Across 16 comparable benchmarks, Gemini 4 Neon has better reported results on 14 and worse on 2. 4 further shared results are listed below, each with the reason it is not counted.
Moderate evidence16 of 20 shared results countedHow we compare
Price basis: Current effective rates. The price section below shows the applicable periods.
| Fact | Gemini 4 Neon | Gemini 4 Argon |
|---|---|---|
| Context window | 1M tokens | 1M tokens |
| Input / 1M | $3.00 | $2.00 |
| Output / 1M | $15.00 | $10.00 |
| Blended (4:1) | $3.35 | $1.12 |
| Status | Available | Available |
| Released | November 18, 2026 | October 13, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates β set your own mix.
Mean of 9 shared benchmarks grouped by capability on a 0β100 scale. How averages are built
Gemini 4 Neon ahead on 5 of 5 counted
Gemini 4 Neon ahead on 2 of 3 counted
Gemini 4 Neon ahead on 1 of 1 counted
Split 1β1 of 2 counted
Gemini 4 Neon 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 Neon relative to Gemini 4 Argon. Reading the results
| Benchmark | Gemini 4 Neon | Gemini 4 Argon | Gap |
|---|---|---|---|
| AA Coding Agent Index v2.0Coding Indices Β· Index (0-100) | 58.6Extra-High Β· tools | 53.2β Thinking High Β· tools | 1.10Γ#5 vs #9 of 10 |
| FrontierCode 2.0Repository Engineering Β· Weighted rubric score | 46.2Thinking High Β· tools + web | 26.3Thinking High Β· tools + web | 1.76Γ#3 vs #16 of 32 |
| SWE-sweepRepository Engineering Β· Bugs resolved (%) | 12.8Extra-High Β· tools | 4.3β Max Β· tools | +8.5 pts#2 vs #8 of 20 |
| Terminal-Bench 4.0Agentic Development Β· Resolution rate (%)Not counted Β· Different or unrecorded test environments β excluded from the tally | 63.6Extra-High Β· toolsΒ· legacy-default | 57.6β Unspecified Reasoning Β· toolsΒ· vals-mini-swe | β#7 vs #15 of 90 |
| Terminal-Bench 4.1Agentic Development Β· Resolution rate (%) | 65.2Extra-High Β· tools | 55.5β Thinking High Β· tools | +9.8 pts#3 vs #12 of 48 |
| Vibe Code Bench v1.1Code Generation & Editing Β· Pass rate (%) | 93.7Extra-High Β· tools | 91.9β Thinking High Β· tools | +1.8 pts#2 vs #4 of 119 |
| Vending-Bench 2Logical Planning Β· Money Balance (USD)Not counted Β· Speed and cost telemetry is reported, not scored | 16843Unspecified Reasoning Β· tools | 13718Unspecified Reasoning Β· tools | 1.23Γ#1 vs #6 of 64 |
| MysteryMechanismScientific Reasoning Β· Accuracy (%) | 45.0Extra-High Β· tools | 45.5β Thinking High Β· tools | β0.4 pts#9 vs #8 of 32 |
| Terminal-Bench-Science 0.1Scientific Computing Β· Task success rate (%) | 70.0Extra-High Β· tools | 52.9β Thinking High Β· tools | +17.1 pts#4 vs #12 of 32 |
| BioMysteryBenchBiology & Genomics Β· Accuracy (%) | 80.0Extra-High Β· tools | 76.3β Thinking High Β· tools | +3.7 pts#6 vs #11 of 28 |
| Agents' Last Exam v1.1Tool Orchestration Β· Pass rateNot counted Β· Different or unrecorded test environments β excluded from the tally | 75.8Extra-High Β· toolsΒ· score | 40.2β Thinking High Β· toolsΒ· pass-rate | β#1 vs #12 of 21 |
| AutomationBench-AATool Orchestration Β· Guardrail-safe objective completion rate | 79.3Extra-High Β· tools | 77.5β Thinking High Β· tools | +1.8 pts#1 vs #3 of 15 |
