Is Gemini 4 Argon better than Qwen3.6 Plus?

Gemini 4 Argon (high) leads on quality: 65.9 vs 59.1. The BenchLeader Index combines every independent quality benchmark; Gemini 4 Argon (high) is ahead overall as of 29 Oct 2026, but check the category scores for your use.

Gemini 4 Argon vs Qwen3.6 Plus: which is cheaper, and will that change?

Qwen3.6 Plus is cheaper today: $1.13 against $8.00 per million tokens, blended at three input tokens per output token. Gemini 4 Argon's current price runs until 30 Nov 2026, then $8.00.

Is Gemini 4 Argon or Qwen3.6 Plus better for coding?

Gemini 4 Argon scores higher in coding (67 vs 51 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1680 for Gemini 4 Argon against 1462 for Qwen3.6 Plus.

Which is faster, Gemini 4 Argon or Qwen3.6 Plus?

Gemini 4 Argon streams faster (83 vs 56 output tokens per second, Artificial Analysis 7-day median).

Is Gemini 4 Argon or Qwen3.6 Plus better for agents and tool use?

Gemini 4 Argon scores higher in agentic tasks (59 vs 53 on the category index, where 50 is average). On Terminal-Bench 2.1 (Vals), the top shared agents & tools benchmark, it is 57.7% for Gemini 4 Argon against 53.2% for Qwen3.6 Plus.

Which is better for long documents?

They are level on long-context benchmarks (65 vs 64). Both take about 1M tokens: Gemini 4 Argon 1,048,576, Qwen3.6 Plus 1,000,000.

Which has lower latency?

Gemini 4 Argon answers first: 47.3 s against 101.3 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.

When was Gemini 4 Argon released?

Gemini 4 Argon became generally available on 13 Oct 2026, after first appearing on 30 Sept 2026.

Gemini 4 Argon vs Qwen3.6 Plus

Full profiles: Gemini 4 Argon (Google) and Qwen3.6 Plus (Alibaba): every benchmark, price and rank.

Updated 29 Oct 2026 · Data from 9 sources

As of 29 Oct 2026, Gemini 4 Argon is ahead of Qwen3.6 Plus on quality (65.9 vs 59.1 on the BenchLeader Index), but Qwen3.6 Plus is 7.1× cheaper at $1.13 vs $8.00 per 1M tokens blended. Gemini 4 Argon leads in every category we measure both in. Gemini 4 Argon's current price runs until 30 Nov 2026, then $8.00.

Key facts (as of 29 Oct 2026)

Gemini 4 Argon scores 65.9 on the BenchLeader Index and Qwen3.6 Plus scores 59.1 (BenchLeader, 29 Oct 2026).
Gemini 4 Argon costs $8.00 per 1M tokens blended until 30 Nov 2026, then $8.00 (https://ai.google.dev/gemini-api/docs/pricing, checked 20 Oct 2026).
Qwen3.6 Plus costs $1.13 per 1M tokens blended (list price, 29 Oct 2026).
Gemini 4 Argon streams faster than Qwen3.6 Plus (Artificial Analysis, 7-day median, 29 Oct 2026).
Of the 33 benchmarks both models have, Gemini 4 Argon leads 33 (BenchLeader, 29 Oct 2026).
On Arena WebDev, Gemini 4 Argon is rated 1680 and Qwen3.6 Plus 1462 (LMArena, as published by 29 Oct 2026).

Gemini 4 Argon benchmarks high Google

Qwen3.6 Plus benchmarks Alibaba Open in the comparison tool

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use case	Pick	Why	Confidence
Coding	Gemini 4 Argon	67 vs 51 category score; Arena WebDev 1680 vs 1462	High
Agents & tool use	Gemini 4 Argon	59 vs 53 category score; Terminal-Bench 2.1 (Vals) 57.7% vs 53.2%	Medium
Maths	Gemini 4 Argon	70 vs 58 category score; FrontierMath Tiers 1–3 86.0% vs 38.3%	High
Reasoning	Gemini 4 Argon	71 vs 63 category score; GPQA Diamond 96.4% vs 88.4%	High
Knowledge	Gemini 4 Argon	73 vs 57 category score; SimpleQA Verified 76.0% vs 44.1%	High
Long documents	Either	65 vs 64 category score; AA-LCR v1.1 79.7% vs 78.3%	Either
Chat quality (human preference)	Gemini 4 Argon	72 vs 63 on Arena votes	High
Lowest cost	Qwen3.6 Plus	$1.13 vs $8.00 per 1M blended; agentic coding session $0.042 vs $0.320; from 1 Dec 2026: $1.13 vs $8.00	–
Fastest first answer	Gemini 4 Argon	47.3 s (Gemini 4 Argon (high)) vs 101.3 s (Qwen3.6 Plus) to the first answer token	–
High volume on a budget	Neither flagship	A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs	–

