BenchLeader

GPT-5.4 vs Qwen3.8-Flash-Next

Full profiles: GPT-5.4 (OpenAI) and Qwen3.8-Flash-Next (Alibaba): every benchmark, price and rank.

Updated · Data from 12 sources

As of 16 Nov 2026, GPT-5.4 is ahead of Qwen3.8-Flash-Next on quality (63.1 vs 53.9 on the BenchLeader Index), but Qwen3.8-Flash-Next is 24× cheaper at $0.230 vs $5.63 per 1M tokens blended. Choose GPT-5.4 for reasoning (66 vs 43), knowledge (59 vs 38), and coding (65 vs 61); choose Qwen3.8-Flash-Next for fast first answers (65.5 s vs 144.9 s) and agents & tools (64 vs 63).

Key facts (as of 16 Nov 2026)

  • GPT-5.4 scores 63.1 on the BenchLeader Index and Qwen3.8-Flash-Next scores 53.9 (BenchLeader, 16 Nov 2026).
  • GPT-5.4 costs $5.63 per 1M tokens blended (list price, 16 Nov 2026).
  • Qwen3.8-Flash-Next costs $0.230 per 1M tokens blended (list price, 16 Nov 2026).
  • Of the 17 benchmarks both models have, GPT-5.4 leads 9 (BenchLeader, 16 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
CodingGPT-5.465 vs 61 category score; LiveBench 1.0 Coding 77.5% vs 72.5%Medium
Agents & tool useQwen3.8-Flash-Next64 vs 63 category score; τ³-Banking (AA) 45.4% vs 39.6%Medium
ReasoningGPT-5.466 vs 43 category score; LiveBench 1.0 Reasoning 88.1% vs 87.4%High
KnowledgeGPT-5.459 vs 38 category score; LiveBench 1.0 Data Analysis 79.3% vs 74.2%High
Long documentsGPT-5.466 vs 65 category score; AA-LCR v1.1 82.0% vs 79.7%Medium
Images and other mediaEither61 vs 61 category score; MMMU-Pro 78.4% vs 78.6%Either
Lowest costQwen3.8-Flash-Next$0.230 vs $5.63 per 1M blended; agentic coding session $0.011 vs $0.210–
Fastest first answerQwen3.8-Flash-Next65.5 s (Qwen3.8-Flash-Next) vs 144.9 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

  • GPT-5.4 (xhigh) leads on quality: 63.1 vs 53.9.
  • GPT-5.4 (xhigh) is stronger in coding, knowledge, long context, reasoning.
  • Qwen3.8-Flash-Next is stronger in agents & tools, multimodal.
  • Qwen3.8-Flash-Next is 24× cheaper ($0.230 vs $5.63 per 1M blended).

At a glance

SpecGPT-5.4Qwen3.8-Flash-Next
DeveloperOpenAIAlibaba
Released5 Mar 202626 Aug 2026
Context window (tokens)1,050,000256,000
Compared atGPT-5.4 (xhigh)Qwen3.8-Flash-Next
Open weightsNoYes
Price in / out / cached input per 1M$2.50 / $15.00 / $0.250$0.150 / $0.470 / –

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.

CategoryGPT-5.4 (xhigh)Qwen3.8-Flash-NextLeader
Reasoning65.743.0GPT-5.4
Coding64.760.7GPT-5.4
Agents & tools63.064.0Qwen3.8-Flash-Next
Maths64.8–not comparable
Knowledge58.638.1GPT-5.4
Instruction following72.4–not comparable
Multimodal60.861.0level
Long context65.764.5GPT-5.4

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 & toolsKnowledgeLong contextMultimodalGPT-5.4, Reasoning: 65.7GPT-5.4, Coding: 64.7GPT-5.4, Agents & tools: 63.0GPT-5.4, Knowledge: 58.6GPT-5.4, Long context: 65.7GPT-5.4, Multimodal: 60.8Qwen3.8-Flash-Next, Reasoning: 43.0Qwen3.8-Flash-Next, Coding: 60.7Qwen3.8-Flash-Next, Agents & tools: 64.0Qwen3.8-Flash-Next, Knowledge: 38.1Qwen3.8-Flash-Next, Long context: 64.5Qwen3.8-Flash-Next, Multimodal: 61.0

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

Model, click to add or removeIndex

Where sources disagree

Across the 17 benchmarks both have, GPT-5.4 leads 9, Qwen3.8-Flash-Next leads 8. Every overall index that rates both puts GPT-5.4 ahead.

