查看中文版 →

Deutsche Version ansehen →

Открыть русскую версию →

Ver versión en español →

Log inChoose a plan
Blog · Model tests

Gemini 4 models compared: Carbon, Neon, Hydrogen, Argon

Four releases in seven weeks split Gemini 4 across four distinct points on the speed, intelligence, and price curve. Here is how Carbon, Neon, Hydrogen, and Argon compare on benchmarks, per-task cost, and daily coding workloads.

Over seven weeks in late 2026, Google shipped four Gemini 4 models: Argon, Carbon, Hydrogen, and Neon. Instead of a simple small-medium-large ladder, each element targets a different point on the capability, latency, and cost curve.

All four share a 1-million-token context window and native multimodal input (text, image, video, audio, PDF), yet their benchmark ceilings, output speeds, thinking levels, and API bills differ sharply.

The short take: Use Gemini 4 Neon as your everyday default for complex coding and agents (high scores 60 on the AA Intelligence Index at less than half the time and cost of Carbon). Route high-frequency edits and subagents to Hydrogen (~140 tok/s at half Neon's price). Carbon and Argon keep their $2 / $10 intro rate only through November 30; once they double to $4 / $20 on December 1, save Carbon for the hardest long-horizon problems.

Positioning and specs across the lineup

Official Gemini 4 family comparison: Carbon, Neon, and Hydrogen across positioning, AA Intelligence Index (60 / 61 / 54), pricing, thinking levels, speed, subscription tiers, and availability
Official Gemini 4 family comparison (excluding Argon, which was removed from the Gemini app picker). Source: Google Official Blog, November 18, 2026.

Putting Argon back into the same table shows how the full four-model lineup fits together:

Positioning, AA Intelligence Index, throughput, thinking levels, context window, and API pricing for Gemini 4 Carbon, Neon, Hydrogen, and Argon
Spec / MetricCarbonNeonHydrogenArgon
Primary focusHardest long-horizon tasks & deep researchComplex coding, knowledge work & scienceFast, low-cost daily coding & subagentsEarly baseline & general automation
AA Intelligence Index (peak)60 (high)61 (xhigh) / 60 (high default)54 (xhigh) / 51 (high)50 (high) / 48 (medium)
Output speed (approx.)57 tok/s110 tok/s140 tok/sModerate-slow
Thinking levelslow, medium, highlow, medium, high (default), xhighlow, medium, high, xhighlow, medium (default), high
Context window1M tokens1M tokens1M tokens1M tokens
API input / output (per 1M)$4 / $20 ($2 / $10 through Nov 30)$3 / $15$1.50 / $7.50$4 / $20 ($2 / $10 through Nov 30)
Cached input (per 1M)$0.20 ($0.10 through Nov 30)$0.15$0.075$0.20 ($0.10 through Nov 30)
CodingPass minimum planPlusGoGoGo

One channel detail to note: Google removed Argon from the Gemini consumer app's model selector (which now lists Auto, Hydrogen, Neon, and Carbon), though gemini-4-argon remains active on the API pricing page and on CodingPass.

As for Gemini 4 Krypton, which has circulated in SVG and video demos on X, it is still an unreleased test checkpoint with no official API pricing or full benchmark suite, so it is left out of production recommendations here.

Benchmarks: coding, long context, and knowledge work

The four models separate along three axes: terminal coding reliability, 1M-token recall, and how many thinking tokens each task burns.

Public benchmark scores and Artificial Analysis task cost/time across Gemini 4 Carbon, Neon, Hydrogen, and Argon
EvaluationCarbonNeonHydrogenArgon
AA Intelligence Index6060 (high) / 61 (xhigh)51 (high) / 54 (xhigh)50 (high)
Terminal-Bench 4.0 / 4.165.2% (4.0)65.2% (4.1) / 61.62% (Vals 4.0)54.04% (4.0)~57.2% (4.0)
GraphWalks (256k–1M)96.2%95.2%—84.2%
Agent Arena+16.2% (#2)1336 Elo (#2)—+11.0% (#7)
AA cost per task (high / max)$7.76 (Dec pricing)$3.74 (high) / $6.44 (xhigh)$3.16 (xhigh)Above median
AA time per task34.2 min (25.6 min early)14.8 min (high) / 22.6 min (xhigh)14.9 min (xhigh)Slower

Carbon: highest ceiling, slowest turnaround

Carbon is built for long-horizon reasoning where exploring multiple hypotheses matters more than speed. It tops GraphWalks (256k–1M) at 96.2% and ranked #1 in Agent Arena on mid-session course correction when users push back or change requirements.

The trade-off is heavy token consumption and latency. Across the full Artificial Analysis Intelligence Index suite, Carbon emitted 205M tokens versus a 72.8M peer median, running around 57 tok/s and averaging 25.6 to 34.2 minutes per task.

Neon: the practical flagship for daily work

Adapted from Carbon, Neon hits the same 60-point AA Intelligence Index score at its default high level while cutting time per task from 34.2 minutes to 14.8 minutes and cost from $7.76 (post-December pricing) to $3.74.

On several domain benchmarks, Neon beats Carbon outright:

  • Coding: #1 overall on the AA Coding Agent Index (58.6), and 39.0% on SWE-sweep inside Google Antigravity.
  • Finance and legal: #1 on both Vals Finance (68.32%) and Vals Legal (78.36%), plus #1 on AA-Briefcase presentation quality (1771 Elo).
  • Agent discipline: Google reports Neon has the lowest hallucination rate in the Gemini 4 family, cutting incomplete-task shortcuts by 43%–56% and unrequested edits by 15%–35% versus Carbon.

