BenchLeader

Gemini 4 Neon vs GPT-5.4

Full profiles: Gemini 4 Neon (Google) and GPT-5.4 (OpenAI): every benchmark, price and rank.

Updated · Data from 12 sources

As of 19 Nov 2026, Gemini 4 Neon is ahead of GPT-5.4 on quality (67.3 vs 63.0 on the BenchLeader Index), and they cost about the same at $6.00 vs $5.63 per 1M tokens blended. Gemini 4 Neon leads in every category we measure both in. Gemini 4 Neon streams faster.

Key facts (as of 19 Nov 2026)

  • Gemini 4 Neon scores 67.3 on the BenchLeader Index and GPT-5.4 scores 63.0 (BenchLeader, 19 Nov 2026).
  • Gemini 4 Neon costs $6.00 per 1M tokens blended (list price, 19 Nov 2026).
  • GPT-5.4 costs $5.63 per 1M tokens blended (list price, 19 Nov 2026).
  • Gemini 4 Neon streams faster than GPT-5.4 (Artificial Analysis, 7-day median, 19 Nov 2026).

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 casePickWhyConfidence
CodingGemini 4 Neon73 vs 65 category scoreHigh
Agents & tool useGemini 4 Neon76 vs 63 category scoreHigh
ReasoningGemini 4 Neon72 vs 65 category scoreMedium
KnowledgeGemini 4 Neon72 vs 58 category scoreHigh
Chat quality (human preference)–Only Gemini 4 Neon has an Arena rating (72 category score)Not comparable
Lowest costEither$6.00 vs $5.63 per 1M blended; agentic coding session $0.240 vs $0.210–
Fastest first answerGemini 4 Neon40.6 s (Gemini 4 Neon (high)) vs 104.6 s (GPT-5.4 (xhigh)) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • Gemini 4 Neon (high) leads on quality: 67.3 vs 63.0.
  • Gemini 4 Neon (high) is stronger in agents & tools, coding, knowledge, reasoning.
  • They cost about the same ($5.63 per 1M blended).
  • Gemini 4 Neon (high) streams 1.6× faster (101 vs 65 tokens per second).

At a glance

SpecGemini 4 NeonGPT-5.4
DeveloperGoogleOpenAI
Released18 Nov 20265 Mar 2026
Context window (tokens)1,048,5761,050,000
Compared atGemini 4 Neon (high)GPT-5.4 (xhigh)
Open weightsNoNo
Price in / out / cached input per 1M$3.00 / $15.00 / $0.150$2.50 / $15.00 / $0.250

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.

CategoryGemini 4 Neon (high)GPT-5.4 (xhigh)Leader
Reasoning71.965.3Gemini 4 Neon
Coding73.464.7Gemini 4 Neon
Agents & tools76.263.0Gemini 4 Neon
Maths–64.7not comparable
Knowledge72.358.4Gemini 4 Neon
Instruction following–72.4not comparable
Human preference71.7–not comparable
Multimodal–60.5not comparable
Long context–65.7not comparable

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsKnowledgeGemini 4 Neon, Reasoning: 71.9Gemini 4 Neon, Coding: 73.4Gemini 4 Neon, Agents & tools: 76.2Gemini 4 Neon, Knowledge: 72.3GPT-5.4, Reasoning: 65.3GPT-5.4, Coding: 64.7GPT-5.4, Agents & tools: 63.0GPT-5.4, Knowledge: 58.4

Not drawn, measured for fewer than two of these models: Maths, Instruction following, Long context, Multimodal, Human preference.

Model, click to add or removeIndex

Where sources disagree

Across the 0 benchmarks both have, Gemini 4 Neon leads 0, GPT-5.4 leads 0. Every overall index that rates both puts Gemini 4 Neon ahead.