Overall indexGPT-5.4 (xhigh)Qwen3.8-Flash-NextLeader
BenchLeader Index63.153.9GPT-5.4

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.

MeasureGPT-5.4 (xhigh)Qwen3.8-Flash-Next
Blended price per 1M tokens$5.63$0.230
Input / output per 1M$2.50 / $15.00$0.150 / $0.470
Cached input per 1M$0.250–
Price per task: chat reply$0.0055$0.0002
Price per task: summarize a 30-page report$0.039$0.0021
Price per task: code edit$0.037$0.0016
Price per task: agentic coding session$0.210$0.011
Price per task: structured extraction$0.0080$0.0004
Agentic coding session, input mostly cached$0.109–
Cost per benchmark task (AA Index)–$0.569
Output tokens per task (AA Index)–148k
Of which reasoning–97k
Time per task (AA Index)–31 min
Output speed73 tok/s80 tok/s
Time to first answer144.9 s65.5 s
Time to a complete answer, last measured 13 Nov 2026193.1 s202.8 s

Each model is compared at its best-ranked reasoning-effort setting. GPT-5.4 (xhigh) scores 63.1 and takes 145 s to its first answer token; GPT-5.4 (low) scores 58.8 in 3 s, GPT-5.4 (high) scores 58.6 in 2 s. Qwen3.8-Flash-Next scores 53.9 and takes 66 s to its first answer token. 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

136 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.