Key differences

Gemini 4 Argon (high) leads on quality: 65.9 vs 59.1.
Gemini 4 Argon (high) is stronger in agents & tools, coding, human preference, knowledge, long context, maths, reasoning.
Qwen3.6 Plus is stronger in instruction following, multimodal.
Qwen3.6 Plus is 7.1× cheaper ($1.13 vs $8.00 per 1M blended) until 30 Nov 2026, then $1.13 vs $8.00 from 1 Dec 2026.
Gemini 4 Argon (high) streams 1.5× faster (83 vs 56 tokens per second).

At a glance

Spec	Gemini 4 Argon	Qwen3.6 Plus
Developer	Google	Alibaba
Released	30 Sept 2026	31 Mar 2026
Generally available	13 Oct 2026	31 Mar 2026
Context window (tokens)	1,048,576	1,000,000
Max output (tokens)	65,536 (up to 1,048,576 with long decode)	–
Input types	text, image, video, audio, PDF	–
Reasoning effort settings	low, medium, high	–
Compared at	Gemini 4 Argon (high)	Qwen3.6 Plus
Open weights	No	No
Price in / out / cached input per 1M	$4.00 / $20.00 / $0.100	$0.500 / $3.00 / $0.028
Announced price change	$4.00 / $20.00 / $0.200 from 1 Dec 2026	None announced
API model ID	gemini-4-argon	–
Where to use it	Gemini API (AI Studio), Gemini Enterprise Agent Platform, Gemini app	–

Limits, availability and announced prices from the vendors' own pages: ai.google.dev, ai.google.dev pricing (checked 20 Oct 2026). Everything else is from the day's data.

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

Category	Gemini 4 Argon (high)	Qwen3.6 Plus	Leader
Reasoning	71.2	63.3	Gemini 4 Argon
Coding	66.5	51.1	Gemini 4 Argon
Agents & tools	58.8	53.1	Gemini 4 Argon
Maths	70.3	57.9	Gemini 4 Argon
Knowledge	73.1	57.0	Gemini 4 Argon
Instruction following	–	73.3	not comparable
Human preference	71.6	62.6	Gemini 4 Argon
Multimodal	–	60.6	not comparable
Long context	64.7	64.0	level

Where sources disagree

Across the 33 benchmarks both have, Gemini 4 Argon leads 33, Qwen3.6 Plus leads 0. Every overall index that rates both puts Gemini 4 Argon ahead.

Overall index	Gemini 4 Argon (high)	Qwen3.6 Plus	Leader
BenchLeader Index	65.9	59.1	Gemini 4 Argon
Arena Text	1517	1443	Gemini 4 Argon

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.

Measure	Gemini 4 Argon (high)	Qwen3.6 Plus
Blended price per 1M tokens, until 30 Nov 2026	$8.00	$1.13
Input / output per 1M	$4.00 / $20.00	$0.500 / $3.00
Blended price per 1M from 1 Dec 2026	$8.00	$1.13
Input / output per 1M from 1 Dec 2026	$4.00 / $20.00	$0.500 / $3.00
Cached input per 1M	$0.100	$0.028
Price per task: chat reply	$0.0076	$0.0011
Price per task: summarize a 30-page report	$0.060	$0.0078
Price per task: code edit	$0.054	$0.0075
Price per task: agentic coding session	$0.320	$0.042
Price per task: structured extraction	$0.012	$0.0016
Cost to run a full benchmark suite	$7.68	–
Output speed	83 tok/s	56 tok/s
Time to first answer	47.3 s	101.3 s
Time to a complete answer	53.3 s	110.2 s

