Across 16 comparable benchmarks, Gemini 4 Argon has better reported results on 16 and worse on 0. 2 further shared results are listed below, each with the reason it is not counted.
Strong evidence16 of 18 shared results countedHow we compare
Price basis: Current effective rates. The price section below shows the applicable periods.
| Fact | Gemini 4 Argon | Gemini 3.0 Flash |
|---|---|---|
| Context window | 1M tokens | 1M tokens |
| Input / 1M | $2.00 | $0.500 |
| Output / 1M | $10.00 | $3.00 |
| Blended (4:1) | $1.12 | $0.676 |
| Status | Available | Preview |
| Released | October 13, 2026 | December 17, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates β set your own mix.
Mean of 12 shared benchmarks grouped by capability on a 0β100 scale. How averages are built
Gemini 4 Argon ahead on 2 of 2 counted
Gemini 4 Argon ahead on 2 of 2 counted
Gemini 4 Argon ahead on 2 of 2 counted
Gemini 4 Argon ahead on 4 of 4 counted
Gemini 4 Argon ahead on 6 of 6 counted
No shared comparable results for Computer & tool use, Research & search, Long context, Multimodal, Cybersecurity.
Published scores, with matching modes where available. Gaps show Gemini 4 Argon relative to Gemini 3.0 Flash. Reading the results
| Benchmark | Gemini 4 Argon | Gemini 3.0 Flash | Gap |
|---|---|---|---|
| Code MigrationMaintenance & Optimization Β· Hidden-test pass rate (%) | 68.2Thinking High Β· tools | 6.4Thinking High Β· tools | +61.8 pts#3 vs #70 of 79 |
| Vibe Code Bench v1.1Code Generation & Editing Β· Pass rate (%) | 91.9Thinking High Β· tools | 20.2Thinking High Β· tools | +71.7 pts#4 vs #87 of 121 |
| ARC-AGI-1Abstract Generalization Β· Score (%) | 98.5Thinking Medium Β· no tools | 84.7β Thinking High Β· no tools | +13.8 pts#1 vs #46 of 87 |
| ARC-AGI-2Abstract Generalization Β· Score (% solved); cost per task (USD)Not counted Β· Speed and cost telemetry is reported, not scored | 91.3Thinking High Β· no tools | 33.6Thinking High Β· no tools | 2.71Γ#8 vs #51 of 80 |
| SimpleBenchCommonsense Β· Score (AVG@5) | 91.7Reported best | 61.1β Normal Β· no tools | 1.50Γ#4 vs #43 of 106 |
| FrontierMath Tier 4 v2Mathematics Β· Accuracy (verification_code) | 78.0Thinking High Β· tools | 17.1β Reported best | +61.0 pts#13 vs #53 of 73 |
| FrontierMath v2Mathematics Β· Accuracy (verification_code) | 86.0Thinking High Β· tools | 51.2β Reported best | +34.7 pts#13 vs #55 of 85 |
| CritPtScientific Reasoning Β· Score | 27.1Thinking High Β· no tools | 8.6β Thinking Β· no tools | 3.16Γ#17 vs #61 of 134 |
| GPQA DiamondScientific Reasoning Β· Accuracy | 96.4Thinking High Β· no tools | 90.4β Thinking Β· no tools | +6.0 pts#2 vs #48 of 200 |
| MedCodeClinical Workflows Β· Accuracy (%) | 58.8Thinking High Β· tools | 55.9Thinking High Β· tools | +2.9 pts#3 vs #5 of 97 |
| MedScribeClinical Workflows Β· Rubric pass rate (%) | 87.4Thinking High Β· tools | 69.9Thinking High Β· tools | +17.5 pts#17 vs #87 of 99 |
| EMB (Excel Modeling)Finance Β· Accuracy (%) | 75.2Thinking High Β· tools | 26.0Thinking High Β· tools | +49.2 pts#6 vs #70 of 78 |
| Finance Agent v2Finance Β· Score | 65.4Max Β· tools | 42.5β Thinking High Β· tools | 1.54Γ#1 vs #58 of 75 |
| Harvey's Legal Agent BenchmarkLegal Β· Accuracy (%) | 19.6Thinking High Β· tools | 0.0Thinking High Β· tools | +19.6 pts#4 vs #44 of 52 |
| Legal Research BenchLegal Β· Score | 54.8Thinking High Β· tools | 18.3Thinking High Β· tools | 3.00Γ#6 vs #69 of 91 |
