequently Asked Questions (3)

Which is better, Inkling or LFM2.5-8B-A1B?

Inkling is ahead on BenchLM's provisional leaderboard, 69 to 37. The biggest single separator in this matchup is AIME26, where the scores are 97.1% and 50.0%.

Which is better for math, Inkling or LFM2.5-8B-A1B?

Inkling has the edge for math in this comparison, averaging 97.1 versus 50. Inside this category, AIME26 is the benchmark that creates the most daylight between them.

Which is better for instruction following, Inkling or LFM2.5-8B-A1B?

Inkling has the edge for instruction following in this comparison, averaging 79.8 versus 68.8. 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.