Overall indexGemini 4 Neon (high)GPT-5.4 (xhigh)Leader
BenchLeader Index67.363.0Gemini 4 Neon
Arena Text15191475†Gemini 4 Neon

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. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureGemini 4 Neon (high)GPT-5.4 (xhigh)
Blended price per 1M tokens$6.00$5.63
Input / output per 1M$3.00 / $15.00$2.50 / $15.00
Cached input per 1M$0.150$0.250
Price per task: chat reply$0.0057$0.0055
Price per task: summarize a 30-page report$0.045$0.039
Price per task: code edit$0.041$0.037
Price per task: agentic coding session$0.240$0.210
Price per task: structured extraction$0.0090$0.0080
Agentic coding session, input mostly cached$0.112$0.109
Cost per benchmark task (AA Index)$3.74–
Output tokens per task (AA Index)90k–
Of which reasoning46k–
Time per task (AA Index)15 min–
Output speed101 tok/s65 tok/s
Time to first answer40.6 s104.6 s
Time to a complete answer, last measured 13 Nov 2026–193.1 s

Each model is compared at its best-ranked reasoning-effort setting. Gemini 4 Neon (high) scores 67.3 and takes 41 s to its first answer token; Gemini 4 Neon (xhigh) scores 64.3 in 57 s. GPT-5.4 (xhigh) scores 63.0 and takes 105 s to its first answer token; GPT-5.4 (low) scores 58.7 in 3 s, GPT-5.4 (high) scores 58.3 in 2 s. 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

142 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.

