Skip to main content
BenchLM
Advertise

Model comparison

GPT-5.4 mini vs Qwen3.7 Plus

Data verified

Head-to-head evidence from 23 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.

56.77/100
Margin
10.4pts
winning →
67.22/100
0 category wins4 category wins

Public leaderboard positions: GPT-5.4 mini #75 (Estimated); Qwen3.7 Plus #21 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.

Evidence parity. GPT-5.4 mini and Qwen3.7 Plus share 23 comparable benchmark results. 4 of 8 categories are comparable. 7 results are unique to GPT-5.4 mini; 46 to Qwen3.7 Plus.

Updated July 23, 2026
Shared results
23
GPT-5.4 mini only
7
Qwen3.7 Plus only
46
Comparable categories
4 / 8

Pick Qwen3.7 Plus if you want the stronger benchmark profile. GPT-5.4 mini only becomes the better choice if its workflow or ecosystem matters more than the raw scoreboard.

Confidence note. This is a partial-evidence comparison with 23 shared benchmark results across 6 evidence categories; 4 of 8 categories currently have scoreable aggregates for both models. Treat the verdict as directional until coverage is more balanced.

Why this result

Qwen3.7 Plus is clearly ahead on the BenchAlign aggregate, 67.22 to 56.77. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.

Qwen3.7 Plus's sharpest advantage is in mathematics, where it averages 92.9 against 21.7. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 60% to 70.3%.

Qwen3.7 Plus gives you the larger context window at 1M, compared with 400K for GPT-5.4 mini.

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 mini and Qwen3.7 Plus
CategoryGPT-5.4 miniΔQwen3.7 Plus
MathGPT-5.4 mini21.7Margin→ 71.2Qwen3.7 Plus92.9
KnowledgeGPT-5.4 mini47.8Margin→ 12.3Qwen3.7 Plus60.1
AgenticGPT-5.4 mini65.7Margin→ 6.0Qwen3.7 Plus71.7
MultimodalGPT-5.4 mini76.6Margin→ 4.9Qwen3.7 Plus81.5
CodingGPT-5.4 miniNot measuredMarginNo overlapQwen3.7 Plus75.6
ReasoningGPT-5.4 miniNot measuredMarginNo overlapQwen3.7 Plus91.7
MultilingualGPT-5.4 miniNot measuredMarginNo overlapQwen3.7 Plus85.4
Inst. FollowingGPT-5.4 miniNot measuredMarginNo overlapQwen3.7 Plus84.5

Decisive benchmark drivers

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

More
A · GPT-5.4 miniB · Qwen3.7 Plus

  1. Terminal-Bench 2.0

    Agentic
    Source ↗
    A 60%B 70.3%
    Winner: Qwen3.7 PlusΔ 10.3
    Terminal-Bench 2.0: GPT-5.4 mini scored 60%; Qwen3.7 Plus scored 70.3%. Qwen3.7 Plus wins this benchmark.

  2. HLE

    Knowledge
    Source ↗
    A 41.5%B 34.7%
    Winner: GPT-5.4 miniΔ 6.8
    HLE: GPT-5.4 mini scored 41.5%; Qwen3.7 Plus scored 34.7%. GPT-5.4 mini wins this benchmark.

  3. MMMU-Pro

    Multimodal
    Source ↗
    A 76.6%B 79%
    Winner: Qwen3.7 PlusΔ 2.4
    MMMU-Pro: GPT-5.4 mini scored 76.6%; Qwen3.7 Plus scored 79%. Qwen3.7 Plus wins this benchmark.

  4. GPQA

    Knowledge
    Source ↗
    A 88%B 90.3%
    Winner: Qwen3.7 PlusΔ 2.3
    GPQA: GPT-5.4 mini scored 88%; Qwen3.7 Plus scored 90.3%. Qwen3.7 Plus wins this benchmark.

