Skip to main content
BenchLM
Advertise

Model comparison

Step 3.7 Flash vs ZAYA1-74B-Preview

Data verified

Head-to-head evidence from 0 shared benchmark results across 0 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

No sourced benchmark result is currently shared by both models. This page therefore compares only the available metadata, pricing, and runtime rows; it does not name a quality winner.
50.87/100
No comparison
N/A
1 category wins0 category wins

Public leaderboard positions: Step 3.7 Flash #110 (Estimated); ZAYA1-74B-Preview unranked (Not scored). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Step 3.7 Flash and ZAYA1-74B-Preview share 0 comparable benchmark results. 1 of 8 categories are comparable. 29 results are unique to Step 3.7 Flash; 7 to ZAYA1-74B-Preview.

Updated July 21, 2026
Shared results
0
Step 3.7 Flash only
29
ZAYA1-74B-Preview only
7
Comparable categories
1 / 8

Treat this as a split decision. Step 3.7 Flash makes more sense if coding is the priority; ZAYA1-74B-Preview is the better fit if you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 0 shared benchmark results across 0 evidence categories; 1 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 and ZAYA1-74B-Preview 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.

Step 3.7 Flash is also the more expensive model on tokens at $0.20 input / $1.15 output per 1M tokens, versus $0.00 input / $0.00 output per 1M tokens for ZAYA1-74B-Preview. That is roughly Infinityx on output cost alone.

Operational comparison

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

MetricStep 3.7 FlashZAYA1-74B-PreviewComparison
Input / output priceUSD per 1M tokensStep 3.7 Flash$0.2 input / $1.15 outputZAYA1-74B-Preview$0 input / $0 outputZAYA1-74B-Preview has the lower combined listed price.
Generation speedtokens per secondStep 3.7 FlashNot availableZAYA1-74B-PreviewNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenStep 3.7 FlashNot availableZAYA1-74B-PreviewNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensStep 3.7 Flash256KZAYA1-74B-Preview256KListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkStep 3.7 FlashZAYA1-74B-PreviewResult
Terminal-Bench 2.0Source 59.5%—Not comparable
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 1017—Not comparable
APEX-Agents-AASource 14.8%—Not comparable
τ²-bench AirlineSource —56.1%Not comparable
CodingStep 3.7 Flash wins
BenchmarkStep 3.7 FlashZAYA1-74B-PreviewResult
SWE-bench ProSource 56.3%—Not comparable
Terminal-Bench 2.0Source 59.5%—Not comparable
AA Coding IndexSource 39.6%—Not comparable
AA-SciCodeSource 40.0%—Not comparable
LiveCodeBench v6Source —65.7%Not comparable
SWE-bench VerifiedSource —53.2%Not comparable
Reasoning
BenchmarkStep 3.7 FlashZAYA1-74B-PreviewResult
AA-LCRSource 63.7%—Not comparable
CritPtSource 2.3%—Not comparable
Knowledge
BenchmarkStep 3.7 FlashZAYA1-74B-PreviewResult
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
MMLU-ProSource —68.1%Not comparable
GPQASource —57.3%Not comparable
GPQA-DSource —57.3%Not comparable
Math
BenchmarkStep 3.7 FlashZAYA1-74B-PreviewResult
AIME26Source —76.4%Not comparable
Multimodal
BenchmarkStep 3.7 FlashZAYA1-74B-PreviewResult
SimpleVQASource 79.2%—Not comparable
V*Source 95.3%—Not comparable
AA-MMMU-ProSource 75.3%—Not comparable
Design Arena WebsiteSource 1211—Not comparable
Inst. Following
BenchmarkStep 3.7 FlashZAYA1-74B-PreviewResult
AA-IFBenchSource 67.3%—Not comparable
Frequently Asked Questions (2)

Which is better, Step 3.7 Flash or ZAYA1-74B-Preview?

Step 3.7 Flash and ZAYA1-74B-Preview 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, Step 3.7 Flash or ZAYA1-74B-Preview?

Step 3.7 Flash has the edge for coding in this comparison, averaging 56.3 versus 53.2. ZAYA1-74B-Preview stays close enough that the answer can still flip depending on your workload.

Related Comparisons

Explore More

StepFun Compare Pricing Methodology Find Your Best LLM Overall Rankings
Last updated: July 21, 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.