Noometry

Model comparison

Gemini 3.1 Pro Preview vs Gemini 3.8 Flash

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 56.7 on the Noometry Index.

Last verified . 45 shared benchmarks.

Gemini 3.1 Pro Preview Google

56.7

Rank #23 Confirmed

Gemini 3.8 Flash Google

61.8

Rank #11 Confirmed

Summary

  • They share 45 benchmarks with published results for both. Gemini 3.1 Pro Preview scores higher in 1 category and Gemini 3.8 Flash in 9 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in coding, where Gemini 3.8 Flash leads 59.2 to 42.5.
  • The biggest single-benchmark swing is DeepSWE: 11.7% for Gemini 3.1 Pro Preview and 73.8% for Gemini 3.8 Flash.
  • Gemini 3.8 Flash is cheaper at $0.75 / $3.75 per million input/output tokens, against $2 / $12 for Gemini 3.1 Pro Preview.

Side by side

Gemini 3.1 Pro PreviewGemini 3.8 Flash
ProviderGoogleGoogle
Noometry Index56.761.8
Released2026-02-192026-09-02
WeightsProprietaryProprietary
Context window1.05M1.05M
Max output66K66K
Input $ / M tokens$2$0.75
Output $ / M tokens$12$3.75
Results tracked7150

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Gemini 3.8 Flash leads

Gemini 3.1 Pro Preview: 42.5 (#99), Gemini 3.8 Flash: 59.2 (#15)

BenchmarkGemini 3.1 Pro PreviewGemini 3.8 Flash
DeepSWE11.7%73.8%
LMArena WebDev14471584
SciCode58.9%56.6%
WeirdML72.1%84.8%
LMArena Coding14841510
ALE-Bench1,1611,270
SWE-bench Verified75.6%—
FrontierCode—41.2%
CursorBench—39.6%
FrontierSWE—19.6%
GSO22.6%—
MirrorCode8.9%—
AlgoTune2.02—

Agentic & Tool Use Gemini 3.8 Flash leads

Gemini 3.1 Pro Preview: 37.7 (#34), Gemini 3.8 Flash: 41.8 (#21)

BenchmarkGemini 3.1 Pro PreviewGemini 3.8 Flash
APEX-Agents35.3%64.3%
GDP.pdf17%23.4%
Vending-Bench 23,7745,094
Terminal-Bench80.2%—
Remote Labor Index—5.8%
τ²-bench Banking26%—
DeepResearch Bench47.8%—
PostTrainBench22%—
BALROG57%—
ExploitBench26.1%—
GBAEval0.8%—
LMArena Search1211—
METR Time Horizons77%—

Reasoning Gemini 3.8 Flash leads

Gemini 3.1 Pro Preview: 71.7 (#12), Gemini 3.8 Flash: 76.9 (#5)

BenchmarkGemini 3.1 Pro PreviewGemini 3.8 Flash
ARC-AGI-277.1%89.2%
NYT Connections (extended)97.4%97.4%
ARC-AGI-198%98.5%
CritPt17.7%18.3%
Chess Puzzles55%61%
LMArena Hard Prompts14851508
Mystery Game Puzzles34%47%
DTBench97.1%95.7%
LMCA53.8%52.9%
Epoch Capabilities Index154.77156.71
SimpleBench79.6%—
EnigmaEval36.8%—
Thematic Generalization79.4%—
EBR-Bench14.3%—
Surface Evolver Bench—76.9%
ForecastBench59—

Math Gemini 3.8 Flash leads

Gemini 3.1 Pro Preview: 62.1 (#34), Gemini 3.8 Flash: 65.3 (#28)

BenchmarkGemini 3.1 Pro PreviewGemini 3.8 Flash
FrontierMath (Tiers 1-3)59.6%68.4%
FrontierMath Tier 426.8%22%
OTIS Mock AIME 2024-202595.6%98.9%
ProofBench26%48%
LMArena Math14851528
MathArena Final-Answer Competitions86.5%—
FrontierMath (Feb 2025 set)36.9%—
FrontierMath Tier 4 (v1)16.7%—

Knowledge Gemini 3.8 Flash leads

Gemini 3.1 Pro Preview: 71.8 (#3), Gemini 3.8 Flash: 74.8 (#2)

BenchmarkGemini 3.1 Pro PreviewGemini 3.8 Flash
GPQA Diamond94.4%95.4%
Humanity's Last Exam46.4%44.5%
SimpleQA Verified73.5%69.7%
LMArena Expert14851524
Vectara Hallucination Rate10.4%—

Multimodal Gemini 3.8 Flash leads

Gemini 3.1 Pro Preview: 37.9 (#69), Gemini 3.8 Flash: 40.7 (#45)

BenchmarkGemini 3.1 Pro PreviewGemini 3.8 Flash
LMArena Vision12961314
Blueprint-Bench 226.5%38.6%
Furniture Assembly26.7%31.7%
LMArena Document1444—

Multilingual Too close to call

Gemini 3.1 Pro Preview: 57.0 (#12), Gemini 3.8 Flash: 58.0 (#5)

BenchmarkGemini 3.1 Pro PreviewGemini 3.8 Flash
LMArena Non-English14771491
LMArena Chinese15291554
LMArena French14871498
LMArena German14911493
LMArena Japanese14931502
LMArena Korean14551459
LMArena Russian14981515
LMArena Spanish14791485

Instruction Following Gemini 3.8 Flash leads

Gemini 3.1 Pro Preview: 77.0 (#32), Gemini 3.8 Flash: 78.0 (#13)

BenchmarkGemini 3.1 Pro PreviewGemini 3.8 Flash
LMArena Instruction Following14661490

Long Context Gemini 3.1 Pro Preview leads

Gemini 3.1 Pro Preview: 47.4 (#18), Gemini 3.8 Flash: 46.3 (#24)

BenchmarkGemini 3.1 Pro PreviewGemini 3.8 Flash
LMArena Longer Query14831508
CL-bench20.8%—
CL-bench Life16.9%—

Writing & Preference Gemini 3.8 Flash leads

Gemini 3.1 Pro Preview: 66.1 (#37), Gemini 3.8 Flash: 72.2 (#15)

BenchmarkGemini 3.1 Pro PreviewGemini 3.8 Flash
LMArena Text14811499
LMArena Creative Writing14821492
EQ-Bench Creative Writing14911748
LMArena Multi-Turn14881501
EQ-Bench 41142—

Frequently asked questions

Is Gemini 3.1 Pro Preview better than Gemini 3.8 Flash?

Gemini 3.8 Flash is the stronger model overall, scoring 61.8 to 56.7 on the Noometry Index.

Which is cheaper, Gemini 3.1 Pro Preview or Gemini 3.8 Flash?

Gemini 3.8 Flash is cheaper. It lists at $0.75 per million input tokens and $3.75 per million output tokens; Gemini 3.1 Pro Preview lists at $2 and $12.

Is Gemini 3.1 Pro Preview or Gemini 3.8 Flash better for coding?

Gemini 3.8 Flash scores higher on coding benchmarks: 59.2 versus 42.5 in the Noometry coding category.

Which has the bigger context window?

Both accept 1.05M tokens.

How many benchmarks do Gemini 3.1 Pro Preview and Gemini 3.8 Flash share?

45 benchmarks have published results for both models. Gemini 3.1 Pro Preview has 71 scored results on Noometry and Gemini 3.8 Flash has 50.

Related comparisons

Go deeper