Skip to main content

Model comparison

GPT-5.4 Pro vs Qwen3.5 397B

Data verified

Head-to-head evidence from 4 shared benchmark results across 4 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

60.89/100
Margin
3.9pts
← winning
57.01/100
4 category wins1 category wins

Public leaderboard positions: GPT-5.4 Pro #44 (Estimated); Qwen3.5 397B #71 (Estimated). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GPT-5.4 Pro and Qwen3.5 397B share 4 comparable benchmark results. 5 of 8 categories are comparable. 8 results are unique to GPT-5.4 Pro; 51 to Qwen3.5 397B.

Updated July 23, 2026
Shared results
4
GPT-5.4 Pro only
8
Qwen3.5 397B only
51
Comparable categories
5 / 8

Pick GPT-5.4 Pro if you want the stronger benchmark profile. Qwen3.5 397B only becomes the better choice if mathematics is the priority or you want the cheaper token bill.

Confidence note. This is a partial-evidence comparison with 4 shared benchmark results across 4 evidence categories; 5 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

GPT-5.4 Pro is clearly ahead on the BenchAlign aggregate, 60.89 to 57.01. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

GPT-5.4 Pro's sharpest advantage is in agentic, where it averages 89.3 against 56.5. The single biggest benchmark swing on the page is HLE, 58.7% to 28.7%. Qwen3.5 397B does hit back in mathematics, so the answer changes if that is the part of the workload you care about most.

GPT-5.4 Pro is also the more expensive model on tokens at $30.00 input / $180.00 output per 1M tokens, versus $0.60 input / $3.60 output per 1M tokens for Qwen3.5 397B. That is roughly 50.0x on output cost alone. GPT-5.4 Pro is the reasoning model in the pair, while Qwen3.5 397B is not. That usually helps on harder chain-of-thought-heavy tests, but it can also mean more latency and more token spend in real use. GPT-5.4 Pro gives you the larger context window at 1.05M, compared with 128K for Qwen3.5 397B.

Category breakdown

Exact category averages are shown below. Not measured means BenchLM does not have enough sourced public coverage for that model and category.

Category scores and score margins for GPT-5.4 Pro and Qwen3.5 397B
CategoryGPT-5.4 ProΔQwen3.5 397B
MathGPT-5.4 Pro46.9Margin 43.7Qwen3.5 397B90.6
AgenticGPT-5.4 Pro89.3Margin 32.8Qwen3.5 397B56.5
ReasoningGPT-5.4 Pro83.3Margin 20.1Qwen3.5 397B63.2
MultimodalGPT-5.4 Pro94.0Margin 14.4Qwen3.5 397B79.6
KnowledgeGPT-5.4 Pro58.7Margin 2.1Qwen3.5 397B56.6
CodingGPT-5.4 ProNot measuredMarginNo overlapQwen3.5 397B66.5
MultilingualGPT-5.4 ProNot measuredMarginNo overlapQwen3.5 397B84.7
Inst. FollowingGPT-5.4 ProNot measuredMarginNo overlapQwen3.5 397B92.6

Decisive benchmark drivers

The largest measured benchmark gaps in this matchup, with exact reported values.

More
A · GPT-5.4 ProB · Qwen3.5 397B
  1. HLE

    Knowledge
    Source ↗
    A 58.7%B 28.7%
    Winner: GPT-5.4 ProΔ 30
    HLE: GPT-5.4 Pro scored 58.7%; Qwen3.5 397B scored 28.7%. GPT-5.4 Pro wins this benchmark.
  2. BrowseComp

    Agentic
    Source ↗
    A 89.3%B 62%
    Winner: GPT-5.4 ProΔ 27.3
    BrowseComp: GPT-5.4 Pro scored 89.3%; Qwen3.5 397B scored 62%. GPT-5.4 Pro wins this benchmark.
  3. MMMU-Pro

    Multimodal
    Source ↗
    A 94%B 79%
    Winner: GPT-5.4 ProΔ 15
    MMMU-Pro: GPT-5.4 Pro scored 94%; Qwen3.5 397B scored 79%. GPT-5.4 Pro wins this benchmark.

Operational comparison

Runtime and commercial metrics are compared only when both models have a complete sourced value.

MetricGPT-5.4 ProQwen3.5 397BComparison
Input / output priceUSD per 1M tokensGPT-5.4 Pro$30 input / $180 outputQwen3.5 397B$0.6 input / $3.6 outputQwen3.5 397B has the lower combined listed price.
Generation speedtokens per secondGPT-5.4 Pro74 tok/sQwen3.5 397B96 tok/sQwen3.5 397B has the higher measured throughput.
First-answer latencyseconds to first tokenGPT-5.4 Pro151.79 sQwen3.5 397B2.44 sQwen3.5 397B reaches the first token sooner.
Context windowmaximum listed tokensGPT-5.4 Pro1.05MQwen3.5 397B128KGPT-5.4 Pro lists the larger context window.

