Gemini 3.1 Pro vs Gemini 3.7 Flash

Model Markets Rankings

Intelligence, Cost, and Efficiency

All rankings →
RankingGemini 3.1 ProGemini 3.7 Flash
IntelligenceHigher is better · MM Intelligence v1.2UnrankedNot in the 22-model eligible cohort#3 of 2287.8 score
CostLower is better · Published-token output estimate#22 of 36$0.161 per LiveBench case#15 of 36$0.085 per LiveBench case
EfficiencyHigher is better · MM Efficiency v1.0UnrankedNot in the 22-model eligible cohort#2 of 2268.1 score

Ranks come from the current complete eligible cohorts. Green highlights appear only when both models are ranked in the same metric. Missing required inputs remain unranked, and the three dimensions are not collapsed into an overall winner.

Benchmark Performance

Available Benchmarks

BenchmarkGemini 3.1 ProGemini 3.7 Flash
LMArena Agent Arenaagent-2026-08-31-011508720696 · outcome_score · leader-3.1396% of row best · score · Gemini 3.1 Pro Preview; 95% CI [-4.00806078, -2.24630473]; sessions 83248; observations 2709356; rank 400.96100% of row best · score · Gemini 3.7 Flash (High); 95% CI [0.05817495, 1.85682345]; sessions 24413; observations 1756405; rank 30
LMArena Text Arenatext-2026-09-01-011508720696 · arena_rating · statistical tie1,480.1099% of row best · rating · gemini-3.1-pro-preview; 95% CI [1476.89767236, 1483.30025658]; votes 102763; rank 111,491.10100% of row best · rating · gemini-3.7-flash-high; 95% CI [1482.94370265, 1499.25525622]; votes 5685; rank 6
LiveBench2026-06-25 · overall · leader81.6698% of row best · percent · gemini-3.1-pro-preview-high · 13,380 output tokens / case83.15100% of row best · percent · gemini-3.7-flash-high · 22,610 output tokens / case
ToneBench2026-08-28-10-task-cd9819ab6e4d · overall_score · leader79.89100% of row best · points · Gemini 3.1 Pro (high thinking) · 10,009 output tokens / case77.9598% of row best · points · Gemini 3.7 Flash (high thinking) · 9,139 output tokens / case
Overall ResultCounted from the protocol-matched rows above · 1 tie1 benchmark win2 benchmark winsOverall lead

Third-party benchmark Only like-for-like primary-publisher results are shown; raw scores, relative scores, configuration, and token spend remain visible.

FieldAt a Glance
Google DeepMind · previewGemini 3.1 ProVerified Aug 29, 2026
Google DeepMind · activeGemini 3.7 FlashVerified Aug 29, 2026

Technical Differences

Side-by-Side Facts

Indexable
FieldGemini 3.1 ProGemini 3.7 Flash
DeveloperGoogle DeepMindGoogle DeepMind
FamilyGemini 3Gemini 3
ModelGemini 3.1 ProGemini 3.7 Flash
VersionGemini 3.1 ProGemini 3.7 Flash
Lifecyclepreviewactive
ReleasedUnknownUnknown
Knowledge cutoffUnknownUnknown
Input modalitiesText, Image, Video, Audio, DocumentText, Image, Video, Audio, Document
Output modalitiesTextText
Context window1,049K1,049K
Total parametersUnknownUnknown
Active parametersUnknownUnknown
LicenseUnknownUnknown
Open weightsNoNo
API availableYesYes
Self-hostableNoNo
Provider accessGoogle AI (Standard), Google Gemini (Standard)Google AI (Standard), Google Gemini (Standard)
Capabilitieschat, generation, reasoning, toolschat, generation, reasoning, tools

13 comparable fields · 3 material differences · Pair passes the primary-source comparison gate

Gemini 3.1 Pro Capabilities

chatgenerationreasoningtools
Input price$2.00
Output price$12.00
Serving providers2
Canonical IDgoogle-deepmind/gemini-3.1-pro-preview

Gemini 3.7 Flash Capabilities

chatgenerationreasoningtools
Input price$0.75
Output price$3.75
Serving providers2
Canonical IDgoogle-deepmind/gemini-3.7-flash

Internal Comparison Graph

Related Comparisons

All text comparisons →
APairBContext
vsfamily variantstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext
vscross-developer peerstext

Primary Evidence

Sources and Freshness

Questions

Gemini 3.1 Pro vs Gemini 3.7 Flash FAQs

Is Gemini 3.1 Pro or Gemini 3.7 Flash better for coding?+

This comparison does not currently contain a protocol-matched coding benchmark for both Gemini 3.1 Pro and Gemini 3.7 Flash, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.

Which is cheaper, Gemini 3.1 Pro or Gemini 3.7 Flash?+

Gemini 3.1 Pro is $2.00 and Gemini 3.7 Flash is $0.75 per million tokens, so Gemini 3.7 Flash is cheaper on this metric. Gemini 3.1 Pro is $12.00 and Gemini 3.7 Flash is $3.75 per million tokens, so Gemini 3.7 Flash is cheaper on this metric.

Which has a larger context window, Gemini 3.1 Pro or Gemini 3.7 Flash?+

Neither model has a larger sourced context window in this comparison. Gemini 3.1 Pro is 1,049K and Gemini 3.7 Flash is 1,049K.

Which performs better in benchmarks, Gemini 3.1 Pro or Gemini 3.7 Flash?+

Gemini 3.7 Flash leads the current overall benchmark count. The result uses 4 protocol-matched benchmarks from 3 publishers; it is not a universal quality score.

Can Gemini 3.1 Pro or Gemini 3.7 Flash be self-hosted?+

Both models have the same recorded self-hosting status: unsupported. Gemini 3.1 Pro is not marked open weight; Gemini 3.7 Flash is not marked open weight.

Can Gemini 3.1 Pro and Gemini 3.7 Flash understand images?+

Gemini 3.1 Pro is documented with image input; Gemini 3.7 Flash is documented with image input. This reflects supported input modalities, not vision quality.

Which can generate longer answers, Gemini 3.1 Pro or Gemini 3.7 Flash?+

Neither has a larger sourced maximum output. Gemini 3.1 Pro is 66K and Gemini 3.7 Flash is 66K.

Do Gemini 3.1 Pro and Gemini 3.7 Flash support reasoning and tool use?+

Gemini 3.1 Pro: reasoning, tool calling, and image input. Gemini 3.7 Flash: reasoning, tool calling, and image input. Feature support does not establish relative quality.

Which is available from more inference providers, Gemini 3.1 Pro or Gemini 3.7 Flash?+

Gemini 3.1 Pro has 2 sourced provider routes; Gemini 3.7 Flash has 2, a tie.

Which offers better value, Gemini 3.1 Pro or Gemini 3.7 Flash?+

There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.

Send Feedback