| ChartographyDocuments & Charts Β· Score | 73.5Extra-High Β· no tools | 71.6β Max Β· no tools | 1.03Γ#15 vs #17 of 24 |
| LVBenchVideo Understanding Β· Accuracy (%) | 89.0Extra-High Β· no tools | 91.7β Max Β· no tools | β2.7 pts#2 vs #1 of 7 |
| AutomationBenchOffice & Business Β· Pass RateNot counted Β· Different or unrecorded test environments β excluded from the tally | 56.3Extra-High Β· toolsΒ· zapier-private-heldout | 51.3β Max Β· toolsΒ· legacy-default | β#3 vs #11 of 64 |
| Legal Research BenchLegal Β· Score | 56.3Extra-High Β· tools + internet | 54.8β Thinking High Β· tools | 1.03Γ#1 vs #6 of 91 |
| Tax Agent BenchFinance Β· Accuracy (%, rubric Γ citation quality) | 54.9Extra-High Β· tools + internet | 44.6β Thinking High Β· tools | +10.3 pts#22 vs #25 of 74 |
| Reported separately from the capability domains; not included in the averages. Read each metricβs direction β lower can be better. | |||
| AA-OmniscienceHonesty & Factuality Β· AA-Omniscience Index | 54.8Extra-High Β· no tools | 42.4β Thinking High Β· no tools | 1.29Γ#1 vs #6 of 16 |
| AA Intelligence Index v5.0.1Capability Indices Β· Index (0-100) | 61.4Extra-High Β· tools | 50.4β Thinking High Β· tools | 1.22Γ#3 vs #11 of 61 |
| Vals Index v2.2Capability Indices Β· GDP-weighted accuracy (%) | 70.9Extra-High Β· tools | 69.2β Thinking High Β· tools | +1.6 pts#2 vs #6 of 34 |
Coding Indices Β· Index (0-100)
Repository Engineering Β· Weighted rubric score
Repository Engineering Β· Bugs resolved (%)
Agentic Development Β· Resolution rate (%)
Not counted Β· Different or unrecorded test environments β excluded from the tally
Agentic Development Β· Resolution rate (%)
Code Generation & Editing Β· Pass rate (%)
Logical Planning Β· Money Balance (USD)
Not counted Β· Speed and cost telemetry is reported, not scored
Scientific Reasoning Β· Accuracy (%)
Scientific Computing Β· Task success rate (%)
Biology & Genomics Β· Accuracy (%)
Tool Orchestration Β· Pass rate
Not counted Β· Different or unrecorded test environments β excluded from the tally
Tool Orchestration Β· Guardrail-safe objective completion rate
Documents & Charts Β· Score
Video Understanding Β· Accuracy (%)
Office & Business Β· Pass Rate
Not counted Β· Different or unrecorded test environments β excluded from the tally
Legal Β· Score
Finance Β· Accuracy (%, rubric Γ citation quality)
Honesty & Factuality Β· AA-Omniscience Index
Capability Indices Β· Index (0-100)
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 Neon costs50%morethan Gemini 4 Argon per million tokens.Using current effective rates at this token mix.
Gemini 4 Neon: Standard pricing. Unified 1M context pricing; thinking tokens included in output; paid tier only (no free tier).
Gemini 4 Argon: Listed text rates; pricing tier not confirmed.
| Price / 1M tokens | Gemini 4 Neon | Gemini 4 Argon | Ratio |
|---|---|---|---|
| Input | $3.00 | $2.00 | 1.50Γ |
| Output | $15.00 | $10.00 | 1.50Γ |
| Cached input | $0.15 | $0.10 | 1.50Γ |
| Cache write | β | β | β |
| Blended | $3.35 | $2.23 | 1.50Γ |
Gemini 4 Neon costs25%lessthan Gemini 4 Argon per million tokens.Using standard list rates after promotions end at this token mix.
