Model comparison

DeepSeek-V3.1-Terminus vs Gemini 2.5 Pro

Gemini 2.5 Pro is the stronger model overall, scoring 45.0 to 43.1 on the Noometry Index. DeepSeek-V3.1-Terminus costs 7.6× less per token, which makes it the better buy when Gemini 2.5 Pro's lead doesn't matter for your workload.

Last verified October 10, 2026. 16 shared benchmarks.

DeepSeek-V3.1-Terminus

DeepSeek

43.1

Rank #97 Confirmed

Gemini 2.5 Pro

Google

45.0

Rank #75 Confirmed

Summary

They share 16 benchmarks with published results for both. DeepSeek-V3.1-Terminus scores higher in 1 category and Gemini 2.5 Pro in 6 categories; 5 gaps are clear of the uncertainty.
The widest gap is in long context, where Gemini 2.5 Pro leads 59.8 to 43.4.
The biggest single-benchmark swing is Kagi LLM Benchmark: 57.4% for DeepSeek-V3.1-Terminus and 70.3% for Gemini 2.5 Pro.
DeepSeek-V3.1-Terminus is cheaper at $0.27 / $1 per million input/output tokens, against $1.25 / $10 for Gemini 2.5 Pro.
Gemini 2.5 Pro 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 2.5 Pro specifications
	DeepSeek-V3.1-Terminus	Gemini 2.5 Pro
Provider	DeepSeek	Google
Noometry Index	43.1	45.0
Released	2025-09-22	2025-03-25
Weights	Open	Proprietary
Context window	164K	1.05M
Max output	147K	66K
Input $ / M tokens	$0.27	$1.25
Output $ / M tokens	$1	$10
Results tracked	16	78

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

Category by category

Coding Too close to call

DeepSeek-V3.1-Terminus: 42.0 (#113), Gemini 2.5 Pro: 42.4 (#101)

Coding benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 2.5 Pro
SciCode	40.6%	42.8%
LMArena Coding	1426	1452
ALE-Bench	745.17	785.52
SWE-bench Verified	—	57.6%
SWE-bench Verified (bash only)	—	53.6%
Aider Polyglot	—	83.1%
LMArena WebDev	—	1227
GSO	—	3.9%
WeirdML	—	54%
LiveBench Coding	—	85.9%
CadEval	—	64%
AlgoTune	—	1.51

Agentic & Tool Use Not comparable

DeepSeek-V3.1-Terminus: —, Gemini 2.5 Pro: 29.2 (#88)

Agentic & Tool Use benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 2.5 Pro
Terminal-Bench	—	32.6%
GDPval	—	23.3%
Remote Labor Index	—	0.8%
TheAgentCompany	—	30.3%
τ²-bench Banking	—	13.7%
DeepResearch Bench	—	42.8%
BALROG	—	43.3%
LMArena Search	—	1142
METR Time Horizons	—	55.4%
Vending-Bench 2	—	573.64

Reasoning Gemini 2.5 Pro leads

DeepSeek-V3.1-Terminus: 26.4 (#133), Gemini 2.5 Pro: 28.8 (#99)

Reasoning benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 2.5 Pro
Kagi LLM Benchmark	57.4%	70.3%
CritPt	1.7%	2%
LMArena Hard Prompts	1426	1455
DTBench	81.3%	82.4%
LMCA	28.6%	34.8%
ARC-AGI-2	—	4.9%
SimpleBench	—	62.4%
ARC-AGI-1	—	41%
Chess Puzzles	—	20%
EnigmaEval	—	5.6%
LiveBench Reasoning	—	89.8%
LiveBench Data Analysis	—	79.9%
Epoch Capabilities Index	—	145.32
ForecastBench	—	61.3
LiveBench	—	82.3%

Math DeepSeek-V3.1-Terminus leads

DeepSeek-V3.1-Terminus: 38.5 (#137), Gemini 2.5 Pro: 32.5 (#213)

