Skip to main content

Model comparison

Gemini 3 Pro vs Step 3.7 Flash

Data verified

Head-to-head evidence from 15 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

67.67/100
Margin
16.9pts
← winning
50.76/100
0 category wins0 category wins

BenchAlign evidence: Gemini 3 Pro supported; Step 3.7 Flash estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Gemini 3 Pro and Step 3.7 Flash share 15 comparable benchmark results. 0 of 8 categories are comparable. 13 results are unique to Gemini 3 Pro; 15 to Step 3.7 Flash.

Updated July 16, 2026
Shared results
15
Gemini 3 Pro only
13
Step 3.7 Flash only
15
Comparable categories
0 / 8

Benchmark data for Gemini 3 Pro and Step 3.7 Flash is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 15 shared benchmark results across 6 evidence categories; 0 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

BenchLM has partial data for these models, but not enough overlapping benchmark coverage to produce a fair score-level comparison yet.

Gemini 3 Pro is priced at $2.00 input / $12.00 output per 1M tokens, versus $0.20 input / $1.15 output per 1M tokens for Step 3.7 Flash. Gemini 3 Pro has the larger context window at 2M, 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 Gemini 3 Pro and Step 3.7 Flash
CategoryGemini 3 ProΔStep 3.7 Flash
AgenticGemini 3 ProNot measuredMarginNo overlapStep 3.7 Flash66.4
CodingGemini 3 ProNot measuredMarginNo overlapStep 3.7 Flash56.3
ReasoningGemini 3 Pro31.1MarginNo overlapStep 3.7 FlashNot measured
MathGemini 3 Pro32.9MarginNo overlapStep 3.7 FlashNot measured
MultimodalGemini 3 Pro81.1MarginNo overlapStep 3.7 FlashNot measured

Operational comparison

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

MetricGemini 3 ProStep 3.7 FlashComparison
Input / output priceUSD per 1M tokensGemini 3 Pro$2 input / $12 outputStep 3.7 Flash$0.2 input / $1.15 outputStep 3.7 Flash has the lower combined listed price.
Generation speedtokens per secondGemini 3 Pro109 tok/sStep 3.7 FlashNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGemini 3 Pro32.65 sStep 3.7 FlashNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGemini 3 Pro2MStep 3.7 Flash256KGemini 3 Pro lists the larger context window.

Benchmark Deep Dive

Agentic
BenchmarkGemini 3 ProStep 3.7 FlashResult
τ²-bench resultsSource 87.1%98.5%Step 3.7 Flash leads
Gert LabsSource 63.23%51.57%Gemini 3 Pro leads
JobBenchSource 11.4%Not comparable
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
AA Agentic IndexSource 21.5%Not comparable
GDPval-AASource 1017Not comparable
APEX-Agents-AASource 14.8%Not comparable
Coding
BenchmarkGemini 3 ProStep 3.7 FlashResult
Vibe Code BenchSource 14.30%Not comparable
Terminal-Bench HardSource 41.7%35.6%Gemini 3 Pro leads
AA-SciCodeSource 56.1%40.0%Gemini 3 Pro leads
AA LiveCodeBenchSource 91.7%Not comparable
SWE-bench ProSource 56.3%Not comparable
Terminal-Bench 2.0Source 59.5%Not comparable
AA Coding IndexSource 39.6%Not comparable
Reasoning
BenchmarkGemini 3 ProStep 3.7 FlashResult
ARC-AGI-2Source 31.1%Not comparable
AA-LCRSource 70.7%63.7%Gemini 3 Pro leads
CritPtSource 9.1%2.3%Gemini 3 Pro leads
Knowledge
BenchmarkGemini 3 ProStep 3.7 FlashResult
Artificial Analysis Intelligence IndexSource 39.5%30.3%Gemini 3 Pro leads
AA-GPQA DiamondSource 90.8%80.9%Gemini 3 Pro leads
AA-HLESource 37.2%19.9%Gemini 3 Pro leads
AA-Omniscience IndexSource 15.8%-37.5%Gemini 3 Pro leads
AA-Omniscience AccuracySource 55.9%25.4%Gemini 3 Pro leads
AA-Omniscience Hallucination RateSource 90.9%84.4%Step 3.7 Flash leads
AA MMLU-ProSource 89.8%Not comparable
Math
BenchmarkGemini 3 ProStep 3.7 FlashResult
FrontierMath v2 (Tiers 1-3)Source 37.600%Not comparable
FrontierMath v2 (Tier 4)Source 18.750%Not comparable
Multilingual
BenchmarkGemini 3 ProStep 3.7 FlashResult
AA Global-MMLU-LiteSource 92.2%Not comparable
Multimodal
BenchmarkGemini 3 ProStep 3.7 FlashResult
MMMU-ProSource 81%Not comparable
MathVisionSource 86.6%Not comparable
VideoMMMUSource 87.6%Not comparable
ScreenSpot ProSource 72.7%Not comparable
CharXivSource 81.4%Not comparable
V*Source 88.0%95.3%Step 3.7 Flash leads
AA-MMMU-ProSource 80.2%75.3%Gemini 3 Pro leads
SimpleVQASource 79.2%Not comparable
Design Arena WebsiteSource 1218Not comparable
Inst. Following
BenchmarkGemini 3 ProStep 3.7 FlashResult
AA-IFBenchSource 70.4%67.3%Gemini 3 Pro leads
Frequently Asked Questions (3)

Can I compare Gemini 3 Pro and Step 3.7 Flash on BenchLM yet?

Not fully yet. BenchLM is tracking both models, but the sourced benchmark breakdown for this comparison is still coming soon.

Why does this comparison show “coming soon”?

BenchLM only shows category winners and benchmark-level calls when we have sourced results that can be compared fairly. For these models, the public benchmark coverage is not complete enough yet.

What data is available for Gemini 3 Pro and Step 3.7 Flash today?

Gemini 3 Pro: $2.00 input / $12.00 output per 1M tokens Step 3.7 Flash: $0.20 input / $1.15 output per 1M tokens Both model pages still include creator, context window, reasoning mode, and other metadata while benchmark coverage fills in.

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.