Gemini 4 Neon: Standard pricing. Unified 1M context pricing; thinking tokens included in output; paid tier only (no free tier).
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
| Price / 1M tokens | Gemini 4 Neon | Gemini 4 Argon | Ratio |
|---|---|---|---|
| Input | $3.00 | $4.00 | 0.75Γ |
| Output | $15.00 | $20.00 | 0.75Γ |
| Cached input | $0.15 | $0.20 | 0.75Γ |
| Cache write | β | β | β |
| Blended | $3.35 | $4.46 | 0.75Γ |
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 Neon relative to Gemini 4 Argon
Summary: 1 of 5 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 Neon 2.7Γ cheaper
Settings or sources differ
Settings or sources differ
Settings or sources differ
Settings or sources differ
Gemini 4 Neon 2.7Γ cheaper
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 Neon
Gemini 4 Argon
Effort, protocol, aggregation and source match; other run conditions may differ.
Gemini 4 Neon
Gemini 4 Argon
Settings or sources differ or are not recorded; interpret the comparison with care.
Gemini 4 Neon
Gemini 4 Argon
Settings or sources differ or are not recorded; interpret the comparison with care.
Gemini 4 Neon
Gemini 4 Argon
Settings or sources differ or are not recorded; interpret the comparison with care.
Gemini 4 Neon
Gemini 4 Argon
| Benchmark | Gemini 4 Neon | Gemini 4 Argon |
|---|---|---|
| AA Coding Agent Index v1.5 | Not reported | |
| AA Intelligence Index v4.3 | Not reported | |
| AA-Omniscience | Not reported | |
| Agent Arena | Not reported | $0.694 / task Median Β· Net improvement index (percentage points vs. average model): 10.7 Thinking High (With Tools + Internet) |
| ARC-AGI-1 | Not reported | |
| ARC-AGI-2 | Not reported | |
| AutomationBench | Not reported | $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 |
| AutomationBench-AA | Not reported | $0.6087 / task Average Β· Guardrail-safe objective completion rate: 77.5 Thinking High (With Tools) |
| CritPt | Not reported | |
| CursorBench 4.0 | Not reported | $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 |
| CWE-bench v1 | Not reported | |
| FrontierCode 2.0 | Not reported | $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) |
| FrontierCS 2 | Not reported | |
| FrontierSWE v2 | Not reported | |
| GDPx | Not reported | $12.79 / task Average Β· GDPx β Score: 7.3 Thinking High (With Tools) Β· overall/score |
| HLE | Not reported | $0.1764 / task Average Β· Accuracy: 57.1 Thinking High (No Tools) Β· Text only Β· text-only |
| Legal Research Bench | Not reported | |
| LiveBench 2.0 | Not reported | $1.5159 / task Average Β· Overall score (equal-weight mean of 7 suite scores, 0-100): 84.1 Thinking High (With Tools) |
| 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 4.0 | Not reported | $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 |
| 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 | Not reported | $16.2075 / task Average Β· Official score (0-1; higher is better): 0.2 Thinking High (With Tools) |
| Attribute | Gemini 4 Neon | Gemini 4 Argon |
|---|---|---|
| Availability | Available | Available |
| Provider | Google Deep Mind | Google Deep Mind |
| Model type | Multimodal model | Multimodal model |
| First release | November 18, 2026 | October 13, 2026 |
| Context window | 1M tokens | 1M tokens |
| Max output | 1M tokens | 1M tokens |
| Architecture | Undisclosed | Undisclosed |
| Documented capabilities | Reasoning, Coding, Tool use, Computer use, Long context, Function calling, Structured output, Web search | Reasoning, Coding, Tool use, Computer use, Long context |
| Knowledge cutoff | 2026-03 | β |
| 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 Neon or Gemini 4 Argon? 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.