Model comparison

DeepSeek-V3.1-Terminus vs Gemini 3.7 Flash

Gemini 3.7 Flash is the stronger model overall, scoring 59.8 to 42.6 on the Noometry Index. DeepSeek-V3.1-Terminus costs 3.2× less per token, which makes it the better buy when Gemini 3.7 Flash's lead doesn't matter for your workload.

Last verified October 10, 2026. 15 shared benchmarks.

DeepSeek-V3.1-Terminus

DeepSeek

42.6

Rank #96 Confirmed

Gemini 3.7 Flash

Google

59.8

Rank #11 Confirmed

Summary

They share 15 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 0 categories and Gemini 3.7 Flash in 7 categories; 7 gaps are clear of the uncertainty.
The widest gap is in reasoning, where Gemini 3.7 Flash leads 70.1 to 25.7.
The biggest single-benchmark swing is LMCA: 28.6% for DeepSeek-V3.1-Terminus and 50.4% for Gemini 3.7 Flash.
DeepSeek-V3.1-Terminus is cheaper at $0.30 / $1 per million input/output tokens, against $0.75 / $3.75 for Gemini 3.7 Flash.
Gemini 3.7 Flash accepts more context: 1.05M tokens versus 164K.
DeepSeek-V3.1-Terminus has downloadable open weights; the other is API-only.

Side by side

DeepSeek-V3.1-Terminus and Gemini 3.7 Flash specifications
	DeepSeek-V3.1-Terminus	Gemini 3.7 Flash
Provider	DeepSeek	Google
Noometry Index	42.6	59.8
Released	2025-09-22	2026-08-13
Weights	Open	Proprietary
Context window	164K	1.05M
Max output	66K	66K
Input $ / M tokens	$0.30	$0.75
Output $ / M tokens	$1	$3.75
Results tracked	16	44

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

Category by category

Coding Gemini 3.7 Flash leads

DeepSeek-V3.1-Terminus: 41.5 (#114), Gemini 3.7 Flash: 55.7 (#19)

Coding benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 3.7 Flash
SciCode	40.6%	59.8%
LMArena Coding	1426	1499
ALE-Bench	745.17	904.3
DeepSWE	—	65.5%
FrontierCode	—	43.6%
LMArena WebDev	—	1593
FrontierSWE	—	20.3%

Agentic & Tool Use Not comparable

DeepSeek-V3.1-Terminus: —, Gemini 3.7 Flash: 42.2 (#18)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 3.7 Flash
APEX-Agents	—	67.8%
Remote Labor Index	—	5%
GDP.pdf	—	23.8%

Reasoning Gemini 3.7 Flash leads

DeepSeek-V3.1-Terminus: 25.7 (#126), Gemini 3.7 Flash: 70.1 (#12)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 3.7 Flash
CritPt	1.7%	14.3%
LMArena Hard Prompts	1427	1497
DTBench	81.3%	96.8%
LMCA	28.6%	50.4%
ARC-AGI-2	—	84.6%
Kagi LLM Benchmark	57.4%	—
NYT Connections (extended)	—	94%
ARC-AGI-1	—	95.5%
Chess Puzzles	—	47%
Mystery Game Puzzles	—	37%
Epoch Capabilities Index	—	157.72

Math Gemini 3.7 Flash leads

DeepSeek-V3.1-Terminus: 35.7 (#138), Gemini 3.7 Flash: 69.5 (#18)

Math benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 3.7 Flash
LMArena Math	1402	1511
FrontierMath (Tiers 1-3)	—	71.6%
FrontierMath Tier 4	—	36.6%
OTIS Mock AIME 2024-2025	—	97.2%
ProofBench	—	58%

Knowledge Not comparable

DeepSeek-V3.1-Terminus: —, Gemini 3.7 Flash: 69.8 (#4)

Knowledge benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 3.7 Flash
GPQA Diamond	—	94.8%
SimpleQA Verified	—	69.2%
LMArena Expert	—	1508

Multimodal Not comparable

DeepSeek-V3.1-Terminus: —, Gemini 3.7 Flash: 36.9 (#69)

Multimodal benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 3.7 Flash
LMArena Vision	—	1314
Furniture Assembly	—	26.7%

Multilingual Gemini 3.7 Flash leads

DeepSeek-V3.1-Terminus: 52.3 (#87), Gemini 3.7 Flash: 57.8 (#7)

Multilingual benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 3.7 Flash
LMArena Non-English	1407	1485
LMArena Russian	1434	1519
LMArena Chinese	—	1553
LMArena French	—	1512
LMArena German	—	1485
LMArena Japanese	—	1506
LMArena Korean	—	1486
LMArena Spanish	—	1507

Instruction Following Gemini 3.7 Flash leads

DeepSeek-V3.1-Terminus: 74.4 (#96), Gemini 3.7 Flash: 78.0 (#12)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 3.7 Flash
LMArena Instruction Following	1406	1486

Long Context Gemini 3.7 Flash leads

DeepSeek-V3.1-Terminus: 43.5 (#88), Gemini 3.7 Flash: 45.8 (#28)

Long Context benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 3.7 Flash
LMArena Longer Query	1426	1493

Writing & Preference Gemini 3.7 Flash leads

DeepSeek-V3.1-Terminus: 61.3 (#87), Gemini 3.7 Flash: 71.4 (#19)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 3.7 Flash
LMArena Text	1420	1487
LMArena Creative Writing	1404	1490
LMArena Multi-Turn	1411	1495
EQ-Bench Creative Writing	—	1723

Frequently asked questions

Is DeepSeek-V3.1-Terminus better than Gemini 3.7 Flash?

Which is cheaper, DeepSeek-V3.1-Terminus or Gemini 3.7 Flash?

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.30 per million input tokens and $1 per million output tokens; Gemini 3.7 Flash lists at $0.75 and $3.75.

Is DeepSeek-V3.1-Terminus or Gemini 3.7 Flash better for coding?

Gemini 3.7 Flash scores higher on coding benchmarks: 55.7 versus 41.5 in the Noometry coding category.

Which has the bigger context window?

Gemini 3.7 Flash does, with 1.05M tokens against 164K.

How many benchmarks do DeepSeek-V3.1-Terminus and Gemini 3.7 Flash share?

15 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemini 3.7 Flash has 44.