  5. OSWorld-Verified

    Agentic
    Source ↗
    A 72.1%B 73.3%
    Winner: Qwen3.7 PlusΔ 1.2
    OSWorld-Verified: GPT-5.4 mini scored 72.1%; Qwen3.7 Plus scored 73.3%. Qwen3.7 Plus wins this benchmark.

Operational comparison

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

MetricGPT-5.4 miniQwen3.7 PlusComparison
Input / output priceUSD per 1M tokensGPT-5.4 mini$0.75 input / $4.5 outputQwen3.7 PlusNot availableA complete price comparison is not available.
Generation speedtokens per secondGPT-5.4 mini201 tok/sQwen3.7 PlusNot availableA complete speed comparison is not available.
First-answer latencyseconds to first tokenGPT-5.4 mini3.85 sQwen3.7 PlusNot availableA complete latency comparison is not available.
Context windowmaximum listed tokensGPT-5.4 mini400KQwen3.7 Plus1MQwen3.7 Plus lists the larger context window.

Benchmark Deep Dive

AgenticQwen3.7 Plus wins
BenchmarkGPT-5.4 miniQwen3.7 PlusResult
Terminal-Bench 2.0Source 60%70.3%Qwen3.7 Plus leads
OSWorld-VerifiedSource 72.1%73.3%Qwen3.7 Plus leads
MCP AtlasSource 57.7%73.2%Qwen3.7 Plus leads
ToolathlonSource 42.9%—Not comparable
τ²-bench resultsSource 83.3%93%Qwen3.7 Plus leads
AA Agentic IndexSource 30.2%20.8%GPT-5.4 mini leads
APEX-Agents-AASource 28.2%22.4%GPT-5.4 mini leads
GDPval-AASource 33.6%21.8%GPT-5.4 mini leads
GDPval-AASource 1171936GPT-5.4 mini leads
QwenClawBenchSource —61.8%Not comparable
QwenWebBenchSource —1536Not comparable
Claw-EvalSource —62.7%Not comparable
BFCL v4Source —72.9%Not comparable
VITA-BenchSource —45.6%Not comparable
DeepPlanningSource —62.3%Not comparable
AndroidWorldSource —81.0%Not comparable
OSWorld 2.0Source —2.8%Not comparable
Coding
BenchmarkGPT-5.4 miniQwen3.7 PlusResult
Vibe Code BenchSource 47.97%—Not comparable
AA Coding IndexSource 56.1%55.9%GPT-5.4 mini leads
AA-SciCodeSource 49.9%45.5%GPT-5.4 mini leads
FrontierCode 1.1 MainSource 27.0%—Not comparable
Terminal-Bench 2.0Source —70.3%Not comparable
SWE-bench VerifiedSource —77.7%Not comparable
SWE-bench ProSource —57.6%Not comparable
SWE MultilingualSource —75.8%Not comparable
NL2RepoSource —41.1%Not comparable
SciCodeSource —51.3%Not comparable
LiveCodeBenchSource —89.6%Not comparable
Reasoning
BenchmarkGPT-5.4 miniQwen3.7 PlusResult
AA-LCRSource 69.3%65.0%GPT-5.4 mini leads
CritPtSource 10.0%9.1%GPT-5.4 mini leads
MRCRv2Source —91.7%Not comparable
KnowledgeQwen3.7 Plus wins
BenchmarkGPT-5.4 miniQwen3.7 PlusResult
GPQASource 88%90.3%Qwen3.7 Plus leads
HLESource 41.5%34.7%GPT-5.4 mini leads
HLE w/o toolsSource 28.2%—Not comparable
Artificial Analysis Intelligence IndexSource 40.0%39.0%GPT-5.4 mini leads
AA-GPQA DiamondSource 87.5%90.0%Qwen3.7 Plus leads
AA-HLESource 26.6%33.4%Qwen3.7 Plus leads
AA-Omniscience IndexSource -18.7%2.4%Qwen3.7 Plus leads
AA-Omniscience AccuracySource 37.5%22.2%GPT-5.4 mini leads
AA-Omniscience Hallucination RateSource 89.8%25.5%Qwen3.7 Plus leads
GPQA-DSource —90.3%Not comparable
MMLU-ProSource —88.5%Not comparable
MMLU-ReduxSource —94.5%Not comparable
SuperGPQASource —71.4%Not comparable
MMMLUSource —89.0%Not comparable
MathQwen3.7 Plus wins
BenchmarkGPT-5.4 miniQwen3.7 PlusResult
FrontierMath v2 (Tiers 1-3)Source 28.280%—Not comparable
FrontierMath v2 (Tier 4)Source 2.080%—Not comparable
HMMT Feb 2026Source —92.9%Not comparable
IMOAnswerBenchSource —86.0%Not comparable
ApexSource —22.7%Not comparable
Multilingual
BenchmarkGPT-5.4 miniQwen3.7 PlusResult
MMLU-ProXSource —85.4%Not comparable
NOVA-63Source —58.8%Not comparable
INCLUDESource —83.0%Not comparable
MAXIFESource —88.8%Not comparable
PolyMathSource —84.0%Not comparable
MultimodalQwen3.7 Plus wins
BenchmarkGPT-5.4 miniQwen3.7 PlusResult
MMMU-ProSource 76.6%79%Qwen3.7 Plus leads
MMMU-Pro w/ PythonSource 78%—Not comparable
AA-MMMU-ProSource 73.3%80.5%Qwen3.7 Plus leads
MathVisionSource —90.3%Not comparable
CharXivSource —85.9%Not comparable
ERQASource —69.8%Not comparable
MedXpertQA (MM)Source —71.0%Not comparable
ScreenSpot ProSource —79.0%Not comparable
SimpleVQASource —81.7%Not comparable
MMSearch-PlusSource —41.4%Not comparable
RealWorldQASource —86.9%Not comparable
OmniDocBench 1.5Source —91.4%Not comparable
OCRBench V2Source —70.7%Not comparable
ODINW13Source —51.1%Not comparable
Video-MME (with subtitle)Source —88.0%Not comparable
VideoMMMUSource —85.4%Not comparable
MLVU (M-Avg)Source —87.4%Not comparable
Design Arena WebsiteSource —1288Not comparable
Inst. Following
BenchmarkGPT-5.4 miniQwen3.7 PlusResult
AA-IFBenchSource 73.3%78.0%Qwen3.7 Plus leads
IFEvalSource —94.6%Not comparable
IFBenchSource —79.1%Not comparable
Frequently Asked Questions (5)

