Model comparison

DeepSeek V4 Pro vs Gemini 3.1 Pro

DeepSeek against Google, compared on context, price, and attributed benchmark results.

Recorded profile verification October 1, 2026Individual provider fields may changeEvidence confidence: Medium — see receipts below

DeepSeek

DeepSeek V4 Pro

Frontier · Open weights

Google

Gemini 3.1 Pro

Frontier

AI model capability comparison
Specification	DeepSeek V4 Pro	Gemini 3.1 Pro
Provider
Provider	DeepSeek	Google
Tier
Tier	Frontier	Frontier
Context window
Context window	1M	Winner: 1.05M
Max output
Max output	Winner: 384K	66K
Input / 1M tokens
Input / 1M tokens	Winner: $1.32	$2
Output / 1M tokens
Output / 1M tokens	Winner: $3.96	$12
Weights
Weights	Open	Closed
Parameters
Parameters	1.6T total / 49B active (MoE)	Not verifiedUnverified
Reasoning levels
Reasoning levels	low, high, max	low, medium, high
Modalities
Modalities	text	text, image, video, audio, pdf
License
License	MIT	Not verifiedUnverified
API model id
API model id	deepseek-v4-pro	gemini-3.1-pro-preview
Released
Released	April 24, 2026	February 19, 2026
Artificial Analysis Intelligence Index [max] · source date DeepSeek V4 Pro: 2026-10-01
Artificial Analysis Intelligence Index [max] · source date DeepSeek V4 Pro: 2026-10-01	36	Not verifiedUnverified
SWE-bench Verified [max] · source date DeepSeek V4 Pro: 2026-04-24
SWE-bench Verified [max] · source date DeepSeek V4 Pro: 2026-04-24	80.6	Not verifiedUnverified
SWE-bench Verified · source date Gemini 3.1 Pro: 2026-02
SWE-bench Verified · source date Gemini 3.1 Pro: 2026-02	Not verifiedUnverified	80.6
GPQA Diamond [max] · source date DeepSeek V4 Pro: 2026-04-24
GPQA Diamond [max] · source date DeepSeek V4 Pro: 2026-04-24	90.1	Not verifiedUnverified
GPQA Diamond · source date Gemini 3.1 Pro: 2026-02
GPQA Diamond · source date Gemini 3.1 Pro: 2026-02	Not verifiedUnverified	94.3
Humanity's Last Exam [max] · source date DeepSeek V4 Pro: 2026-04-24
Humanity's Last Exam [max] · source date DeepSeek V4 Pro: 2026-04-24	48.2	Not verifiedUnverified
Humanity's Last Exam · source date DeepSeek V4 Pro: 2026-08-13
Humanity's Last Exam · source date DeepSeek V4 Pro: 2026-08-13	42.7	Not verifiedUnverified
Humanity's Last Exam · source date DeepSeek V4 Pro: 2026-08-13
Humanity's Last Exam · source date DeepSeek V4 Pro: 2026-08-13	60	Not verifiedUnverified
Humanity's Last Exam · source date Gemini 3.1 Pro: 2026-02
Humanity's Last Exam · source date Gemini 3.1 Pro: 2026-02	Not verifiedUnverified	44.4
MMLU-Pro [max] · source date DeepSeek V4 Pro: 2026-04-24
MMLU-Pro [max] · source date DeepSeek V4 Pro: 2026-04-24	87.5	Not verifiedUnverified
Terminal-Bench 2.1 · source date DeepSeek V4 Pro: 2026-08-13
Terminal-Bench 2.1 · source date DeepSeek V4 Pro: 2026-08-13	87.9	Not verifiedUnverified
Terminal-Bench 2.1 · source date Gemini 3.1 Pro: 2026-07
Terminal-Bench 2.1 · source date Gemini 3.1 Pro: 2026-07	Not verifiedUnverified	73.8
DeepSWE 1.1 · source date DeepSeek V4 Pro: 2026-08-13
DeepSWE 1.1 · source date DeepSeek V4 Pro: 2026-08-13	62.7	Not verifiedUnverified

Dates beside benchmark scores refer to the linked source’s publication or capture date unless that source explicitly states when it measured the result. A shared URL alone does not establish comparable runs; unverified setups are marked. Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

Where each score comes from, and how far it can be compared across models.

