Across 14 comparable benchmarks, Gemini 4 Argon has better reported results on 12 and worse on 2. 1 further shared result is listed below, each with the reason it is not counted.
Moderate evidence14 of 15 shared results countedHow we compare
Price basis: Current effective rates. The price section below shows the applicable periods.
| Fact | Gemini 4 Argon | Qwen4-Max |
|---|---|---|
| Context window | 1M tokens | 1M tokens |
| Input / 1M | $2.00 | $1.50 |
| Output / 1M | $10.00 | $4.50 |
| Blended (4:1) | $1.12 | $1.07 |
| Status | Available | Available |
| Released | October 13, 2026 | November 16, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates β set your own mix.
Mean of 7 shared benchmarks grouped by capability on a 0β100 scale. How averages are built
Gemini 4 Argon ahead on 3 of 3 counted
Qwen4-Max ahead on 1 of 1 counted
Gemini 4 Argon ahead on 2 of 3 counted
Gemini 4 Argon ahead on 1 of 1 counted
No fixed-scale average β see the rows in Benchmark results
Gemini 4 Argon ahead on 2 of 2 counted
No shared comparable results for Abstract reasoning, Mathematics, Research & search, Long context, Cybersecurity.
Published scores, with matching modes where available. Gaps show Gemini 4 Argon relative to Qwen4-Max. Reading the results
| Benchmark | Gemini 4 Argon | Qwen4-Max | Gap |
|---|---|---|---|
| DeepSWERepository Engineering Β· Pass@1 (DeepSWE v1.1) | 77.9Max Β· tools | 75.7Max Β· tools | +2.2 pts#3 vs #5 of 73 |
| Terminal-Bench 4.0Agentic Development Β· Resolution rate (%) | 57.6Unspecified Reasoning Β· toolsΒ· vals-mini-swe | 48.5Unspecified Reasoning Β· toolsΒ· vals-mini-swe | +9.1 pts#15 vs #20 of 90 |
| Vibe Code Bench v1.1Code Generation & Editing Β· Pass rate (%) | 91.9Thinking High Β· tools | 86.7β Max Β· tools | +5.3 pts#4 vs #16 of 121 |
| BioMysteryBenchBiology & Genomics Β· Accuracy (%) | 76.3Thinking High Β· tools | 85.0β Max Β· tools | β8.7 pts#11 vs #1 of 28 |
| Agents' Last Exam v1.1Tool Orchestration Β· Pass rate | 40.2Thinking High Β· toolsΒ· pass-rate | 46.7β Max Β· toolsΒ· pass-rate | β6.5 pts#8 vs #1 of 17 |
| APEX-AgentsTool Orchestration Β· Score | 82.4Reported best | 72.1β Max Β· tools | 1.14Γ#1 vs #5 of 61 |
| AutomationBench-AATool Orchestration Β· Guardrail-safe objective completion rate | 77.5Thinking High Β· tools | 72.5β Max Β· tools | +5.0 pts#3 vs #9 of 18 |
| ChartographyDocuments & Charts Β· Score | 71.6Max Β· no tools | 54.2β Max Β· tools | 1.32Γ#18 vs #23 of 29 |
| Legal Research BenchLegal Β· Score | 54.8Thinking High Β· tools | 41.4β Max Β· tools | 1.33Γ#6 vs #32 of 91 |
| Tax Agent BenchFinance Β· Accuracy (%, rubric Γ citation quality) | 44.6Thinking High Β· tools | 40.4β Max Β· tools | +4.2 pts#25 vs #29 of 74 |
| HLEKnowledge Exams Β· AccuracyNot counted Β· Different or unrecorded test environments β excluded from the tally | 57.1Thinking High Β· no tools Β· text onlyΒ· text-only | 51.7β Max Β· no toolsΒ· legacy-default | β#25 vs #42 of 151 |
| AA Intelligence Index v5.0.1Capability Indices Β· Index (0-100) | 50.4Thinking High Β· tools | 42.9β Max Β· task tools | 1.18Γ#11 vs #18 of 62 |
| Agent ArenaPreference Arenas Β· Net improvement index (percentage points vs. average model) | 10.7Thinking High Β· tools + web | 7.5β Max Β· tools + web | 1.43Γ#10 vs #12 of 35 |
| Agent Arena IndexPreference Arenas Β· Agent Arena Index rating (index points) | 1229Thinking High Β· tools + web | 1189β Extra-High Β· tools + internet | 1.03Γ#13 vs #15 of 36 |
