Skip to main content

Model comparison

MiniMax M2.7 vs Step 3.7 Flash

Data verified

Head-to-head evidence from 23 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

64.03/100
Margin
13.3pts
← winning
50.76/100
0 category wins2 category wins

BenchAlign evidence: MiniMax M2.7 supported; Step 3.7 Flash estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. MiniMax M2.7 and Step 3.7 Flash share 23 comparable benchmark results. 2 of 8 categories are comparable. 14 results are unique to MiniMax M2.7; 7 to Step 3.7 Flash.

Updated July 16, 2026
Shared results
23
MiniMax M2.7 only
14
Step 3.7 Flash only
7
Comparable categories
2 / 8

Pick Step 3.7 Flash if you want the stronger benchmark profile. MiniMax M2.7 only becomes the better choice if you would rather avoid the extra latency and token burn of a reasoning model.

Confidence note. This is a partial-evidence comparison with 23 shared benchmark results across 6 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

Step 3.7 Flash is clearly ahead on the provisional aggregate, 57 to 52. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Step 3.7 Flash's sharpest advantage is in agentic, where it averages 66.4 against 57. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 57% to 59.5%.

MiniMax M2.7 is also the more expensive model on tokens at $0.30 input / $1.20 output per 1M tokens, versus $0.20 input / $1.15 output per 1M tokens for Step 3.7 Flash. Step 3.7 Flash is the reasoning model in the pair, while MiniMax M2.7 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. Step 3.7 Flash gives you the larger context window at 256K, compared with 200K for MiniMax M2.7.

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 MiniMax M2.7 and Step 3.7 Flash
CategoryMiniMax M2.7ΔStep 3.7 Flash
AgenticMiniMax M2.757.0Margin 9.4Step 3.7 Flash66.4
CodingMiniMax M2.753.3Margin 3.0Step 3.7 Flash56.3

Decisive benchmark drivers

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

More
A · MiniMax M2.7B · Step 3.7 Flash
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 57%B 59.5%
    Winner: Step 3.7 FlashΔ 2.5
    Terminal-Bench 2.0: MiniMax M2.7 scored 57%; Step 3.7 Flash scored 59.5%. Step 3.7 Flash wins this benchmark.
  2. SWE-bench Pro

    Coding
    Source ↗
    A 56.2%B 56.3%
    Winner: Step 3.7 FlashΔ 0.1
    SWE-bench Pro: MiniMax M2.7 scored 56.2%; 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.

MetricMiniMax M2.7Step 3.7 FlashComparison
Input / output priceUSD per 1M tokensMiniMax M2.7$0.3 input / $1.2 outputStep 3.7 Flash$0.2 input / $1.15 outputStep 3.7 Flash has the lower combined listed price.
Generation speedtokens per secondMiniMax M2.745 tok/sStep 3.7 FlashNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenMiniMax M2.72.53 sStep 3.7 FlashNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensMiniMax M2.7200KStep 3.7 Flash256KStep 3.7 Flash lists the larger context window.

Benchmark Deep Dive

AgenticStep 3.7 Flash wins
BenchmarkMiniMax M2.7Step 3.7 FlashResult
Terminal-Bench 2.0Source 57%59.5%Step 3.7 Flash leads
τ²-bench resultsSource 84.8%98.5%Step 3.7 Flash leads
ToolathlonSource 46.3%49.5%Step 3.7 Flash leads
MLE-Bench LiteSource 66.6%Not comparable
MM-ClawBenchSource 62.7%Not comparable
Claw-EvalSource 48.7%67.1%Step 3.7 Flash leads
AA Agentic IndexSource 25.6%21.5%MiniMax M2.7 leads
APEX-Agents-AASource 10.6%14.8%Step 3.7 Flash leads
GDPval-AASource 32.9%25.9%MiniMax M2.7 leads
GDPval-AASource 11581017MiniMax M2.7 leads
Gert LabsSource 40.40%51.57%Step 3.7 Flash leads
BrowseCompSource 75.8%Not comparable
DeepSearchQASource 92.8%Not comparable
HLE w/ toolsSource 47.2%Not comparable
CodingStep 3.7 Flash wins
BenchmarkMiniMax M2.7Step 3.7 FlashResult
SWE-bench Verified*Source 75.4%Not comparable
SWE-bench ProSource 56.2%56.3%Step 3.7 Flash leads
SWE-RebenchSource 51.9%Not comparable
SWE MultilingualSource 76.5%Not comparable
Multi-SWE BenchSource 52.7%Not comparable
VIBE-ProSource 55.6%Not comparable
NL2RepoSource 39.8%Not comparable
Vibe Code BenchSource 27.04%Not comparable
React Native EvalsSource 71.4%Not comparable
AA Coding IndexSource 52.6%39.6%MiniMax M2.7 leads
Terminal-Bench HardSource 39.4%35.6%MiniMax M2.7 leads
AA-SciCodeSource 47.0%40.0%MiniMax M2.7 leads
Terminal-Bench 2.0Source 59.5%Not comparable
Reasoning
BenchmarkMiniMax M2.7Step 3.7 FlashResult
AA-LCRSource 68.7%63.7%MiniMax M2.7 leads
CritPtSource 0.6%2.3%Step 3.7 Flash leads
Knowledge
BenchmarkMiniMax M2.7Step 3.7 FlashResult
GPQA-DSource 87.0%Not comparable
MMLU-Pro (Arcee)Source 80.8%Not comparable
Artificial Analysis Intelligence IndexSource 38.1%30.3%MiniMax M2.7 leads
AA-GPQA DiamondSource 87.4%80.9%MiniMax M2.7 leads
AA-HLESource 28.1%19.9%MiniMax M2.7 leads
AA-Omniscience IndexSource 0.7%-37.5%MiniMax M2.7 leads
AA-Omniscience AccuracySource 26.1%25.4%MiniMax M2.7 leads
AA-Omniscience Hallucination RateSource 34.4%84.4%MiniMax M2.7 leads
Math
BenchmarkMiniMax M2.7Step 3.7 FlashResult
AIME25 (Arcee)Source 80.0%Not comparable
Multimodal
BenchmarkMiniMax M2.7Step 3.7 FlashResult
GDPval-AASource 1495Not comparable
Design Arena WebsiteSource 12791218MiniMax M2.7 leads
SimpleVQASource 79.2%Not comparable
V*Source 95.3%Not comparable
AA-MMMU-ProSource 75.3%Not comparable
Inst. Following
BenchmarkMiniMax M2.7Step 3.7 FlashResult
AA-IFBenchSource 75.7%67.3%MiniMax M2.7 leads
Frequently Asked Questions (3)

Which is better, MiniMax M2.7 or Step 3.7 Flash?

Step 3.7 Flash is ahead on BenchLM's provisional leaderboard, 57 to 52. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 57% and 59.5%.

Which is better for coding, MiniMax M2.7 or Step 3.7 Flash?

Step 3.7 Flash has the edge for coding in this comparison, averaging 56.3 versus 53.3. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, MiniMax M2.7 or Step 3.7 Flash?

Step 3.7 Flash has the edge for agentic tasks in this comparison, averaging 66.4 versus 57. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 16, 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.