MetricPublisherGemini 4 Neon (high)GPT-5.4 (xhigh)
BenchLeader IndexBenchLeader67.363.0
Agents & tools scoreBenchLeader76.263.0
Coding scoreBenchLeader73.464.7
Human preference scoreBenchLeader71.7–
Knowledge scoreBenchLeader72.358.4
Reasoning scoreBenchLeader71.965.3
Instruction following scoreBenchLeader–72.4
Long context scoreBenchLeader–65.7
Maths scoreBenchLeader–64.7
Multimodal scoreBenchLeader–60.5
Blended price $/MBenchLeader$6.00$5.63
Output speedBenchLeader101 tok/s65 tok/s
Time to first answerBenchLeader40.6 s104.6 s
Context windowBenchLeader1,048,576 tokens1,050,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub–93.3%
Humanity's Last ExamScale AI / CAIS–36.2%
Arena Hard PromptsArena (LMArena)15461487†
LiveBench 2.0 ReasoningLiveBench89.6%†–
LiveBench 1.0 ReasoningLiveBench–88.1%
GPQA Diamond (AA)Artificial Analysis–92.0%
Humanity's Last Exam (AA)Artificial Analysis–43.7%
HLE-Diamond (AA)Artificial Analysis68.4%–
GPQA Diamond (Vals)Vals AI–91.7%
Kagi LLM BenchmarkKagi LLM Benchmark–63.8%†
ARC-AGI-1ARC Prize–93.7%
ARC-AGI-2ARC Prize–74.0%
ARC-AGI-3ARC Prize–0.2%†
CritPtArtificial Analysis–23.4%
CritPt v2 hard subset (AA)Artificial Analysis59.0%–
Arena ExpertArena (LMArena)15411491†
Chess PuzzlesEpoch AI Benchmarking Hub–48.0%
Mystery Game PuzzlesEpoch AI Benchmarking Hub–37.0%
CL-benchEpoch AI Benchmarking Hub–27.9%
CL-bench LifeEpoch AI Benchmarking Hub–21.7%
LMCAEpoch AI Benchmarking Hub–52.0%
DTBenchEpoch AI Benchmarking Hub–94.4%
ForecastBenchForecastBench–62.7%†
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub–76.9%†
SciCodeSciCode–56.6%
Show all 142 benchmarks
MetricPublisherGemini 4 Neon (high)GPT-5.4 (xhigh)
Coding
WeirdMLWeirdML–77.7%
GSO-BenchGSO-Bench–31.4%
Arena CodingArena (LMArena)15581511†
Arena WebDevArena (LMArena)17641400†
LiveBench 2.0 CodingLiveBench89.7%†–
LiveBench 1.0 CodingLiveBench–77.5%
LiveCodeBenchVals AI–84.1%
SWE-bench (Vals)Vals AI–78.2%
SWE-Bench ProScale AI SEAL–59.1%
Code MigrationVals AI–35.0%
ProgramBenchVals AI–0.0%
Vibe Code Bench v1.1Vals AI–67.4%
SWE-Bench Pro (private)Scale AI SEAL–43.4%
SWE Atlas v1.0: Codebase QnAScale AI SEAL–40.8%
SWE Atlas v1.0: RefactoringScale AI SEAL–44.3%
SWE Atlas v1.0: Test WritingScale AI SEAL–44.4%
MirrorCodeEpoch AI Benchmarking Hub–23.3%
DeepSWE v1.1Epoch AI Benchmarking Hub–51.8%
ALE-BenchEpoch AI Benchmarking Hub–1607†
AlgoTuneAlgoTune–1.9†
Terminal-Bench 4.0 (AA)Artificial Analysis61.6%–
Terminal-Bench 2.1 (AA)Artificial Analysis–78.3%
GameBench 2 OverallDuelLab GameBench 2–53.5†
GameBench 2 by reasoning settingDuelLab GameBench 2–62.1
FrontierCode 2.0 (AA)Artificial Analysis43.3%–
Agents & tools
Terminal-BenchTerminal-Bench–81.8%†
APEX-AgentsMercor–52.4%†
Arena AgentArena (LMArena)18.4–
LiveBench Long AgenticLiveBench82.6%†–
LiveBench BrowserLiveBench95.6%†–
LiveBench Agentic CodingLiveBench–53.8%
Terminal-Bench HardArtificial Analysis–57.6%
τ²-Bench Telecom (AA)Artificial Analysis–87.1%
MCP AtlasScale AI SEAL–70.6%
HiL-BenchScale AI SEAL–9.7%†
τ³-bench Bankingτ²-bench–39.4%
GDPval-AA v2.1Artificial Analysis–1256
τ³-Banking (AA)Artificial Analysis–39.6%
APEX-Agents (AA)Artificial Analysis–33.3%
Harvey's Legal Agent Benchmark v1Vals AI–0.0%
SkillsBenchVals AI–51.7%
Terminal-Bench 2.0 (Vals)Vals AI–58.4%†
Arena SearchArena (LMArena)–1196†
Arena Agent Task CompletionArena (LMArena)19.2–
DeepResearch BenchDeepResearch Bench–35.1%†
PostTrainBenchEpoch AI Benchmarking Hub–17.8%†
METR Time HorizonsMETR–74.3%
GBAEvalEpoch AI Benchmarking Hub–45.1%†
Vending-Bench 2Andon Labs–6144.2†
AutomationBenchArtificial Analysis79.2%–
GDP.pdf (AA)Artificial Analysis33.4%–
AA-Briefcase v1.1Artificial Analysis1632–
Design Arena AgenticDesign Arena–1034†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis65.7%–
MKA (AA)Artificial Analysis54.6%–
DeepSearchQAGoogle–63.7%†
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub–78.6%
FrontierMath Tier 4Epoch AI Benchmarking Hub–49.0%
OTIS Mock AIMEEpoch AI Benchmarking Hub–95.3%
ProofBenchVals AI–56.0%
LiveBench MathematicsLiveBench–94.2%
AIME (Vals)Vals AI–96.7%
AIME 2026MathArena–99.2%
HMMT February 2026MathArena–97.7%
USAMO 2026MathArena–95.2%
MathArena ApexMathArena–54.2%
Arena MathsArena (LMArena)–1459†
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub–45.1%
LiveBench 2.0 Data AnalysisLiveBench85.3%†–
LiveBench ResearchLiveBench94.5%†–
LiveBench 1.0 Data AnalysisLiveBench–79.3%
AA-Omniscience v1.1Artificial Analysis53.8–
MMLU-ProVals AI–87.5%
LegalBenchVals AI–86.0%
CorpFinVals AI–65.3%
TaxEvalVals AI–74.0%
MedQAVals AI–96.1%
PRBench FinanceScale AI SEAL–45.6%†
PRBench LegalScale AI SEAL–44.4%†
MultiNRCScale AI SEAL–58.3%†
CaseLaw v2Vals AI–63.8%
MedCodeVals AI–41.3%
MedScribeVals AI–77.5%
EBR-benchEpoch AI Benchmarking Hub–25.4%
AA-Omniscience v1.1: accuracyArtificial Analysis59.4%–
AA-Omniscience v1.1: non-hallucinationArtificial Analysis86.1%–
Instruction following
LiveBench LanguageLiveBench–82.6%
LiveBench Instruction FollowingLiveBench–70.2%
IFBenchArtificial Analysis–74.0%
Arena Instruction FollowingArena (LMArena)15221460†
Human preference
Arena TextArena (LMArena)15191465†
EQ-Bench 4EQ-Bench–1258†
EQ-Bench Creative Writing v3EQ-Bench–1841†
Arena Creative WritingArena (LMArena)15141433†
Arena Multi-turnArena (LMArena)15291480†
Arena Longer QueriesArena (LMArena)15211477†
Multimodal
Arena VisionArena (LMArena)–1292†
LiveBench DesignLiveBench81.5%†–
MMMU-ProArtificial Analysis–78.4%
VISTAScale AI SEAL–50.9%†
MMMU-Pro (Vals)Vals AI–87.5%
MortgageTaxVals AI–68.3%
Humanity's Sixth SenseScale AI SEAL75.9%†–
VTBScale AI SEAL–29.2%†
Blueprint-Bench 2Epoch AI Benchmarking Hub–27.1%†
Furniture AssemblyEpoch AI Benchmarking Hub–37.5%
Long context
AA-LCR v1.1Artificial Analysis–82.0%
Arena DocumentArena (LMArena)–1471†
MLCRArtificial Analysis28.9%–
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub–157.9†
LiveBench 2.0LiveBench87.4%†–
LiveBench 1.0LiveBench–78.0%
AA Intelligence Index v5.0.1Artificial Analysis59.6–
AA Intelligence Index v4.3.2Artificial Analysis–39.0
AA Progress Index v1Artificial Analysis–311.6
Vals RSI IndexVals AI–15.5%
Safety & honesty
MASKScale AI SEAL–89.7%†