Math benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 2.5 Pro
LMArena Math	1402	1450
FrontierMath (Tiers 1-3)	—	24.6%
FrontierMath Tier 4	—	0%
OTIS Mock AIME 2024-2025	—	84.7%
Omni-MATH	—	41.6%
LiveBench Math	—	90.2%
MATH Level 5	—	95.9%
FrontierMath (Feb 2025 set)	—	14.1%
FrontierMath Tier 4 (v1)	—	4.2%

Knowledge Not comparable

DeepSeek-V3.1-Terminus: —, Gemini 2.5 Pro: 56.0 (#46)

Knowledge benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 2.5 Pro
GPQA Diamond	—	85.3%
Humanity's Last Exam	—	21.6%
MMLU-Pro	—	86.3%
Confabulations	—	10.6%
Vectara Hallucination Rate	—	7%
GPQA (HELM)	—	74.9%
LMArena Expert	—	1452

Multimodal Not comparable

DeepSeek-V3.1-Terminus: —, Gemini 2.5 Pro: 45.2 (#18)

Multimodal benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 2.5 Pro
LMArena Vision	—	1263
GeoBench	—	86%
VPCT	—	48%
LMArena Document	—	1421
SpatialViz-Bench	—	44.7%

Multilingual Gemini 2.5 Pro leads

DeepSeek-V3.1-Terminus: 52.1 (#92), Gemini 2.5 Pro: 55.3 (#31)

Multilingual benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 2.5 Pro
LMArena Non-English	1407	1451
LMArena Russian	1436	1461
LMArena Chinese	—	1507
LMArena French	—	1472
LMArena German	—	1487
LMArena Japanese	—	1461
LMArena Korean	—	1434
LMArena Spanish	—	1473

Instruction Following Too close to call

DeepSeek-V3.1-Terminus: 74.0 (#106), Gemini 2.5 Pro: 75.0 (#75)

Instruction Following benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 2.5 Pro
LMArena Instruction Following	1404	1437
LiveBench Instruction Following	—	80.6%
IFEval	—	84%

Long Context Gemini 2.5 Pro leads

DeepSeek-V3.1-Terminus: 43.4 (#97), Gemini 2.5 Pro: 59.8 (#5)

Long Context benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 2.5 Pro
LMArena Longer Query	1421	1449
Fiction.LiveBench	—	91.7%

Writing & Preference Gemini 2.5 Pro leads

DeepSeek-V3.1-Terminus: 61.0 (#92), Gemini 2.5 Pro: 63.7 (#62)

Writing & Preference benchmarks
Benchmark	DeepSeek-V3.1-Terminus	Gemini 2.5 Pro
LMArena Text	1419	1458
LMArena Creative Writing	1403	1454
LMArena Multi-Turn	1411	1453
Short-Story Creative Writing	—	83.8%
EQ-Bench Creative Writing	—	1421
WildBench	—	85.7%
LiveBench Language	—	67.8%

Frequently asked questions

Is DeepSeek-V3.1-Terminus better than Gemini 2.5 Pro?

Which is cheaper, DeepSeek-V3.1-Terminus or Gemini 2.5 Pro?

DeepSeek-V3.1-Terminus is cheaper. It lists at $0.27 per million input tokens and $1 per million output tokens; Gemini 2.5 Pro lists at $1.25 and $10.

Is DeepSeek-V3.1-Terminus or Gemini 2.5 Pro better for coding?

They score almost the same on coding (42.0 vs 42.4); test both on your own repository before choosing.

Which has the bigger context window?

Gemini 2.5 Pro does, with 1.05M tokens against 164K.

How many benchmarks do DeepSeek-V3.1-Terminus and Gemini 2.5 Pro share?

16 benchmarks have published results for both models. DeepSeek-V3.1-Terminus has 16 scored results on Noometry and Gemini 2.5 Pro has 78.