| Vals Index v2.2Capability Indices Β· GDP-weighted accuracy (%) | 69.2Thinking High Β· tools | 63.2β Max Β· tools | +6.0 pts#6 vs #13 of 36 |
Repository Engineering Β· Pass@1 (DeepSWE v1.1)
Agentic Development Β· Resolution rate (%)
Code Generation & Editing Β· Pass rate (%)
Biology & Genomics Β· Accuracy (%)
Tool Orchestration Β· Pass rate
Tool Orchestration Β· Score
Tool Orchestration Β· Guardrail-safe objective completion rate
Documents & Charts Β· Score
Legal Β· Score
Finance Β· Accuracy (%, rubric Γ citation quality)
Knowledge Exams Β· Accuracy
Not counted Β· Different or unrecorded test environments β excluded from the tally
Capability Indices Β· Index (0-100)
Preference Arenas Β· Net improvement index (percentage points vs. average model)
Preference Arenas Β· Agent Arena Index rating (index points)
Capability Indices Β· GDP-weighted accuracy (%)
A dash means no result is available.
Both models publish peak and off-peak prices. Each period is compared separately using the same token mix; hours follow each providerβs schedule.
Drag the handle above the bar for cache hits, the one below it for the input : output mix Β· 5% steps
Blended price = effective input rate at 90% cache hits Γ 80% + output rate Γ 20%
Gemini 4 Argon costs108%morethan Qwen4-Max per million tokens β 2.1Γ the price.Using current effective rates at this token mix.
Gemini 4 Argon: Listed text rates; pricing tier not confirmed.
Qwen4-Max: International pricing. context_length <= 1000000 QwenCloud International (Singapore)
| Price / 1M tokens | Gemini 4 Argon | Qwen4-Max | Ratio |
|---|---|---|---|
| Input | $2.00 | $1.50 | 1.33Γ |
| Output | $10.00 | $4.50 | 2.22Γ |
| Cached input | $0.10 | $0.075 | 1.33Γ |
| Cache write | β | $1.88 | β |
| Blended | $2.23 | $1.07 | 2.08Γ |
Gemini 4 Argon costs316%morethan Qwen4-Max per million tokens β 4.2Γ the price.Using standard list rates after promotions end at this token mix.
Gemini 4 Argon: Standard pricing. Google Gemini API official pricing (ai.google.dev/gemini-api/docs/pricing) verified 2026-10-21; paid tier; standard tier; scheduled price starting 2026-12-01
Qwen4-Max: International pricing. context_length <= 1000000 QwenCloud International (Singapore)
| Price / 1M tokens | Gemini 4 Argon | Qwen4-Max | Ratio |
|---|---|---|---|
| Input | $4.00 | $1.50 | 2.67Γ |
| Output | $20.00 | $4.50 | 4.44Γ |
| Cached input | $0.20 | $0.075 | 2.67Γ |
| Cache write | β | $1.88 | β |
| Blended | $4.46 | $1.07 | 4.16Γ |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
Gemini 4 Argon relative to Qwen4-Max
Summary: 1 of 6 shared benchmarks have matching recorded settings and sources. The average is a geometric mean of 1 positive-cost ratios, one equal weight per benchmark. This benchmark set can include related tests and indexes; it is not a workload cost estimate.
Gemini 4 Argon 4.5Γ more expensive
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ
Gemini 4 Argon 4.5Γ more expensive
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ or are not recorded; interpret the comparison with care.
Gemini 4 Argon
Qwen4-Max
Settings or sources differ or are not recorded; interpret the comparison with care.
Gemini 4 Argon
Qwen4-Max
Settings or sources differ or are not recorded; interpret the comparison with care.
Gemini 4 Argon
Qwen4-Max
Effort, protocol, aggregation and source match; other run conditions may differ.
Gemini 4 Argon
Qwen4-Max
Settings or sources differ or are not recorded; interpret the comparison with care.
Gemini 4 Argon
Qwen4-Max
Settings or sources differ or are not recorded; interpret the comparison with care.