| SAGEService Workflows Β· Accuracy (%) | 53.6Thinking High Β· tools | 51.9Thinking High Β· tools | +1.8 pts#5 vs #10 of 82 |
| Tax Agent BenchFinance Β· Accuracy (%, rubric Γ citation quality) | 44.6Thinking High Β· tools | 11.8Thinking High Β· tools | +32.7 pts#25 vs #63 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 | 43.5β Thinking Β· toolsΒ· legacy-default | β#25 vs #71 of 151 |
Maintenance & Optimization Β· Hidden-test pass rate (%)
Code Generation & Editing Β· Pass rate (%)
Abstract Generalization Β· Score (%)
Abstract Generalization Β· Score (% solved); cost per task (USD)
Not counted Β· Speed and cost telemetry is reported, not scored
Commonsense Β· Score (AVG@5)
Mathematics Β· Accuracy (verification_code)
Mathematics Β· Accuracy (verification_code)
Scientific Reasoning Β· Score
Scientific Reasoning Β· Accuracy
Clinical Workflows Β· Accuracy (%)
Clinical Workflows Β· Rubric pass rate (%)
Finance Β· Accuracy (%)
Finance Β· Score
Legal Β· Accuracy (%)
Legal Β· Score
Service Workflows Β· Accuracy (%)
Finance Β· Accuracy (%, rubric Γ citation quality)
Knowledge Exams Β· Accuracy
Not counted Β· Different or unrecorded test environments β excluded from the tally
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 costs230%morethan Gemini 3.0 Flash per million tokens β 3.3Γ the price.Using current effective rates at this token mix.
Gemini 4 Argon: Listed text rates; pricing tier not confirmed.
Gemini 3.0 Flash: Standard pricing. Google Gemini API official pricing (ai.google.dev/gemini-api/docs/pricing) verified 2026-11-13; paid tier; standard tier; text input Google Gemini API official pricing (ai.google.dev/gemini-api/docs/pricing) verified 2026-11-13; paid tier; standard tier; output
| Price / 1M tokens | Gemini 4 Argon | Gemini 3.0 Flash | Ratio |
|---|---|---|---|
| Input | $2.00 | $0.50 | 4.00Γ |
| Output | $10.00 | $3.00 | 3.33Γ |
| Cached input | $0.10 | $0.05 | 2.00Γ |
| Cache write | β | β | β |
| Blended | $2.23 | $0.676 | 3.30Γ |
Gemini 4 Argon costs560%morethan Gemini 3.0 Flash per million tokens β 6.6Γ 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
Gemini 3.0 Flash: Standard pricing. Google Gemini API official pricing (ai.google.dev/gemini-api/docs/pricing) verified 2026-11-13; paid tier; standard tier; text input Google Gemini API official pricing (ai.google.dev/gemini-api/docs/pricing) verified 2026-11-13; paid tier; standard tier; output
| Price / 1M tokens | Gemini 4 Argon | Gemini 3.0 Flash | Ratio |
|---|---|---|---|
| Input | $4.00 | $0.50 | 8.00Γ |
| Output | $20.00 | $3.00 | 6.67Γ |
| Cached input | $0.20 | $0.05 | 4.00Γ |
| Cache write | β | β | β |
| Blended | $4.46 | $0.676 | 6.60Γ |
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 Gemini 3.0 Flash
Summary: 7 of 7 shared benchmarks have matching recorded settings and sources. The average is a geometric mean of 7 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 34.5Γ more expensive
Gemini 4 Argon 22.2Γ more expensive
Gemini 4 Argon 10.2Γ more expensive
Gemini 4 Argon 8.6Γ more expensive
Gemini 4 Argon 5.4Γ more expensive
Gemini 4 Argon 1.4Γ more expensive
Gemini 4 Argon 1.1Γ cheaper
Gemini 4 Argon 34.5Γ more expensive
Gemini 4 Argon 22.2Γ more expensive
Gemini 4 Argon 10.2Γ more expensive
Gemini 4 Argon 8.6Γ more expensive
Gemini 4 Argon 5.4Γ more expensive
Gemini 4 Argon 1.4Γ more expensive
Gemini 4 Argon 1.1Γ cheaper
Effort, protocol, aggregation and source match; other run conditions may differ.