Source date2026-10-01
Artificial Analysis (DeepSeek V4 Pro 0813 (max))
Composite index blending reasoning, knowledge, and coding evals into one 0–100 score.
Comparable with caveatOnly same-version scores are comparable. v4.3.2 was rebaselined (the top score fell from 66 on v4.1.1 to ~58), so v4.1.1 figures must not be compared with v4.3.2 figures — check the cited source and its date.
Source date2026-08-13
DeepSeek August 13 GA changelog (vendor) (0813 GA refresh; vendor report, exact run configuration unverified)
Agentic software engineering: pass@1 on real repo tasks with reported cost per completed task.
Directly comparable
Source date2026-08-13
DeepSeek August 13 GA changelog (vendor) (0813 GA refresh; vendor report, exact run configuration unverified)
Agentic terminal work: multi-step tasks executed in a sandboxed shell environment.
Comparable with caveatNot comparable with Terminal-Bench 3.0 or 4.0 (different task sets) or v1; harness configuration (container, time limits) also shifts results.
Source date2026-08-13
DeepSeek August 13 GA changelog (vendor) (0813 GA refresh; with tools; vendor report, exact run configuration unverified)
Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise.
Comparable with caveatSubset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.
Source date2026-08-13
DeepSeek August 13 GA changelog (vendor) (0813 GA refresh; without tools; vendor report, exact run configuration unverified)
Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise.
Comparable with caveatSubset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.
Source date2026-07
Google DeepMind model evaluation report (vendor, Terminus-2; own Feb report separately reported TB 2.0 = 68.5 — versions preserved)
Agentic terminal work: multi-step tasks executed in a sandboxed shell environment.
Comparable with caveatNot comparable with Terminal-Bench 3.0 or 4.0 (different task sets) or v1; harness configuration (container, time limits) also shifts results.
Source date2026-04-24
DeepSeek V4 Pro HF model card (vendor, Think Max, exact match) (Original April 24 checkpoint; historical vendor evaluation, not the served 0813 refresh)
Broad knowledge across 14 domains with harder, reasoning-focused multiple-choice questions.
Comparable with caveatFrontier models cluster in the high 80s–90s; near-ceiling differences are weak evidence. CoT vs direct answering must match.
Source date2026-04-24
DeepSeek V4 Pro HF model card (vendor, Think Max, with tools; 37.7 no tools) (Original April 24 checkpoint; historical vendor evaluation, not the served 0813 refresh)
Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise.
Comparable with caveatSubset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.
Source date2026-04-24
DeepSeek V4 Pro HF model card (vendor, Think Max, pass@1) (Original April 24 checkpoint; historical vendor evaluation, not the served 0813 refresh)
Graduate-level science reasoning: multiple-choice questions written by domain PhDs.
Comparable with caveatDo not treat a fixed two-point band as universal measurement uncertainty; it depends on run count and evaluation setup. Chain-of-thought, prompt, and tool policy must match. The small pool limits fine-grained conclusions, and frontier scores can be near ceiling; Artificial Analysis dropped it from its Intelligence Index in v4.3.
Source date2026-04-24
DeepSeek original V4 Pro HF card (vendor, Think Max; verifier/harness comparability unverified) (Original April 24 checkpoint; historical vendor evaluation, not the served 0813 refresh)
Real GitHub issue resolution: does the model's patch pass the hidden tests.
Comparable with caveatPost-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.
Source date2026-02
Google DeepMind model evaluation report (vendor, no tools; 51.4 with search+code)
Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise.
Comparable with caveatSubset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.
Source date2026-02
Google DeepMind model evaluation report (vendor, no tools, pass@1)
Graduate-level science reasoning: multiple-choice questions written by domain PhDs.
Comparable with caveatDo not treat a fixed two-point band as universal measurement uncertainty; it depends on run count and evaluation setup. Chain-of-thought, prompt, and tool policy must match. The small pool limits fine-grained conclusions, and frontier scores can be near ceiling; Artificial Analysis dropped it from its Intelligence Index in v4.3.
Source date2026-02
Google DeepMind model evaluation report (vendor, Thinking High, avg of 10 runs, +0.6 disclosed adjustment)
Real GitHub issue resolution: does the model's patch pass the hidden tests.
Comparable with caveatPost-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.