Each model is compared at its best-ranked reasoning-effort setting. Gemini 4 Argon (high) scores 65.9 and takes 47 s to its first answer token; Gemini 4 Argon scores 63.1 in 5 s. Qwen3.6 Plus scores 59.1 and takes 101 s to its first answer token. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

145 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

Metric	Publisher	Gemini 4 Argon (high)	Qwen3.6 Plus
BenchLeader Index	BenchLeader	65.9	59.1
Agents & tools score	BenchLeader	58.8	53.1
Coding score	BenchLeader	66.5	51.1
Human preference score	BenchLeader	71.6	62.6
Knowledge score	BenchLeader	73.1	57.0
Long context score	BenchLeader	64.7	64.0
Maths score	BenchLeader	70.3	57.9
Reasoning score	BenchLeader	71.2	63.3
Instruction following score	BenchLeader	–	73.3
Multimodal score	BenchLeader	–	60.6
Blended price $/M	BenchLeader	$8.00	$1.13
Output speed	BenchLeader	83 tok/s	56 tok/s
Time to first answer	BenchLeader	47.3 s	101.3 s
Context window	BenchLeader	1,048,576 tokens	1,000,000 tokens
Reasoning
GPQA Diamond	Epoch AI Benchmarking Hub	96.4%	88.4%
Arena Hard Prompts	Arena (LMArena)	1540	1468
LiveBench 2.0 Reasoning	LiveBench	95.1%†	–
LiveBench 1.0 Reasoning	LiveBench	–	75.8%
GPQA Diamond (AA)	Artificial Analysis	–	88.2%
Humanity's Last Exam (AA)	Artificial Analysis	57.1%	27.9%
HLE-Diamond (AA)	Artificial Analysis	56.7%	–
GPQA Diamond (Vals)	Vals AI	–	87.4%
ARC-AGI-1	ARC Prize	98.5%	–
ARC-AGI-2	ARC Prize	91.3%	–
ARC-AGI-3	ARC Prize	97.3%	–
CritPt	Artificial Analysis	27.1%	2.9%
CritPt v2 hard subset (AA)	Artificial Analysis	52.5%	–
MysteryMechanism	Vals AI	45.5%	–
Chess Puzzles	Epoch AI Benchmarking Hub	59.0%	14.0%
Mystery Game Puzzles	Epoch AI Benchmarking Hub	64.0%	12.0%†
CL-bench	Epoch AI Benchmarking Hub	–	20.3%
LMCA	Epoch AI Benchmarking Hub	63.7%	33.1%
DTBench	Epoch AI Benchmarking Hub	97.3%	81.9%
Coding
SWE-bench Verified (Epoch)	Epoch AI Benchmarking Hub	–	57.9%
SciCode	SciCode	61.8%	40.7%
FrontierCode	Cognition	47.5%†	–
Arena Coding	Arena (LMArena)	1552	1496
Arena WebDev	Arena (LMArena)	1680	1462
LiveBench 2.0 Coding	LiveBench	89.7%†	–

