Model comparison

Gemini 3.7 Flash vs Gemini 3 Deep Think

Gemini 3.7 Flash has enough public results to be ranked (#11); Gemini 3 Deep Think does not yet, so treat this comparison as directional.

Last verified . 3 shared benchmarks.

Gemini 3.7 Flash Google

59.8

Rank #11 Confirmed

Gemini 3 Deep Think Google

58.5

Unranked Sparse

Summary

  • They share 3 benchmarks with published results for both. Gemini 3.7 Flash scores higher in 0 categories and Gemini 3 Deep Think in 1 category, but none of those gaps is larger than the uncertainty.
  • The biggest single-benchmark swing is CritPt: 14.3% for Gemini 3.7 Flash and 25.7% for Gemini 3 Deep Think.

Side by side

Gemini 3.7 Flash and Gemini 3 Deep Think specifications
Gemini 3.7 FlashGemini 3 Deep Think
ProviderGoogleGoogle
Noometry Index59.858.5
Released2026-08-132026-02-12
WeightsProprietaryProprietary
Context window1.05M—
Max output66K—
Input $ / M tokens$0.75—
Output $ / M tokens$3.75—
Results tracked443

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

Category by category

Coding Not comparable

Gemini 3.7 Flash: 55.7 (#19), Gemini 3 Deep Think: —

Coding benchmarks
BenchmarkGemini 3.7 FlashGemini 3 Deep Think
DeepSWE65.5%—
FrontierCode43.6%—
LMArena WebDev1593—
FrontierSWE20.3%—
SciCode59.8%—
LMArena Coding1499—
ALE-Bench904.3—

Agentic & Tool Use Not comparable

Gemini 3.7 Flash: 42.2 (#18), Gemini 3 Deep Think: —

Agentic & Tool Use benchmarks
BenchmarkGemini 3.7 FlashGemini 3 Deep Think
APEX-Agents67.8%—
Remote Labor Index5%—
GDP.pdf23.8%—

Reasoning Too close to call

Gemini 3.7 Flash: 70.1 (#12), Gemini 3 Deep Think: 70.8 (#11)

Reasoning benchmarks
BenchmarkGemini 3.7 FlashGemini 3 Deep Think
ARC-AGI-284.6%84.6%
ARC-AGI-195.5%96%
CritPt14.3%25.7%
NYT Connections (extended)94%—
Chess Puzzles47%—
LMArena Hard Prompts1497—
Mystery Game Puzzles37%—
DTBench96.8%—
LMCA50.4%—
Epoch Capabilities Index157.72—

Math Not comparable

Gemini 3.7 Flash: 69.5 (#18), Gemini 3 Deep Think: —

Math benchmarks
BenchmarkGemini 3.7 FlashGemini 3 Deep Think
FrontierMath (Tiers 1-3)71.6%—
FrontierMath Tier 436.6%—
OTIS Mock AIME 2024-202597.2%—
ProofBench58%—
LMArena Math1511—

Knowledge Not comparable

Gemini 3.7 Flash: 69.8 (#4), Gemini 3 Deep Think: —

Knowledge benchmarks
BenchmarkGemini 3.7 FlashGemini 3 Deep Think
GPQA Diamond94.8%—
SimpleQA Verified69.2%—
LMArena Expert1508—

Multimodal Not comparable

Gemini 3.7 Flash: 36.9 (#69), Gemini 3 Deep Think: —

Multimodal benchmarks
BenchmarkGemini 3.7 FlashGemini 3 Deep Think
LMArena Vision1314—
Furniture Assembly26.7%—

Multilingual Not comparable

Gemini 3.7 Flash: 57.8 (#7), Gemini 3 Deep Think: —

Multilingual benchmarks
BenchmarkGemini 3.7 FlashGemini 3 Deep Think
LMArena Non-English1485—
LMArena Chinese1553—
LMArena French1512—
LMArena German1485—
LMArena Japanese1506—
LMArena Korean1486—
LMArena Russian1519—
LMArena Spanish1507—

Instruction Following Not comparable

Gemini 3.7 Flash: 78.0 (#12), Gemini 3 Deep Think: —

Instruction Following benchmarks
BenchmarkGemini 3.7 FlashGemini 3 Deep Think
LMArena Instruction Following1486—

Long Context Not comparable

Gemini 3.7 Flash: 45.8 (#28), Gemini 3 Deep Think: —

Long Context benchmarks
BenchmarkGemini 3.7 FlashGemini 3 Deep Think
LMArena Longer Query1493—

Writing & Preference Not comparable

Gemini 3.7 Flash: 71.4 (#19), Gemini 3 Deep Think: —

Writing & Preference benchmarks
BenchmarkGemini 3.7 FlashGemini 3 Deep Think
LMArena Text1487—
LMArena Creative Writing1490—
EQ-Bench Creative Writing1723—
LMArena Multi-Turn1495—

Frequently asked questions

Is Gemini 3.7 Flash better than Gemini 3 Deep Think?

Gemini 3.7 Flash has enough public results to be ranked (#11); Gemini 3 Deep Think does not yet, so treat this comparison as directional.

How many benchmarks do Gemini 3.7 Flash and Gemini 3 Deep Think share?

3 benchmarks have published results for both models. Gemini 3.7 Flash has 44 scored results on Noometry and Gemini 3 Deep Think has 3.

Related comparisons

Go deeper