Pricing tiers

DeepSeek V4 Pro: Official peak rates $1.32/$3.96 per MTok; off-peak $0.66/$1.98 (cache-miss). Cache hit $0.044 peak / $0.022 off-peak. Peak hours are weekdays 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays; weekends, holidays and all other hours are off-peak. Open weights (MIT). 1.6T/49B active MoE.

Gemini 3.1 Pro: The current Gemini developer guide lists $2/$12 per MTok below 200K input and $4/$18 above 200K, including thinking output. It leaves the exact 200K boundary unspecified; confirm that boundary and other processing/cache tiers before budgeting. The exact API ID remains gemini-3.1-pro-preview. Restricted Gemini 4 Argon is a separate preview and does not make this endpoint stable.

FrontierOpen weightsRecord checked October 1, 2026

DeepSeek V4 Pro

DeepSeek V4 Pro is DeepSeek's large open-weight (MIT) MoE with a 1M-token context — DeepSeek says the cheaper V4.1-Flash now beats it.

Best for

Cost-sensitive hosted agents
Open-weight deployments
High-volume coding

Watch out

The current tariff identifies DeepSeek-V4-Pro-0813. DeepSeek's current changelog reverses the earlier September 14 re-route plan and says it will continue serving V4 Pro at unchanged rates until further notice. Original April benchmark/checkpoint results are not the current 0813 evaluation. Self-hosting memory depends on quantization, offloading and hardware.

FrontierRecord checked October 1, 2026

Gemini 3.1 Pro

Gemini 3.1 Pro Preview is Google's multimodal Pro endpoint with a 1,048,576-token input limit and 65,536-token output limit.

Best for

Very long documents
Multimodal reasoning
Frontier knowledge work

Watch out

This API endpoint remains Preview. A separate customtools endpoint is optimized for bash/custom-tool workflows and can behave differently on other tasks. Keep endpoint, thinking level and benchmark version matched; restricted Gemini 4 Argon access is a separate lifecycle.

When the cheaper one wins

DeepSeek V4 Pro is cheaper on output at $3.96 per million tokens against $12 for Gemini 3.1 Pro — about 3.0×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. On DeepSWE 1.1, DeepSeek V4 Pro is 62.8% Pass@1 at $0.24/task versus Gemini 3.1 Pro at 11.7% / $2.14/task. This compares standard short-context token rates, not total cost per accepted task. Include input, cache, context tiers, schedules, retries and review in your pilot.

Run the model picker

Evidence confidence: Medium

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

Pricing verified on both sides — Input and output rates are verified for both models.
4/5 core specs verified on both sides — Not published for at least one side: parameter count.
No directly aligned benchmark setup — No benchmark has matching cited sources, source dates, units, effort and recorded run details on both models.
Verified within the last 90 days — Older of the two catalog checks was 25 days ago.
Both models carry source citations — Each side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

DeepSeek V4 Pro: Whole-profile primary source check October 1 (accessed 2026-10-01)
DeepSeek V4 Pro: Whole-profile primary source check October 1 (accessed 2026-10-01)
DeepSeek V4 Pro: DeepSeek current API version, holiday tariff and 0813 GA benchmark publication (accessed 2026-10-01)
DeepSeek V4 Pro: DeepSeek current tariff and served endpoint versions (accessed 2026-10-01)
DeepSeek V4 Pro: DeepSeek — V4 news (accessed 2026-08-29)
DeepSeek V4 Pro: DeepSeek API pricing (accessed 2026-08-29)
DeepSeek V4 Pro: DeepSeek — V4.1-Flash release (V4-Pro phase-out) (accessed 2026-09-26)
DeepSeek V4 Pro: DeepSeek API changelog (accessed 2026-09-26)
Gemini 3.1 Pro: Google primary profile — whole-record source check October 1 (accessed 2026-10-01)
Gemini 3.1 Pro: Gemini current API pricing and cache-storage tiers (accessed 2026-10-01)
Gemini 3.1 Pro: Gemini developer guide — exact Preview rates and boundary limitation (accessed 2026-10-01)
Gemini 3.1 Pro: Gemini API 3.1 Pro Preview — exact endpoint and customtools scope (accessed 2026-10-01)
Gemini 3.1 Pro: Google Cloud — Gemini 3.1 Pro (accessed 2026-08-29)
Gemini 3.1 Pro: TechCrunch — Gemini 3.1 Pro (accessed 2026-08-29)

Related comparisons

Diving deeper on one model? DeepSeek V4 Pro · Gemini 3.1 Pro

Common questions

DeepSeek V4 Pro vs Gemini 3.1 Pro

Answered from the verified figures on this page rather than general guidance.