Show all 145 benchmarks

Metric	Publisher	Gemini 4 Argon (high)	Qwen3.6 Plus
Coding
LiveBench 1.0 Coding	LiveBench	–	78.2%
SciCode (AA)	Artificial Analysis	61.8%	–
LiveCodeBench	Vals AI	–	86.0%
IOI	Vals AI	100.0%	–
SWE-bench (Vals)	Vals AI	–	73.4%
Code Migration	Vals AI	68.2%	11.1%
Code Migration v1.1	Vals AI	70.8%	–
ProgramBench	Vals AI	2.5%	0.0%
SWE-bench Multimodal	Vals AI	56.0%	–
Vibe Code Bench 1-100	Vals AI	21.2%	–
Vibe Code Bench v1.1	Vals AI	91.9%	25.6%
MirrorCode	Epoch AI Benchmarking Hub	58.9%	–
CursorBench	Cursor	52.9%	–
ALE-Bench	Epoch AI Benchmarking Hub	2100.1	670.1
FrontierSWE	Epoch AI Benchmarking Hub	55.0%	–
Terminal-Bench 4.0 (AA)	Artificial Analysis	57.1%	–
Terminal-Bench 2.1 (AA)	Artificial Analysis	–	61.4%
Startrise Frontend	Startrise	71.0%†	–
FrontierCode 1.1 (AA)	Artificial Analysis	43.5%	–
FrontierCode 2.0 (AA)	Artificial Analysis	25.7%	–
Agents & tools
Remote Labor Index	Scale AI / CAIS	17.1%†	–
APEX-Agents	Mercor	82.4%†	–
Arena Agent	Arena (LMArena)	11.7	–
LiveBench Long Agentic	LiveBench	61.2%†	–
LiveBench Browser	LiveBench	82.8%†	–
LiveBench Agentic Coding	LiveBench	–	41.4%
Terminal-Bench Hard	Artificial Analysis	–	43.9%
τ²-Bench Telecom (AA)	Artificial Analysis	–	97.7%
Terminal-Bench 2.1 (Vals)	Vals AI	57.7%	53.2%
HiL-Bench	Scale AI SEAL	62.0%†	–
GDPval-AA v2.1, normalised score	Artificial Analysis	56.2%	–
GDPval-AA v2.1	Artificial Analysis	1631	–
τ³-Banking (AA)	Artificial Analysis	–	20.8%
Analyst Agent (AA)	Artificial Analysis	48.8%	–
CUA-bench	Vals AI	4.8%	–
CyberBench	Vals AI	77.9%	–
Finance Agent v2	Vals AI	65.4%	40.9%
Finance Agent v2.1	Vals AI	67.7%	–
Harvey's Legal Agent Benchmark v1.1	Vals AI	27.1%	–
Harvey's Legal Agent Benchmark v1	Vals AI	19.6%	1.3%
Legal Research Bench	Vals AI	54.8%	14.9%
Robo-bench	Vals AI	0.8%	–
SREBench	Vals AI	44.3%	–
Tax Agent Bench	Vals AI	44.6%	7.7%
Terminal-Bench 2.0 (Vals)	Vals AI	–	44.9%
Terminal-Bench 4.0 (Vals)	Vals AI	57.6%	–
Terminal-Bench Science	Vals AI	44.3%	–
Time Horizon Index: KSP	Vals AI	52.5%	–
Vending-Bench 2	Andon Labs	13718.2†	5114.9
AutomationBench	Artificial Analysis	77.5%	–
GDP.pdf (AA)	Artificial Analysis	21.8%	–
Harvey LAB-AA v1.1	Harvey	3.9%	–
AA-Briefcase v1.1	Artificial Analysis	1483	–
Terminal-Bench-Science 0.1 (AA)	Artificial Analysis	52.9%	–
FACTS Search	Google	84.0%†	–
Maths
FrontierMath Tiers 1–3	Epoch AI Benchmarking Hub	86.0%	38.3%
FrontierMath Tier 4	Epoch AI Benchmarking Hub	78.0%	–
OTIS Mock AIME	Epoch AI Benchmarking Hub	100.0%	93.3%
ProofBench	Vals AI	99.0%†	–
LiveBench Mathematics	LiveBench	–	83.7%
AIME (Vals)	Vals AI	–	94.6%
Arena Maths	Arena (LMArena)	1532	1454
Knowledge
SimpleQA Verified	Epoch AI Benchmarking Hub	76.0%	44.1%
LiveBench 2.0 Data Analysis	LiveBench	85.2%†	–
LiveBench Research	LiveBench	83.1%†	–
LiveBench 1.0 Data Analysis	LiveBench	–	69.9%
AA-Omniscience v1.1	Artificial Analysis	46.1	–
MMLU-Pro	Vals AI	–	87.7%
LegalBench	Vals AI	88.3%	84.2%
CorpFin	Vals AI	–	61.9%
TaxEval	Vals AI	–	74.7%
PRBench Finance	Scale AI SEAL	49.9%†	–
PRBench Legal	Scale AI SEAL	49.4%†	–
BioMysteryBench	Vals AI	76.3%	–
CaseLaw v2	Vals AI	–	51.5%
Excel Modeling Benchmark	Vals AI	75.2%	32.9%
Excel Modeling Benchmark v1.1	Vals AI	74.8%	–
MedCode	Vals AI	58.8%	36.9%
MedScribe	Vals AI	87.4%	77.0%
Public Benefits Bench v1.1	Vals AI	69.8%	–
DrugDiscoveryBench	Scale AI SEAL	65.4%	–
EBR-bench	Epoch AI Benchmarking Hub	64.8%	–
GDP.pdf	Epoch AI Benchmarking Hub	28.4%	–
AA-Omniscience v1.1: accuracy	Artificial Analysis	48.3%	–
AA-Omniscience v1.1: non-hallucination	Artificial Analysis	95.7%	–
HealthBench Professional (AA)	OpenAI	55.0%	–
Instruction following
LiveBench Language	LiveBench	–	75.0%
LiveBench Instruction Following	LiveBench	–	58.3%
IFBench	Artificial Analysis	–	75.2%
MultiChallenge	Scale AI SEAL	78.7%†	–
Arena Instruction Following	Arena (LMArena)	1519	1435
Human preference
Arena Text	Arena (LMArena)	1517	1443
EQ-Bench 4	EQ-Bench	1236†	–
Arena Creative Writing	Arena (LMArena)	1512	1407
Arena Multi-turn	Arena (LMArena)	1544	1445
Arena Longer Queries	Arena (LMArena)	1535	1454
Multimodal
LiveBench Design	LiveBench	73.7%†	–
MMMU-Pro	Artificial Analysis	–	78.0%
MMMU-Pro (Vals)	Vals AI	–	84.2%
MortgageTax	Vals AI	–	68.0%
SAGE	Vals AI	89.5%	–
AudioMC	Scale AI SEAL	58.4%	–
AudioMC (text output)	Scale AI SEAL	58.4%	–
Blueprint-Bench 2	Epoch AI Benchmarking Hub	54.5%†	–
Code2Video-AA	Artificial Analysis	1259	–
AA-3D	Artificial Analysis	1153	–
Long context
AA-LCR v1.1	Artificial Analysis	79.7%	78.3%
MLCR	Artificial Analysis	13.9%	–
Composite
Epoch Capabilities Index	Epoch AI Benchmarking Hub	166.4†	147.3
LiveBench 2.0	LiveBench	79.3%†	–
LiveBench 1.0	LiveBench	–	68.9%
AA Intelligence Index v5.0	Artificial Analysis	50.4	–
AA Intelligence Index v4.3.2	Artificial Analysis	52.6	27.0
AA Progress Index v1	Artificial Analysis	341.8	283.4
Vals Index	Vals AI	69.2	–
Vals Finance Index	Vals AI	64.9%	–
Vals RSI Index	Vals AI	30.6%	–
Vals Science Index	Vals AI	55.4%	–
Vals Multimodal Index	Vals AI	–	51.5%
Vals Router Index	Vals AI	69.2%†	–

