Skip to main content

Model comparison

Composer 2 vs Step 3.7 Flash

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.

61/100
Margin
10.2pts
← winning
50.76/100
1 category wins1 category wins

BenchAlign evidence: Composer 2 not scored; Step 3.7 Flash estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Composer 2 and Step 3.7 Flash share 2 comparable benchmark results. 2 of 8 categories are comparable. 3 results are unique to Composer 2; 28 to Step 3.7 Flash.

Updated July 16, 2026
Shared results
2
Composer 2 only
3
Step 3.7 Flash only
28
Comparable categories
2 / 8

Pick Composer 2 if you want the stronger benchmark profile. Step 3.7 Flash only becomes the better choice if agentic is the priority or you want the cheaper token bill.

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

Composer 2 is clearly ahead on the provisional aggregate, 61 to 57. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Composer 2's sharpest advantage is in coding, where it averages 58 against 56.3. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 61.7% to 59.5%. Step 3.7 Flash does hit back in agentic, so the answer changes if that is the part of the workload you care about most.

Composer 2 is also the more expensive model on tokens at $0.50 input / $2.50 output per 1M tokens, versus $0.20 input / $1.15 output per 1M tokens for Step 3.7 Flash. That is roughly 2.2x on output cost alone. Step 3.7 Flash gives you the larger context window at 256K, compared with 200K for Composer 2.

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 Composer 2 and Step 3.7 Flash
CategoryComposer 2ΔStep 3.7 Flash
AgenticComposer 261.7Margin 4.7Step 3.7 Flash66.4
CodingComposer 258.0Margin 1.7Step 3.7 Flash56.3

Decisive benchmark drivers

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

More
A · Composer 2B · Step 3.7 Flash
  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 61.7%B 59.5%
    Winner: Composer 2Δ 2.2
    Terminal-Bench 2.0: Composer 2 scored 61.7%; Step 3.7 Flash scored 59.5%. Composer 2 wins this benchmark.

Operational comparison

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

MetricComposer 2Step 3.7 FlashComparison
Input / output priceUSD per 1M tokensComposer 2$0.5 input / $2.5 outputStep 3.7 Flash$0.2 input / $1.15 outputStep 3.7 Flash has the lower combined listed price.
Generation speedtokens per secondComposer 2Not availableStep 3.7 FlashNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenComposer 2Not availableStep 3.7 FlashNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensComposer 2200KStep 3.7 Flash256KStep 3.7 Flash lists the larger context window.

Benchmark Deep Dive

AgenticStep 3.7 Flash wins
BenchmarkComposer 2Step 3.7 FlashResult
Terminal-Bench 2.0Source 61.7%59.5%Composer 2 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
CodingComposer 2 wins
BenchmarkComposer 2Step 3.7 FlashResult
SWE MultilingualSource 73.7%Not comparable
SWE-RebenchSource 58%Not comparable
React Native EvalsSource 96.1%Not comparable
Terminal-Bench 2.0Source 61.7%59.5%Composer 2 leads
SWE-bench ProSource 56.3%Not comparable
AA Coding IndexSource 39.6%Not comparable
Terminal-Bench HardSource 35.6%Not comparable
AA-SciCodeSource 40.0%Not comparable
Reasoning
BenchmarkComposer 2Step 3.7 FlashResult
AA-LCRSource 63.7%Not comparable
CritPtSource 2.3%Not comparable
Knowledge
BenchmarkComposer 2Step 3.7 FlashResult
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
Multimodal
BenchmarkComposer 2Step 3.7 FlashResult
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
BenchmarkComposer 2Step 3.7 FlashResult
AA-IFBenchSource 67.3%Not comparable
Frequently Asked Questions (3)

Which is better, Composer 2 or Step 3.7 Flash?

Composer 2 is ahead on BenchLM's provisional leaderboard, 61 to 57. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 61.7% and 59.5%.

Which is better for coding, Composer 2 or Step 3.7 Flash?

Composer 2 has the edge for coding in this comparison, averaging 58 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, Composer 2 or Step 3.7 Flash?

Step 3.7 Flash has the edge for agentic tasks in this comparison, averaging 66.4 versus 61.7. Inside this category, Terminal-Bench 2.0 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.