Data as of 2026-11-19. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261114-ca113f475f5e (https://benchmarks.duellab.org/releases/gb2-20261114-ca113f475f5e/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Gemini 4 Neon (high): 13 new results (MLCR, MKA (AA), Arena Text…).
  • Gemini 4 Neon (high): first results.
  • GPT-5.4 (xhigh): 1 new result (GDPval-AA v2.1).
  • GPT-5.4 (xhigh): 1 new result (MirrorCode).
  • GPT-5.4 (xhigh): BenchLeader Index 63.7 → 63.2.
  • GPT-5.4 (xhigh): 1 score revision.
  • GPT-5.4 (xhigh): 1 new result (AA Progress Index v1).
  • GPT-5.4 (xhigh): 2 new results (Harvey's Legal Agent Benchmark v1, Vals RSI Index).

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

Gemini 4 Neon vs GPT-5.4: questions

Is Gemini 4 Neon better than GPT-5.4?
Gemini 4 Neon (high) leads on quality: 67.3 vs 63.0. The BenchLeader Index combines every independent quality benchmark; Gemini 4 Neon (high) is ahead overall as of 19 Nov 2026, but check the category scores for your use.
Gemini 4 Neon vs GPT-5.4: which is cheaper, and will that change?
GPT-5.4 is cheaper today: $5.63 against $6.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is Gemini 4 Neon or GPT-5.4 better for coding?
Gemini 4 Neon scores higher in coding (73 vs 65 on the category index, where 50 is average).
Which is faster, Gemini 4 Neon or GPT-5.4?
Gemini 4 Neon streams faster (101 vs 65 output tokens per second, Artificial Analysis 7-day median).
Is Gemini 4 Neon or GPT-5.4 better for agents and tool use?
Gemini 4 Neon scores higher in agentic tasks (76 vs 63 on the category index, where 50 is average).
More questions (3)
Which is better for long documents?
Both take about 1.1M tokens: Gemini 4 Neon 1,048,576, GPT-5.4 1,050,000.
Which has lower latency?
Gemini 4 Neon answers first: 40.6 s against 104.6 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 Neon released?
Gemini 4 Neon was released on 18 Nov 2026.