MetricPublisherGPT-5.4 (xhigh)Qwen3.8-Flash-Next
BenchLeader IndexBenchLeader63.153.9
Agents & tools scoreBenchLeader63.064.0
Coding scoreBenchLeader64.760.7
Instruction following scoreBenchLeader72.4–
Knowledge scoreBenchLeader58.638.1
Long context scoreBenchLeader65.764.5
Maths scoreBenchLeader64.8–
Multimodal scoreBenchLeader60.861.0
Reasoning scoreBenchLeader65.743.0
Blended price $/MBenchLeader$5.63$0.230
Output speedBenchLeader73 tok/s80 tok/s
Time to first answerBenchLeader144.9 s65.5 s
Context windowBenchLeader1,050,000 tokens256,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub93.3%–
Humanity's Last ExamScale AI / CAIS36.2%–
Arena Hard PromptsArena (LMArena)1487†–
LiveBench 1.0 ReasoningLiveBench88.1%87.4%
GPQA Diamond (AA)Artificial Analysis92.0%92.3%
Humanity's Last Exam (AA)Artificial Analysis43.7%38.0%
HLE-Diamond (AA)Artificial Analysis–16.3%
GPQA Diamond (Vals)Vals AI91.7%–
Kagi LLM BenchmarkKagi LLM Benchmark63.8%†–
ARC-AGI-1ARC Prize93.7%–
ARC-AGI-2ARC Prize74.0%–
ARC-AGI-3ARC Prize0.2%†–
CritPtArtificial Analysis23.4%11.1%
CritPt v2 hard subset (AA)Artificial Analysis–24.5%
Arena ExpertArena (LMArena)1491†–
Chess PuzzlesEpoch AI Benchmarking Hub48.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub37.0%–
CL-benchEpoch AI Benchmarking Hub27.9%–
CL-bench LifeEpoch AI Benchmarking Hub21.7%–
LMCAEpoch AI Benchmarking Hub52.0%–
DTBenchEpoch AI Benchmarking Hub94.4%–
ForecastBenchForecastBench63.0%†–
Coding
SWE-bench Verified (Epoch)Epoch AI Benchmarking Hub76.9%†–
SciCodeSciCode56.6%–
WeirdMLWeirdML77.7%–
Show all 136 benchmarks
MetricPublisherGPT-5.4 (xhigh)Qwen3.8-Flash-Next
Coding
GSO-BenchGSO-Bench31.4%–
Arena CodingArena (LMArena)1511†–
Arena WebDevArena (LMArena)1400†1624
LiveBench 1.0 CodingLiveBench77.5%72.5%
SciCode (AA)Artificial Analysis–50.6%
LiveCodeBenchVals AI84.1%–
SWE-bench (Vals)Vals AI78.2%–
SWE-Bench ProScale AI SEAL59.1%–
Code MigrationVals AI35.0%–
ProgramBenchVals AI0.0%–
Vibe Code Bench v1.1Vals AI67.4%–
SWE-Bench Pro (private)Scale AI SEAL43.4%–
SWE Atlas v1.0: Codebase QnAScale AI SEAL40.8%–
SWE Atlas v1.0: RefactoringScale AI SEAL44.3%–
SWE Atlas v1.0: Test WritingScale AI SEAL44.4%–
MirrorCodeEpoch AI Benchmarking Hub23.3%–
DeepSWE v1.1Epoch AI Benchmarking Hub51.8%–
ALE-BenchEpoch AI Benchmarking Hub1607†–
AlgoTuneAlgoTune1.9†–
Terminal-Bench 4.0 (AA)Artificial Analysis–25.3%
Terminal-Bench 2.1 (AA)Artificial Analysis78.3%86.1%
GameBench 2 OverallDuelLab GameBench 253.4†–
GameBench 2 by reasoning settingDuelLab GameBench 262.1–
Design Arena WebsiteDesign Arena1190†–
FrontierCode 2.0 (AA)Artificial Analysis–27.1%
Agents & tools
Terminal-BenchTerminal-Bench81.8%†–
APEX-AgentsMercor52.4%†–
Arena AgentArena (LMArena)–-4.6
LiveBench Agentic CodingLiveBench53.8%61.6%
Terminal-Bench HardArtificial Analysis57.6%–
τ²-Bench Telecom (AA)Artificial Analysis87.1%–
MCP AtlasScale AI SEAL70.6%–
HiL-BenchScale AI SEAL9.7%†–
τ³-bench Bankingτ²-bench39.4%–
GDPval-AA v2.1, normalised scoreArtificial Analysis–56.4%
GDPval-AA v2.1Artificial Analysis12561637
τ³-Banking (AA)Artificial Analysis39.6%45.4%
APEX-Agents (AA)Artificial Analysis33.3%–
Harvey's Legal Agent Benchmark v1Vals AI0.0%–
SkillsBenchVals AI51.7%–
Terminal-Bench 2.0 (Vals)Vals AI58.4%†–
Arena SearchArena (LMArena)1196†–
Arena Agent Task CompletionArena (LMArena)–0.3
DeepResearch BenchDeepResearch Bench35.1%†–
PostTrainBenchEpoch AI Benchmarking Hub17.8%†–
METR Time HorizonsMETR74.3%–
GBAEvalEpoch AI Benchmarking Hub45.1%†–
Vending-Bench 2Andon Labs6144.2†–
AutomationBenchArtificial Analysis–55.9%
GDP.pdf (AA)Artificial Analysis–15.6%
AA-Briefcase v1.1Artificial Analysis–1572
Design Arena AgenticDesign Arena1042†–
Terminal-Bench-Science 0.1 (AA)Artificial Analysis–7.1%
DeepSearchQAGoogle63.7%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub78.6%–
FrontierMath Tier 4Epoch AI Benchmarking Hub49.0%–
OTIS Mock AIMEEpoch AI Benchmarking Hub95.3%–
ProofBenchVals AI56.0%–
LiveBench MathematicsLiveBench94.2%85.8%
AIME (Vals)Vals AI96.7%–
AIME 2026MathArena99.2%–
HMMT February 2026MathArena97.7%–
USAMO 2026MathArena95.2%–
MathArena ApexMathArena54.2%–
Arena MathsArena (LMArena)1459†–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub45.1%–
LiveBench 1.0 Data AnalysisLiveBench79.3%74.2%
AA-Omniscience v1.1Artificial Analysis–-12.2
MMLU-ProVals AI87.5%–
LegalBenchVals AI86.0%–
CorpFinVals AI65.3%–
TaxEvalVals AI74.0%–
MedQAVals AI96.1%–
PRBench FinanceScale AI SEAL45.6%†–
PRBench LegalScale AI SEAL44.4%†–
MultiNRCScale AI SEAL58.3%†–
CaseLaw v2Vals AI63.8%–
MedCodeVals AI41.3%–
MedScribeVals AI77.5%–
EBR-benchEpoch AI Benchmarking Hub25.4%–
AA-Omniscience v1.1: accuracyArtificial Analysis–23.5%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis–53.2%
Instruction following
LiveBench LanguageLiveBench82.6%74.6%
LiveBench Instruction FollowingLiveBench70.2%77.1%
IFBenchArtificial Analysis74.0%–
Arena Instruction FollowingArena (LMArena)1460†–
Human preference
Arena TextArena (LMArena)1465†–
EQ-Bench 4EQ-Bench1258†–
EQ-Bench Creative Writing v3EQ-Bench1841†–
Arena Creative WritingArena (LMArena)1433†–
Arena Multi-turnArena (LMArena)1480†–
Arena Longer QueriesArena (LMArena)1477†–
Multimodal
Arena VisionArena (LMArena)1292†–
MMMU-ProArtificial Analysis78.4%78.6%
VISTAScale AI SEAL50.9%†–
MMMU-Pro (Vals)Vals AI87.5%–
MortgageTaxVals AI68.3%–
VTBScale AI SEAL29.2%†–
Blueprint-Bench 2Epoch AI Benchmarking Hub27.1%†–
Furniture AssemblyEpoch AI Benchmarking Hub37.5%–
Long context
AA-LCR v1.1Artificial Analysis82.0%79.7%
Arena DocumentArena (LMArena)1471†–
MLCRArtificial Analysis–20.6%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub157.8†–
LiveBench 1.0LiveBench78.0%76.2%
AA Intelligence Index v5.0.1Artificial Analysis–28.6
AA Intelligence Index v4.3.2Artificial Analysis39.039.8
AA Progress Index v1Artificial Analysis311.6320.2
Vals RSI IndexVals AI15.5%–
Safety & honesty
MASKScale AI SEAL89.7%†–
Metadata
AA Openness IndexArtificial Analysis–38.9

Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • GPT-5.4 (xhigh): 1 new result (GDPval-AA v2.1).
  • Qwen3.8-Flash-Next: BenchLeader Index 54.7 → 54.0.
  • Qwen3.8-Flash-Next: 3 new results (AA Intelligence Index v5.0.1, FrontierCode 2.0 (AA), Terminal-Bench-Science 0.1 (AA)).
  • GPT-5.4 (xhigh): 1 new result (MirrorCode).
  • Qwen3.8-Flash-Next: 1 new result (CritPt v2 hard subset (AA)); 1 score revision.
  • GPT-5.4 (xhigh): BenchLeader Index 63.7 → 63.2.
  • GPT-5.4 (xhigh): 1 score revision.
  • Qwen3.8-Flash-Next: 1 new result (AA-Briefcase v1.1); 1 score revision.
  • Qwen3.8-Flash-Next: BenchLeader Index 58.7 → 54.7.
  • GPT-5.4 (xhigh): 1 new result (AA Progress Index v1).

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

GPT-5.4 vs Qwen3.8-Flash-Next: questions

Is GPT-5.4 better than Qwen3.8-Flash-Next?
GPT-5.4 (xhigh) leads on quality: 63.1 vs 53.9. The BenchLeader Index combines every independent quality benchmark; GPT-5.4 (xhigh) is ahead overall as of 16 Nov 2026, but check the category scores for your use.
GPT-5.4 vs Qwen3.8-Flash-Next: which is cheaper, and will that change?
Qwen3.8-Flash-Next is cheaper today: $0.230 against $5.63 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
Is GPT-5.4 or Qwen3.8-Flash-Next better for coding?
GPT-5.4 scores higher in coding (65 vs 61 on the category index, where 50 is average).
Which is faster, GPT-5.4 or Qwen3.8-Flash-Next?
Qwen3.8-Flash-Next streams faster (80 vs 73 output tokens per second, Artificial Analysis 7-day median).
Is GPT-5.4 or Qwen3.8-Flash-Next better for agents and tool use?
Qwen3.8-Flash-Next scores higher in agentic tasks (64 vs 63 on the category index, where 50 is average). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 39.6% for GPT-5.4 against 45.4% for Qwen3.8-Flash-Next.
More questions (4)
Which is better for long documents?
GPT-5.4 scores higher on long-context benchmarks (66 vs 65). GPT-5.4 accepts more context: 1,050,000 against 256,000 tokens for Qwen3.8-Flash-Next.
Which has lower latency?
Qwen3.8-Flash-Next answers first: 65.5 s against 144.9 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.
Do independent benchmarks agree on GPT-5.4 vs Qwen3.8-Flash-Next?
Across the 17 benchmarks both have, GPT-5.4 leads 9, Qwen3.8-Flash-Next leads 8. Every overall index that rates both puts GPT-5.4 ahead.
When was Qwen3.8-Flash-Next released?
Qwen3.8-Flash-Next was released on 26 Aug 2026.