Skip to main content

Model comparison

Gemini 2.5 Flash vs Gemini 3.1 Flash-Lite

Data verified

Head-to-head evidence from 12 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

48.09/100
Margin
2.7pts
winning →
50.83/100
0 category wins0 category wins

Public leaderboard positions: Gemini 2.5 Flash #130 (Supported); Gemini 3.1 Flash-Lite #111 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. Gemini 2.5 Flash and Gemini 3.1 Flash-Lite share 12 comparable benchmark results. 0 of 8 categories are comparable. 3 results are unique to Gemini 2.5 Flash; 8 to Gemini 3.1 Flash-Lite.

Updated July 20, 2026
Shared results
12
Gemini 2.5 Flash only
3
Gemini 3.1 Flash-Lite only
8
Comparable categories
0 / 8

Benchmark data for Gemini 2.5 Flash and Gemini 3.1 Flash-Lite is coming soon on BenchLM.

Confidence note. This is a partial-evidence comparison with 12 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 2.5 Flash is priced at $0.30 input / $2.50 output per 1M tokens, versus $0.25 input / $1.50 output per 1M tokens for Gemini 3.1 Flash-Lite.

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 2.5 Flash and Gemini 3.1 Flash-Lite
CategoryGemini 2.5 FlashΔGemini 3.1 Flash-Lite
MathGemini 2.5 Flash4.7MarginNo overlapGemini 3.1 Flash-LiteNot measured
MultimodalGemini 2.5 FlashNot measuredMarginNo overlapGemini 3.1 Flash-Lite73.2

Operational comparison

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

MetricGemini 2.5 FlashGemini 3.1 Flash-LiteComparison
Input / output priceUSD per 1M tokensGemini 2.5 Flash$0.3 input / $2.5 outputGemini 3.1 Flash-Lite$0.25 input / $1.5 outputGemini 3.1 Flash-Lite has the lower combined listed price.
Generation speedtokens per secondGemini 2.5 Flash221 tok/sGemini 3.1 Flash-Lite205 tok/sGemini 2.5 Flash has the higher measured throughput.
First-answer latencyseconds to first tokenGemini 2.5 Flash0.50 sGemini 3.1 Flash-Lite7.50 sGemini 2.5 Flash reaches the first token sooner.
Context windowmaximum listed tokensGemini 2.5 Flash1MGemini 3.1 Flash-Lite1MListed context windows are equal.

Benchmark Deep Dive

Agentic
BenchmarkGemini 2.5 FlashGemini 3.1 Flash-LiteResult
τ²-bench resultsSource 14.9%31.3%Gemini 3.1 Flash-Lite leads
AA Agentic IndexSource 6.2%Not comparable
APEX-Agents-AASource 12.2%Not comparable
GDPval-AASource 7.1%Not comparable
GDPval-AASource 642Not comparable
Gert LabsSource 38.46%Not comparable
Coding
BenchmarkGemini 2.5 FlashGemini 3.1 Flash-LiteResult
AA-SciCodeSource 29.1%41.9%Gemini 3.1 Flash-Lite leads
Vibe Code BenchSource 0.00%Not comparable
AA Coding IndexSource 34.7%Not comparable
Reasoning
BenchmarkGemini 2.5 FlashGemini 3.1 Flash-LiteResult
AA-LCRSource 45.9%65.3%Gemini 3.1 Flash-Lite leads
CritPtSource 1.4%1.1%Gemini 2.5 Flash leads
Knowledge
BenchmarkGemini 2.5 FlashGemini 3.1 Flash-LiteResult
Artificial Analysis Intelligence IndexSource 14.1%25.0%Gemini 3.1 Flash-Lite leads
AA-GPQA DiamondSource 68.3%82.2%Gemini 3.1 Flash-Lite leads
AA-HLESource 5.1%16.2%Gemini 3.1 Flash-Lite leads
AA-Omniscience IndexSource -42.0%-15.5%Gemini 3.1 Flash-Lite leads
AA-Omniscience AccuracySource 26.5%36.4%Gemini 3.1 Flash-Lite leads
AA-Omniscience Hallucination RateSource 93.3%81.6%Gemini 3.1 Flash-Lite leads
Math
BenchmarkGemini 2.5 FlashGemini 3.1 Flash-LiteResult
FrontierMath v2 (Tiers 1-3)Source 4.844%Not comparable
FrontierMath v2 (Tier 4)Source 4.167%Not comparable
Multimodal
BenchmarkGemini 2.5 FlashGemini 3.1 Flash-LiteResult
AA-MMMU-ProSource 65.5%75.5%Gemini 3.1 Flash-Lite leads
Design Arena WebsiteSource 1148Not comparable
CharXivSource 73.2%Not comparable
Inst. Following
BenchmarkGemini 2.5 FlashGemini 3.1 Flash-LiteResult
AA-IFBenchSource 39.0%77.2%Gemini 3.1 Flash-Lite leads
Frequently Asked Questions (3)

Can I compare Gemini 2.5 Flash and Gemini 3.1 Flash-Lite 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 2.5 Flash and Gemini 3.1 Flash-Lite today?

Gemini 2.5 Flash: $0.30 input / $2.50 output per 1M tokens Gemini 3.1 Flash-Lite: $0.25 input / $1.50 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 20, 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.