Skip to main content

Model comparison

Inkling vs Step 3.7 Flash

Data verified

Head-to-head evidence from 4 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

Thinking Machines Lab
69/100
Margin
18.2pts
← winning
50.76/100
2 category wins0 category wins

Verified leaderboard positions: Inkling #17; Step 3.7 Flash unranked

BenchAlign evidence: Inkling not scored; Step 3.7 Flash estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Inkling and Step 3.7 Flash share 4 comparable benchmark results. 2 of 8 categories are comparable. 12 results are unique to Inkling; 26 to Step 3.7 Flash.

Updated July 15, 2026
Shared results
4
Inkling only
12
Step 3.7 Flash only
26
Comparable categories
2 / 8

Pick Inkling if you want the stronger benchmark profile. Step 3.7 Flash 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 4 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 57. 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 coding, where it averages 68.6 against 56.3. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 63.8% to 59.5%.

Inkling is also the more expensive model on tokens at $1.87 input / $4.68 output per 1M tokens, versus $0.20 input / $1.15 output per 1M tokens for Step 3.7 Flash. That is roughly 4.1x on output cost alone. Step 3.7 Flash 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 Step 3.7 Flash.

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 Step 3.7 Flash
CategoryInklingΔStep 3.7 Flash
CodingInkling68.6Margin 12.3Step 3.7 Flash56.3
AgenticInkling69.4Margin 3.0Step 3.7 Flash66.4
KnowledgeInkling51.7MarginNo overlapStep 3.7 FlashNot measured
MathInkling97.1MarginNo overlapStep 3.7 FlashNot measured
MultimodalInkling76.5MarginNo overlapStep 3.7 FlashNot measured
Inst. FollowingInkling79.8MarginNo overlapStep 3.7 FlashNot measured

Decisive benchmark drivers

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

More
A · InklingB · Step 3.7 Flash
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 63.8%B 59.5%
    Winner: InklingΔ 4.3
    Terminal-Bench 2.0: Inkling scored 63.8%; Step 3.7 Flash scored 59.5%. Inkling wins this benchmark.
  2. SWE-bench Pro

    Coding
    Source ↗
    A 54.3%B 56.3%
    Winner: Step 3.7 FlashΔ 2
    SWE-bench Pro: Inkling scored 54.3%; Step 3.7 Flash scored 56.3%. Step 3.7 Flash wins this benchmark.
  3. BrowseComp

    Agentic
    Source ↗
    A 77.1%B 75.8%
    Winner: InklingΔ 1.3
    BrowseComp: Inkling scored 77.1%; Step 3.7 Flash scored 75.8%. Inkling wins this benchmark.

Operational comparison

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

MetricInklingStep 3.7 FlashComparison
Input / output priceUSD per 1M tokensInkling$1.87 input / $4.68 outputStep 3.7 Flash$0.2 input / $1.15 outputStep 3.7 Flash has the lower combined listed price.
Generation speedtokens per secondInklingNot availableStep 3.7 FlashNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenInklingNot availableStep 3.7 FlashNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensInkling1MStep 3.7 Flash256KInkling lists the larger context window.

Benchmark Deep Dive

AgenticInkling wins
BenchmarkInklingStep 3.7 FlashResult
Terminal-Bench 2.0Source 63.8%59.5%Inkling leads
BrowseCompSource 77.1%75.8%Inkling leads
MCP AtlasSource 74.1%Not comparable
Design Arena Agentic Web DevSource 1258Not comparable
DeepSearchQASource 92.8%Not comparable
GDPval-AASource 25.9%Not comparable
ToolathlonSource 49.5%Not comparable
Claw-EvalSource 67.1%Not comparable
HLE w/ toolsSource 47.2%Not comparable
Gert LabsSource 51.57%Not comparable
AA Agentic IndexSource 21.5%Not comparable
τ²-bench resultsSource 98.5%Not comparable
GDPval-AASource 1017Not comparable
APEX-Agents-AASource 14.8%Not comparable
CodingInkling wins
BenchmarkInklingStep 3.7 FlashResult
SWE-bench VerifiedSource 77.6%Not comparable
SWE-bench ProSource 54.3%56.3%Step 3.7 Flash leads
Terminal-Bench 2.0Source 63.8%59.5%Inkling leads
AA Coding IndexSource 39.6%Not comparable
Terminal-Bench HardSource 35.6%Not comparable
AA-SciCodeSource 40.0%Not comparable
Reasoning
BenchmarkInklingStep 3.7 FlashResult
AA-LCRSource 63.7%Not comparable
CritPtSource 2.3%Not comparable
Knowledge
BenchmarkInklingStep 3.7 FlashResult
GPQASource 87.9%Not comparable
GPQA-DSource 87.9%Not comparable
HLESource 46%Not comparable
HLE w/o toolsSource 30%Not comparable
Artificial Analysis Intelligence IndexSource 30.3%Not comparable
AA-GPQA DiamondSource 80.9%Not comparable
AA-HLESource 19.9%Not comparable
AA-Omniscience IndexSource -37.5%Not comparable
AA-Omniscience AccuracySource 25.4%Not comparable
AA-Omniscience Hallucination RateSource 84.4%Not comparable
Math
BenchmarkInklingStep 3.7 FlashResult
AIME26Source 97.1%Not comparable
Multimodal
BenchmarkInklingStep 3.7 FlashResult
MMMU-ProSource 73.5%Not comparable
CharXivSource 82%Not comparable
CharXiv w/o toolsSource 78.1%Not comparable
SimpleVQASource 79.2%Not comparable
V*Source 95.3%Not comparable
AA-MMMU-ProSource 75.3%Not comparable
Design Arena WebsiteSource 1218Not comparable
Inst. Following
BenchmarkInklingStep 3.7 FlashResult
IFBenchSource 79.8%Not comparable
AA-IFBenchSource 67.3%Not comparable
Frequently Asked Questions (3)

Which is better, Inkling or Step 3.7 Flash?

Inkling is ahead on BenchLM's provisional leaderboard, 69 to 57. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 63.8% and 59.5%.

Which is better for coding, Inkling or Step 3.7 Flash?

Inkling has the edge for coding in this comparison, averaging 68.6 versus 56.3. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, Inkling or Step 3.7 Flash?

Inkling has the edge for agentic tasks in this comparison, averaging 69.4 versus 66.4. Inside this category, Terminal-Bench 2.0 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.