Skip to main content

Model comparison

MAI-Thinking-1 vs Step 3.7 Flash

Data verified

Head-to-head evidence from 3 shared benchmark results across 2 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

N/A
No comparison
50.87/100
1 category wins1 category wins

Public leaderboard positions: MAI-Thinking-1 unranked (Not scored); Step 3.7 Flash #110 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MAI-Thinking-1 and Step 3.7 Flash share 3 comparable benchmark results. 2 of 8 categories are comparable. 10 results are unique to MAI-Thinking-1; 26 to Step 3.7 Flash.

Updated July 23, 2026
Shared results
3
MAI-Thinking-1 only
10
Step 3.7 Flash only
26
Comparable categories
2 / 8

Treat this as a split decision. MAI-Thinking-1 makes more sense if coding is the priority; Step 3.7 Flash is the better fit if agentic is the priority.

Confidence note. This is a partial-evidence comparison with 3 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

MAI-Thinking-1 and Step 3.7 Flash finish on the same BenchAlign overall score, so this is less about a single winner and more about where the edge shows up. The BenchAlign headline says tie; the benchmark table is where the real choice happens.

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 MAI-Thinking-1 and Step 3.7 Flash
CategoryMAI-Thinking-1ΔStep 3.7 Flash
AgenticMAI-Thinking-146.0Margin 20.4Step 3.7 Flash66.4
CodingMAI-Thinking-165.5Margin 9.2Step 3.7 Flash56.3
KnowledgeMAI-Thinking-172.5MarginNo overlapStep 3.7 FlashNot measured
MathMAI-Thinking-189.7MarginNo overlapStep 3.7 FlashNot measured
Inst. FollowingMAI-Thinking-185.0MarginNo overlapStep 3.7 FlashNot measured

Decisive benchmark drivers

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

More
A · MAI-Thinking-1B · Step 3.7 Flash
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 46%B 59.5%
    Winner: Step 3.7 FlashΔ 13.5
    Terminal-Bench 2.0: MAI-Thinking-1 scored 46%; Step 3.7 Flash scored 59.5%. Step 3.7 Flash wins this benchmark.
  2. SWE-bench Pro

    Coding
    Source ↗
    A 52.8%B 56.3%
    Winner: Step 3.7 FlashΔ 3.5
    SWE-bench Pro: MAI-Thinking-1 scored 52.8%; Step 3.7 Flash scored 56.3%. Step 3.7 Flash wins this benchmark.

Operational comparison

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

MetricMAI-Thinking-1Step 3.7 FlashComparison
Input / output priceUSD per 1M tokensMAI-Thinking-1Not availableStep 3.7 Flash$0.2 input / $1.15 outputA complete price comparison is not available.
Generation speedtokens per secondMAI-Thinking-1Not availableStep 3.7 FlashNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMAI-Thinking-1Not availableStep 3.7 FlashNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMAI-Thinking-1256KStep 3.7 Flash256KListed context windows are equal.

Benchmark Deep Dive

AgenticStep 3.7 Flash wins
BenchmarkMAI-Thinking-1Step 3.7 FlashResult
Terminal-Bench 2.0Source 46%59.5%Step 3.7 Flash leads
BrowseCompSource 75.8%Not 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
CodingMAI-Thinking-1 wins
BenchmarkMAI-Thinking-1Step 3.7 FlashResult
SWE-bench VerifiedSource 73.5%Not comparable
SWE-bench ProSource 52.8%56.3%Step 3.7 Flash leads
Terminal-Bench 2.0Source 46.0%59.5%Step 3.7 Flash leads
AA Coding IndexSource 39.6%Not comparable
AA-SciCodeSource 40.0%Not comparable
Reasoning
BenchmarkMAI-Thinking-1Step 3.7 FlashResult
Graphwalks BFS 128KSource 90%Not comparable
AA-LCRSource 63.7%Not comparable
CritPtSource 2.3%Not comparable
Knowledge
BenchmarkMAI-Thinking-1Step 3.7 FlashResult
GPQASource 84.2%Not comparable
GPQA-DSource 84.2%Not comparable
MMLU-ProSource 85%Not comparable
SimpleQASource 31%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
BenchmarkMAI-Thinking-1Step 3.7 FlashResult
AIME 2025Source 97%Not comparable
AIME26Source 94.5%Not comparable
HMMT Feb 2026Source 84.9%Not comparable
Multimodal
BenchmarkMAI-Thinking-1Step 3.7 FlashResult
SimpleVQASource 79.2%Not comparable
V*Source 95.3%Not comparable
AA-MMMU-ProSource 75.3%Not comparable
Design Arena WebsiteSource 1211Not comparable
Inst. Following
BenchmarkMAI-Thinking-1Step 3.7 FlashResult
IFBenchSource 85%Not comparable
AA-IFBenchSource 67.3%Not comparable
Frequently Asked Questions (3)

Which is better, MAI-Thinking-1 or Step 3.7 Flash?

MAI-Thinking-1 and Step 3.7 Flash are tied on the BenchAlign overall score, so the right pick depends on which category matters most for your use case.

Which is better for coding, MAI-Thinking-1 or Step 3.7 Flash?

MAI-Thinking-1 has the edge for coding in this comparison, averaging 65.5 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, MAI-Thinking-1 or Step 3.7 Flash?

Step 3.7 Flash has the edge for agentic tasks in this comparison, averaging 66.4 versus 46. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.