Hydrogen: the high-throughput execution layer

Hydrogen is also adapted from Carbon, tuned for ~140 tok/s output at half of Neon's per-token price ($1.50 / $7.50). When pushed to xhigh, Hydrogen reaches 54 on the AA Intelligence Index—outscoring the earlier Argon (50).

In Google Antigravity's Orchestrator mode, pairing Carbon or Neon as the planner with Hydrogen for file edits, dependency bumps, and test runs achieves near-Carbon success rates on Terminal-Bench while finishing roughly 19% faster and using about 24% less quota.

Argon: squeezed from both sides

Argon launched first with strong long-context recall (84.2% on GraphWalks) and native multimodal streaming. Once Hydrogen and Neon arrived, Argon lost its niche: its Intelligence Index (50) trails Hydrogen (high 51 / xhigh 54), and after the December 1 increase to $4 / $20, it costs more per token than Neon ($3 / $15). Unless an existing pipeline is tuned around Argon's medium default, new workloads have little reason to pick it.

Thinking levels and monthly workload bills

Neon and Hydrogen expose four thinking levels (low, medium, high, xhigh), while Carbon and Argon offer three (low, medium, high). Defaults differ too: Argon defaults to medium, whereas Carbon and Neon default to high. Migrating from Argon to Neon without setting reasoning_effort: "medium" will noticeably increase output token counts.

Assuming 20,000 input tokens per request (50% implicit cache hit at 5% of input rate) and 2,000 output tokens, monthly API bills scale as follows:

Estimated monthly API bills across Gemini 4 models assuming 20K input tokens (50% cached) and 2K output tokens per request
ModelPer request10K req100K req1M req
Gemini 4 Hydrogen$0.031$308$3,075$30,750
Gemini 4 Neon$0.062$615$6,150$61,500
Carbon / Argon (through Nov 30)$0.041$410$4,100$41,000
Carbon / Argon (from Dec 1)$0.082$820$8,200$82,000

Caveats and benchmark limits

Four caveats matter when reading the numbers above:

  • SWE-sweep reflects the Antigravity harness: Neon's 39.0% score was recorded inside Google Antigravity. On the standardized mini-SWE harness, Neon drops to 12.8%—just 1.2 points ahead of GPT-6.2 Sol (11.6%).
  • Neon xhigh has steep diminishing returns: Stepping from high to xhigh adds 1 Intelligence Index point (60 to 61) while raising per-task cost by 72% ($3.74 to $6.44), adding nearly 8 minutes, and regressing on GDP.pdf document reading (33.4% down to 28.0%).
  • Carbon and Argon double on December 1: Their $2 / $10 rate is an introductory tier through November 30. Once $4 / $20 takes effect, the same monthly allowance buys half as many tokens.
  • Simple tasks can flip the cost order: On Plotly's 43-question data analysis benchmark, all four Gemini 4 models earned an A, but total spend ran Hydrogen $6, Carbon $11, Argon $13, and Neon $17 because Neon's high default generates more thinking tokens on well-guided prompts.

CodingPass allowances and quick start

CodingPass meters all four Gemini 4 models at official Google API rates. Hydrogen, Neon, and Argon start on Go; Carbon starts on Plus:

Monthly token allowances for Gemini 4 models on CodingPass Go, Plus, and Pro
ModelMin planGoPlusPro
Gemini 4 HydrogenGo305M1.0B2.5B
Gemini 4 NeonGo205M508M1.3B
Gemini 4 ArgonGo205M761M1.9B
Gemini 4 CarbonPlus—761M1.9B

Switch models per request on a single key and set reasoning_effort to match the job:

Terminal
curl https://codingpass.ai/v1/chat/completions \  -H "Authorization: Bearer $CODINGPASS_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "gemini-4-neon",    "reasoning_effort": "medium",    "messages": [{"role": "user", "content": "Review the diff in src/billing/ for race conditions"}]  }'

Workload decision table

Recommended Gemini 4 model and thinking level by workload
WorkloadRecommendedRationale and trade-off
Routine edits, unit tests, high-volume subagentsHydrogen (medium / high)~140 tok/s at half of Neon's price; avoids overthinking simple prompts
Multi-file refactors, debugging, primary coding agentNeon (high default)Matches Carbon's 60 AA score in less than half the time and cost
Financial, legal, and spreadsheet analysisNeon (high)#1 on Vals Finance & Legal; avoid xhigh where document reading drops
Stuck architectural bugs, 1M-token repo auditsCarbon (high) or Neon (xhigh)96.2% on GraphWalks; expect 30+ minute runs and higher token spend
Existing Argon workflowsMigrate to Neon (medium)Argon is slower and pricier after Dec 1; medium keeps output tokens in check

For most teams, Neon (medium or high) is the right default, with Hydrogen handling fast subagent loops and Carbon reserved for problems that stall Neon twice in a row.

FAQ

Which Gemini 4 model is best for coding?
Gemini 4 Neon (default high) is the best primary coding model, ranking #1 on the AA Coding Agent Index while running over twice as fast as Carbon. Pair it with Hydrogen for fast subagent edits and test runs.
What should I watch out for when switching from Argon to Neon?
Set reasoning_effort explicitly to medium. Argon defaults to medium, whereas Neon defaults to high, which generates noticeably more thinking tokens if left at the default.
Does CodingPass Go include all four Gemini 4 models?
Go includes Hydrogen, Neon, and Argon; Carbon requires Plus or Pro. All models meter at official Google API rates from the same monthly allowance. See Usage limits for full cap rules.
Boarding

All four Gemini 4 models, on one key.

Go, Plus and Pro meter at official API prices. No surprise charges, cancel anytime.

  • Request ID on every response
  • Full refund if you've used 5% or less
  • No surprise charges
Choose GoOpenCode guide

$10/mo until you cancel.