Benchmark Deep Dive

AgenticGPT-5.4 Pro wins
BenchmarkGPT-5.4 ProQwen3.5 397BResult
BrowseCompSource 89.3%62%GPT-5.4 Pro leads
Terminal-Bench 2.0Source 52.5%Not comparable
Claw-EvalSource 56.8%Not comparable
QwenClawBenchSource 51.8%Not comparable
τ³-bench resultsSource 68.4%Not comparable
VITA-BenchSource 43.7%Not comparable
DeepPlanningSource 37.6%Not comparable
ToolathlonSource 36.3%Not comparable
MCP AtlasSource 46.1%Not comparable
MCP-TasksSource 74.2%Not comparable
WideResearchSource 74.0%Not comparable
τ²-bench resultsSource 95.6%Not comparable
Gert LabsSource 46.76%Not comparable
ResearchClawBenchSource 14.2%Not comparable
AA Agentic IndexSource 19.9%Not comparable
APEX-Agents-AASource 15.3%Not comparable
GDPval-AASource 23.1%Not comparable
GDPval-AASource 962Not comparable
Coding
BenchmarkGPT-5.4 ProQwen3.5 397BResult
SWE-bench VerifiedSource 76.2%Not comparable
LiveCodeBench v6Source 83.6%Not comparable
SWE-bench ProSource 50.9%Not comparable
AA-SciCodeSource 42.0%Not comparable
AA Coding IndexSource 48.2%Not comparable
ReasoningGPT-5.4 Pro wins
BenchmarkGPT-5.4 ProQwen3.5 397BResult
ARC-AGI-2Source 83.3%Not comparable
CritPtSource 30.0%1.7%GPT-5.4 Pro leads
LongBench v2Source 63.2%Not comparable
AI-NeedleSource 68.7%Not comparable
AA-LCRSource 65.7%Not comparable
KnowledgeGPT-5.4 Pro wins
BenchmarkGPT-5.4 ProQwen3.5 397BResult
HLESource 58.7%28.7%GPT-5.4 Pro leads
FrontierScienceSource 36.7%Not comparable
FrontierScience ResearchSource 36.7%Not comparable
HLE w/o toolsSource 42.7%Not comparable
GPQASource 88.4%Not comparable
SuperGPQASource 70.4%Not comparable
MMLU-ProSource 87.8%Not comparable
MMLU-ReduxSource 94.9%Not comparable
C-EvalSource 93%Not comparable
Artificial Analysis Intelligence IndexSource 33.7%Not comparable
AA-GPQA DiamondSource 89.3%Not comparable
AA-HLESource 27.3%Not comparable
AA-Omniscience IndexSource -29.8%Not comparable
AA-Omniscience AccuracySource 31.4%Not comparable
AA-Omniscience Hallucination RateSource 89.1%Not comparable
MathQwen3.5 397B wins
BenchmarkGPT-5.4 ProQwen3.5 397BResult
IPhO 2025 (Theory)Source 93.5%Not comparable
FrontierMath (legacy)Source 50%Not comparable
FrontierMath v2 (Tiers 1-3)Source 50.000%Not comparable
FrontierMath v2 (Tier 4)Source 37.500%Not comparable
AIME26Source 93.3%Not comparable
HMMT Feb 2025Source 94.8%Not comparable
HMMT Nov 2025Source 92.7%Not comparable
HMMT Feb 2026Source 87.9%Not comparable
MMAnswerBenchSource 80.9%Not comparable
Multilingual
BenchmarkGPT-5.4 ProQwen3.5 397BResult
MMLU-ProXSource 84.7%Not comparable
NOVA-63Source 59.1%Not comparable
MultimodalGPT-5.4 Pro wins
BenchmarkGPT-5.4 ProQwen3.5 397BResult
MMMU-ProSource 94%79%GPT-5.4 Pro leads
MathVisionSource 88.6%Not comparable
CharXivSource 80.8%Not comparable
VideoMMMUSource 84.7%Not comparable
ScreenSpot ProSource 65.6%Not comparable
V*Source 95.8%Not comparable
AA-MMMU-ProSource 77.3%Not comparable
Inst. Following
BenchmarkGPT-5.4 ProQwen3.5 397BResult
IFEvalSource 92.6%Not comparable
AA-IFBenchSource 78.8%Not comparable
Frequently Asked Questions (6)

Which is better, GPT-5.4 Pro or Qwen3.5 397B?

GPT-5.4 Pro is ahead on BenchLM's BenchAlign leaderboard, 60.89 to 57.01. The biggest single separator in this matchup is HLE, where the scores are 58.7% and 28.7%.

Which is better for knowledge tasks, GPT-5.4 Pro or Qwen3.5 397B?

GPT-5.4 Pro has the edge for knowledge tasks in this comparison, averaging 58.7 versus 56.6. Inside this category, HLE is the benchmark that creates the most daylight between them.

Which is better for math, GPT-5.4 Pro or Qwen3.5 397B?

Qwen3.5 397B has the edge for math in this comparison, averaging 90.6 versus 46.9. GPT-5.4 Pro stays close enough that the answer can still flip depending on your workload.

Which is better for reasoning, GPT-5.4 Pro or Qwen3.5 397B?

GPT-5.4 Pro has the edge for reasoning in this comparison, averaging 83.3 versus 63.2. Inside this category, CritPt is the benchmark that creates the most daylight between them.

Which is better for agentic tasks, GPT-5.4 Pro or Qwen3.5 397B?

GPT-5.4 Pro has the edge for agentic tasks in this comparison, averaging 89.3 versus 56.5. Inside this category, BrowseComp is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, GPT-5.4 Pro or Qwen3.5 397B?

GPT-5.4 Pro has the edge for multimodal and grounded tasks in this comparison, averaging 94 versus 79.6. Inside this category, MMMU-Pro is the benchmark that creates the most daylight between them.

Related Comparisons

Last updated: July 23, 2026

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.