Gemini 4 Argon
Qwen4-Max
| Benchmark | Gemini 4 Argon | Qwen4-Max |
|---|---|---|
| AA Coding Agent Index v1.5 | Not reported | |
| AA Coding Agent Index v2.0 | Not reported | |
| AA Intelligence Index v4.3 | Not reported | |
| AA-Omniscience | Not reported | |
| Agent Arena | $0.694 / task Median Β· Net improvement index (percentage points vs. average model): 10.7 Thinking High (With Tools + Internet) | Not reported |
| ARC-AGI-1 | Not reported | |
| ARC-AGI-2 | Not reported | |
| AutomationBench | $1.70 / task Average Β· Pass Rate: 51.3 Thinking High (With Tools) Β· zapier-private-heldout $1.54 / task Average Β· Pass Rate: 50.1 Thinking Medium (With Tools) Β· zapier-private-heldout | Not reported |
| AutomationBench-AA | $0.6087 / task Average Β· Guardrail-safe objective completion rate: 77.5 Thinking High (With Tools) | Not reported |
| CritPt | Not reported | |
| CursorBench 4.0 | $4.57 / task Average Β· Task score: 52.9 Thinking High (With Tools) Β· cursorbench-4-0-cursor-agent $4.09 / task Average Β· Task score: 50.6 Thinking Low (With Tools) Β· cursorbench-4-0-cursor-agent $4.39 / task Average Β· Task score: 52.8 Thinking Medium (With Tools) Β· cursorbench-4-0-cursor-agent | Not reported |
| CWE-bench v1 | Not reported | |
| FrontierCode 2.0 | $6.514 / task Average Β· Weighted rubric score: 26.3 Thinking High (With Tools + Internet) $3.977 / task Average Β· Weighted rubric score: 21.5 Thinking Low (With Tools + Internet) $5.688 / task Average Β· Weighted rubric score: 23.4 Thinking Medium (With Tools + Internet) | Not reported |
| FrontierCS 2 | Not reported | |
| FrontierSWE v2 | Not reported | |
| GDPx | $12.79 / task Average Β· GDPx β Score: 7.3 Thinking High (With Tools) Β· overall/score | Not reported |
| HLE | $0.1764 / task Average Β· Accuracy: 57.1 Thinking High (No Tools) Β· Text only Β· text-only | Not reported |
| Legal Research Bench | Not reported | |
| LiveBench 2.0 | $1.5159 / task Average Β· Overall score (equal-weight mean of 7 suite scores, 0-100): 84.1 Thinking High (With Tools) | Not reported |
| MedCode | Not reported | |
| MedScribe | Not reported | |
| MysteryMechanism | Not reported | |
| ProofBench v1.1 (Lean 4) | Not reported | |
| Public Benefits Bench v1.1 | Not reported | |
| SAGE | Not reported | |
| SciCode | Not reported | |
| Terminal-Bench 4.1 | Not reported | |
| Terminal-Bench-Science 0.1 | Not reported | |
| Vals Index v2.1 | Not reported | |
| Vibe Code Bench 1-100 | Not reported | |
| WeirdML v3 | $16.2075 / task Average Β· Official score (0-1; higher is better): 0.2 Thinking High (With Tools) | Not reported |
| Attribute | Gemini 4 Argon | Qwen4-Max |
|---|---|---|
| Availability | Available | Available |
| Provider | Google Deep Mind | Alibaba |
| Model type | Multimodal model | Reasoning model |
| First release | October 13, 2026 | November 16, 2026 |
| Context window | 1M tokens | 1M tokens |
| Max output | 1M tokens | 384K tokens |
| Total parameters | β | 2.4T |
| Active parameters | β | 71B |
| Architecture | Undisclosed | Mixture of Experts (MoE) |
| Documented capabilities | Reasoning, Coding, Tool use, Computer use, Long context | Reasoning, Multilingual, Coding, Function calling, Tool use, Structured output, Web search, Long context |
| Input modalities | Text, Image, Audio, Video | Text, Image, Video |
| Output modalities | Text | Text |
| Weights | Closed / API only | Closed / API only |
| Commercial use | Proprietary | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used Gemini 4 Argon or Qwen4-Max? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.