Data as of 2026-10-29. Best configuration of each model; every score links to its source on the model pages.

What changed

1 Dec 2026 Gemini 4 Argon: list price moves to $4.00 / $20.00 per 1M input / output tokens (announced).
29 Oct 2026 Gemini 4 Argon (high): input price moved from $2.00/M to $4.00/M (100% up); output price moved from $10.00/M to $20.00/M (100% up); cost per task moved from $3.84/M to $7.68/M (100% up).
29 Oct 2026 Qwen3.6 Plus: Qwen3.6 Plus cached input price moved from $0.050/M to $0.028/M (45% down).
28 Oct 2026 Gemini 4 Argon (high): BenchLeader Index 66.8 → 65.9.
28 Oct 2026 Gemini 4 Argon (high): 5 new results (AA Intelligence Index v5.0, AA Progress Index v1, HLE-Diamond (AA)…); 5 score revisions; cost per task moved from $1.62/M to $3.84/M (137% up).
28 Oct 2026 Qwen3.6 Plus: 1 new result (AA Progress Index v1).
27 Oct 2026 Gemini 4 Argon (high): BenchLeader Index 68.5 → 66.8.
27 Oct 2026 Qwen3.6 Plus: BenchLeader Index 59.7 → 59.2.
27 Oct 2026 Gemini 4 Argon (high): 1 new result (Terminal-Bench 2.1 (Vals)).
27 Oct 2026 Qwen3.6 Plus: Qwen3.6 Plus cached input price moved from $0.028/M to $0.050/M (81% up).

Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs