Model comparison
GPT-5.4 vs Qwen3.7 Plus
Head-to-head evidence from 32 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-5.4 #8 (Supported); Qwen3.7 Plus #21 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-5.4 and Qwen3.7 Plus share 32 comparable benchmark results. 5 of 8 categories are comparable. 20 results are unique to GPT-5.4; 37 to Qwen3.7 Plus.
Updated July 23, 2026- Shared results
- 32
- GPT-5.4 only
- 20
- Qwen3.7 Plus only
- 37
- Comparable categories
- 5 / 8
Pick GPT-5.4 if you want the stronger benchmark profile. Qwen3.7 Plus only becomes the better choice if mathematics is the priority.
Confidence note. This is a partial-evidence comparison with 32 shared benchmark results across 6 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 is clearly ahead on the BenchAlign aggregate, 74.24 to 67.22. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.4's sharpest advantage is in agentic, where it averages 77.2 against 71.7. The single biggest benchmark swing on the page is HLE, 52.1% to 34.7%. Qwen3.7 Plus does hit back in mathematics, so the answer changes if that is the part of the workload you care about most.
GPT-5.4 gives you the larger context window at 1.05M, compared with 1M for Qwen3.7 Plus.
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 | GPT-5.4 | Δ | Qwen3.7 Plus |
|---|---|---|---|
| Math | GPT-5.442.5 | Margin→ 50.4 | Qwen3.7 Plus92.9 |
| Coding | GPT-5.457.7 | Margin→ 17.9 | Qwen3.7 Plus75.6 |
| Multimodal | GPT-5.473.2 | Margin→ 8.3 | Qwen3.7 Plus81.5 |
| Agentic | GPT-5.477.2 | Margin← 5.5 | Qwen3.7 Plus71.7 |
| Knowledge | GPT-5.457.6 | Margin→ 2.5 | Qwen3.7 Plus60.1 |
| Reasoning | GPT-5.4Not measured | MarginNo overlap | Qwen3.7 Plus91.7 |
| Multilingual | GPT-5.4Not measured | MarginNo overlap | Qwen3.7 Plus85.4 |
| Inst. Following | GPT-5.4Not measured | MarginNo overlap | Qwen3.7 Plus84.5 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
HLE
KnowledgeA 52.1%B 34.7%Winner: GPT-5.4Δ 17.4HLE: GPT-5.4 scored 52.1%; Qwen3.7 Plus scored 34.7%. GPT-5.4 wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 75.1%B 70.3%Winner: GPT-5.4Δ 4.8Terminal-Bench 2.0: GPT-5.4 scored 75.1%; Qwen3.7 Plus scored 70.3%. GPT-5.4 wins this benchmark. - Source ↗
CharXiv
MultimodalA 82.8%B 85.9%Winner: Qwen3.7 PlusΔ 3.1CharXiv: GPT-5.4 scored 82.8%; Qwen3.7 Plus scored 85.9%. Qwen3.7 Plus wins this benchmark. - Source ↗
GPQA
KnowledgeA 92.8%B 90.3%Winner: GPT-5.4Δ 2.5GPQA: GPT-5.4 scored 92.8%; Qwen3.7 Plus scored 90.3%. GPT-5.4 wins this benchmark. - Source ↗
MMMU-Pro
MultimodalA 81.2%B 79%Winner: GPT-5.4Δ 2.2MMMU-Pro: GPT-5.4 scored 81.2%; Qwen3.7 Plus scored 79%. GPT-5.4 wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-5.4 | Qwen3.7 Plus | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-5.4$2.5 input / $15 output | Qwen3.7 PlusNot available | A complete price comparison is not available. |
| Generation speedtokens per second | GPT-5.474 tok/s | Qwen3.7 PlusNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GPT-5.4151.79 s | Qwen3.7 PlusNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GPT-5.41.05M | Qwen3.7 Plus1M | GPT-5.4 lists the larger context window. |
Benchmark Deep Dive
AgenticGPT-5.4 wins24 benchmarks
| Benchmark | GPT-5.4 | Qwen3.7 Plus | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 75.1% | 70.3% | GPT-5.4 leads |
| CyberGymSource | 79.0% | — | Not comparable |
| BrowseCompSource | 82.7% | — | Not comparable |
| OSWorld-VerifiedSource | 75% | 73.3% | GPT-5.4 leads |
| MCP AtlasSource | 70.6% | 73.2% | Qwen3.7 Plus leads |
| ToolathlonSource | 54.6% | — | Not comparable |
| τ²-bench resultsSource | 87.1% | 93% | Qwen3.7 Plus leads |
| Claw-EvalSource | 60.3% | 62.7% | Qwen3.7 Plus leads |
| DeepSearchQASource | 73.6% | — | Not comparable |
| AA Agentic IndexSource | 41.1% | 20.8% | GPT-5.4 leads |
| APEX-Agents-AASource | 33.3% | 22.4% | GPT-5.4 leads |
| GDPval-AASource | 44.7% | 21.8% | GPT-5.4 leads |
| GDPval-AASource | 1395 | 936 | GPT-5.4 leads |
| Gert LabsSource | 64.89% | — | Not comparable |
| ResearchClawBenchSource | 15.3% | — | Not comparable |
| JobBenchSource | 38.9% | — | Not comparable |
| ExploitGymSource | 6.0% | — | Not comparable |