Gemini 4 Argon
Gemini 3.0 Flash
Effort, protocol, aggregation and source match; other run conditions may differ.
Gemini 4 Argon
Gemini 3.0 Flash
Effort, protocol, aggregation and source match; other run conditions may differ.
Gemini 4 Argon
Gemini 3.0 Flash
Effort, protocol, aggregation and source match; other run conditions may differ.
Gemini 4 Argon
Gemini 3.0 Flash
Effort, protocol, aggregation and source match; other run conditions may differ.
Gemini 4 Argon
Gemini 3.0 Flash
Effort, protocol, aggregation and source match; other run conditions may differ.
Gemini 4 Argon
Gemini 3.0 Flash
Effort, protocol, aggregation and source match; other run conditions may differ.
Gemini 4 Argon
Gemini 3.0 Flash
| Benchmark | Gemini 4 Argon | Gemini 3.0 Flash |
|---|---|---|
| AA Coding Agent Index v1.5 | Not reported | |
| AA Coding Agent Index v2.0 | Not reported | |
| AA Intelligence Index v4.3 | Not reported | |
| AA Intelligence Index v5.0.1 | 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 |
| Agent Arena Index | $0.6569 / task Median Β· Agent Arena Index rating (index points): 1229 Thinking High (With Tools + Internet) | Not reported |
| AIME 2026 | 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 |
| Code Migration | 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 | |
| EMB (Excel Modeling) | Not reported | |
| Finance Agent v2 | 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 |
| MysteryMechanism | Not reported | |
| ProofBench v1.1 (Lean 4) | Not reported | |
| Public Benefits Bench v1.1 | Not reported | |
| SciCode | Not reported | |
| Terminal-Bench 4.0 | $16.8269 / task Average Β· Resolution rate (%): 55.6 Thinking High (With Tools) Β· vals-effort-study $13.4495 / task Average Β· Resolution rate (%): 52.5 Thinking Low (With Tools) Β· vals-effort-study 2 more settings$13.3909 / task Average Β· Resolution rate (%): 56.6 Thinking Medium (With Tools) Β· vals-effort-study $17.64 / task Average Β· Resolution rate (%): 57.6 Unspecified Reasoning (With Tools) Β· vals-mini-swe | Not reported |
| Terminal-Bench 4.1 | Not reported | |
| Terminal-Bench-Science 0.1 | Not reported | |
| Vals Index v2.1 | Not reported | |
| Vals Index v2.2 | 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 | Gemini 3.0 Flash |
|---|---|---|
| Availability | Available | Preview |
| Provider | Google Deep Mind | Google Deep Mind |
| Model type | Multimodal model | Chat model |
| First release | October 13, 2026 | December 17, 2025 |
| Context window | 1M tokens | 1M tokens |
| Max output | 1M tokens | 64K tokens |
| Architecture | Undisclosed | Undisclosed |
| Documented capabilities | Reasoning, Coding, Tool use, Computer use, Long context | Reasoning, Multilingual |
| Input modalities | Text, Image, Audio, Video | Text, Image, Audio, 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 Gemini 3.0 Flash? 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.