Which is better, GPT-5.4 mini or Qwen3.7 Plus?

Qwen3.7 Plus is ahead on BenchLM's BenchAlign leaderboard, 67.22 to 56.77. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 60% and 70.3%.

Which is better for knowledge tasks, GPT-5.4 mini or Qwen3.7 Plus?

Qwen3.7 Plus has the edge for knowledge tasks in this comparison, averaging 60.1 versus 47.8. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.

Which is better for math, GPT-5.4 mini or Qwen3.7 Plus?

Qwen3.7 Plus has the edge for math in this comparison, averaging 92.9 versus 21.7. GPT-5.4 mini stays close enough that the answer can still flip depending on your workload.

Which is better for agentic tasks, GPT-5.4 mini or Qwen3.7 Plus?

Qwen3.7 Plus has the edge for agentic tasks in this comparison, averaging 71.7 versus 65.7. Inside this category, GDPval-AA is the benchmark that creates the most daylight between them.

Which is better for multimodal and grounded tasks, GPT-5.4 mini or Qwen3.7 Plus?

Qwen3.7 Plus has the edge for multimodal and grounded tasks in this comparison, averaging 81.5 versus 76.6. Inside this category, AA-MMMU-Pro is the benchmark that creates the most daylight between them.

Related Comparisons

Explore More

OpenAI Compare Pricing Methodology Find Your Best LLM Overall Rankings
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.