| QwenClawBenchSource | — | 61.8% | Not comparable |
| QwenWebBenchSource | — | 1536 | 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 |
CodingQwen3.7 Plus wins12 benchmarks
| Benchmark | GPT-5.4 | Qwen3.7 Plus | Result |
|---|---|---|---|
| LiveCodeBench ProSource | 87.5% | — | Not comparable |
| SWE-bench ProSource | 57.7% | 57.6% | GPT-5.4 leads |
| React Native EvalsSource | 85.3% | — | Not comparable |
| Vibe Code BenchSource | 67.42% | — | Not comparable |
| AA Coding IndexSource | 71.0% | 55.9% | GPT-5.4 leads |
| AA-SciCodeSource | 56.6% | 45.5% | GPT-5.4 leads |
| Terminal-Bench 2.0Source | — | 70.3% | Not comparable |
| SWE-bench VerifiedSource | — | 77.7% | Not comparable |
| SWE MultilingualSource | — | 75.8% | Not comparable |
| NL2RepoSource | — | 41.1% | Not comparable |
| SciCodeSource | — | 51.3% | Not comparable |
| LiveCodeBenchSource | — | 89.6% | Not comparable |
Reasoning3 benchmarks
KnowledgeQwen3.7 Plus wins17 benchmarks
| Benchmark | GPT-5.4 | Qwen3.7 Plus | Result |
|---|---|---|---|
| GPQASource | 92.8% | 90.3% | GPT-5.4 leads |
| HLESource | 52.1% | 34.7% | GPT-5.4 leads |
| HLE w/o toolsSource | 39.8% | — | Not comparable |
| GPQA-DSource | 92.8% | 90.3% | GPT-5.4 leads |
| HealthBench HardSource | 40.1% | — | Not comparable |
| MedXpertQA (Text)Source | 59.6% | — | Not comparable |
| Artificial Analysis Intelligence IndexSource | 51.4% | 39.0% | GPT-5.4 leads |
| AA-GPQA DiamondSource | 92.0% | 90.0% | GPT-5.4 leads |
| AA-HLESource | 41.6% | 33.4% | GPT-5.4 leads |
| AA-Omniscience IndexSource | 5.7% | 2.4% | GPT-5.4 leads |
| AA-Omniscience AccuracySource | 50.0% | 22.2% | GPT-5.4 leads |
| AA-Omniscience Hallucination RateSource | 88.6% | 25.5% | Qwen3.7 Plus leads |
| HealthBench ProfessionalSource | 48.1% | — | 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 wins5 benchmarks
Multilingual5 benchmarks
MultimodalQwen3.7 Plus wins20 benchmarks
| Benchmark | GPT-5.4 | Qwen3.7 Plus | Result |
|---|---|---|---|
| MMMU-ProSource | 81.2% | 79% | GPT-5.4 leads |
| OfficeQA ProSource | 53.2% | — | Not comparable |
| MMMU-Pro w/ PythonSource | 82.1% | — | Not comparable |
| CharXivSource | 82.8% | 85.9% | Qwen3.7 Plus leads |
| ERQASource | 65.4% | 69.8% | Qwen3.7 Plus leads |
| SimpleVQASource | 61.1% | 81.7% | Qwen3.7 Plus leads |
| ScreenSpot ProSource | 85.4% | 79.0% | GPT-5.4 leads |
| ZeroBenchSource | 41.0% | — | Not comparable |
| MedXpertQA (MM)Source | 77.1% | 71.0% | GPT-5.4 leads |
| AA-MMMU-ProSource | 78.4% | 80.5% | Qwen3.7 Plus leads |
| Design Arena WebsiteSource | 1250 | 1288 | Qwen3.7 Plus leads |
| MathVisionSource | — | 90.3% | 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 |
Frequently Asked Questions (6)
Which is better, GPT-5.4 or Qwen3.7 Plus?
GPT-5.4 is ahead on BenchLM's BenchAlign leaderboard, 74.24 to 67.22. The biggest single separator in this matchup is HLE, where the scores are 52.1% and 34.7%.
Which is better for knowledge tasks, GPT-5.4 or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for knowledge tasks in this comparison, averaging 60.1 versus 57.6. Inside this category, AA-Omniscience Hallucination Rate is the benchmark that creates the most daylight between them.
Which is better for coding, GPT-5.4 or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for coding in this comparison, averaging 75.6 versus 57.7. Inside this category, AA Coding Index is the benchmark that creates the most daylight between them.
Which is better for math, GPT-5.4 or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for math in this comparison, averaging 92.9 versus 42.5. GPT-5.4 stays close enough that the answer can still flip depending on your workload.
Which is better for agentic tasks, GPT-5.4 or Qwen3.7 Plus?
GPT-5.4 has the edge for agentic tasks in this comparison, averaging 77.2 versus 71.7. 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 or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for multimodal and grounded tasks in this comparison, averaging 81.5 versus 73.2. Inside this category, Design Arena Website is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
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.