Is DeepSeek V4 Pro or Gemini 3.1 Pro cheaper for input?

DeepSeek V4 Pro is cheaper at $1.32 per million input tokens, against $2 for Gemini 3.1 Pro — roughly 1.5× the price. Estimate both input and output token volume for your workload. These are base rates; DeepSeek V4 Pro: Official peak rates $1.32/$3.96 per MTok; off-peak $0.66/$1.98 (cache-miss). Cache hit $0.044 peak / $0.022 off-peak. Peak hours are weekdays 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays; weekends, holidays and all other hours are off-peak. Open weights (MIT). 1.6T/49B active MoE. Gemini 3.1 Pro: The current Gemini developer guide lists $2/$12 per MTok below 200K input and $4/$18 above 200K, including thinking output. It leaves the exact 200K boundary unspecified; confirm that boundary and other processing/cache tiers before budgeting. The exact API ID remains gemini-3.1-pro-preview. Restricted Gemini 4 Argon is a separate preview and does not make this endpoint stable.

Is DeepSeek V4 Pro or Gemini 3.1 Pro cheaper for output?

DeepSeek V4 Pro is cheaper at $3.96 per million output tokens, against $12 for Gemini 3.1 Pro — roughly 3.0× the price. Estimate both input and output token volume for your workload. These are base rates; DeepSeek V4 Pro: Official peak rates $1.32/$3.96 per MTok; off-peak $0.66/$1.98 (cache-miss). Cache hit $0.044 peak / $0.022 off-peak. Peak hours are weekdays 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays; weekends, holidays and all other hours are off-peak. Open weights (MIT). 1.6T/49B active MoE. Gemini 3.1 Pro: The current Gemini developer guide lists $2/$12 per MTok below 200K input and $4/$18 above 200K, including thinking output. It leaves the exact 200K boundary unspecified; confirm that boundary and other processing/cache tiers before budgeting. The exact API ID remains gemini-3.1-pro-preview. Restricted Gemini 4 Argon is a separate preview and does not make this endpoint stable.

Which has the larger context window, DeepSeek V4 Pro or Gemini 3.1 Pro?

Gemini 3.1 Pro accepts 1.05M tokens against 1M for DeepSeek V4 Pro. This only matters if you routinely send very long documents or large codebases.

Do DeepSeek V4 Pro and Gemini 3.1 Pro support the same reasoning levels?

DeepSeek V4 Pro exposes low, high, max, while Gemini 3.1 Pro exposes low, medium, high.

Should I use DeepSeek V4 Pro or Gemini 3.1 Pro?

Both are classified in our frontier tier; this editorial grouping does not imply equal capability. DeepSeek V4 Pro is a candidate for cost-sensitive hosted agents; Gemini 3.1 Pro is a candidate for very long documents. Compare accuracy, tool reliability, latency and cost on representative tasks.

Can I self-host DeepSeek V4 Pro or Gemini 3.1 Pro?

DeepSeek V4 Pro publishes open weights, but self-hosting and third-party provider access depend on the licence, hardware, serving support, and availability. Gemini 3.1 Pro is a closed model whose supported access paths are controlled by its provider.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

Input price: DeepSeek V4 Pro costs $1.32 per 1M tokens versus $2 for Gemini 3.1 Pro — a 1.5x difference at the headline tier.
Context: Gemini 3.1 Pro takes 1.05M against 1M for DeepSeek V4 Pro — only decisive if your prompts approach the smaller window.
Deployment: DeepSeek V4 Pro publishes weights you can self-host; the other is API-only.

Run the model picker Estimate stack cost All model comparisons

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.