Model comparison
GPT-5.3 Codex vs Qwen3.7 Plus
Head-to-head evidence from 17 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Public leaderboard positions: GPT-5.3 Codex #26 (Supported); Qwen3.7 Plus #21 (Supported). Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-5.3 Codex and Qwen3.7 Plus share 17 comparable benchmark results. 2 of 8 categories are comparable. 4 results are unique to GPT-5.3 Codex; 52 to Qwen3.7 Plus.
Updated July 23, 2026- Shared results
- 17
- GPT-5.3 Codex only
- 4
- Qwen3.7 Plus only
- 52
- Comparable categories
- 2 / 8
Pick Qwen3.7 Plus if you want the stronger benchmark profile. GPT-5.3 Codex 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 17 shared benchmark results across 6 evidence categories; 2 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 has the cleaner BenchAlign overall profile here, landing at 67.22 versus 66.69. It is a real lead, but still close enough that category-level strengths matter more than the headline number.
Qwen3.7 Plus's sharpest advantage is in coding, where it averages 75.6 against 67.2. The single biggest benchmark swing on the page is OSWorld-Verified, 64.7% to 73.3%.
Qwen3.7 Plus gives you the larger context window at 1M, compared with 400K for GPT-5.3 Codex.
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-5.3 Codex | Δ | Qwen3.7 Plus |
|---|---|---|---|
| Coding | GPT-5.3 Codex67.2 | Margin→ 8.4 | Qwen3.7 Plus75.6 |
| Agentic | GPT-5.3 Codex71.4 | Margin→ 0.3 | Qwen3.7 Plus71.7 |
| Reasoning | GPT-5.3 CodexNot measured | MarginNo overlap | Qwen3.7 Plus91.7 |
| Knowledge | GPT-5.3 CodexNot measured | MarginNo overlap | Qwen3.7 Plus60.1 |
| Math | GPT-5.3 CodexNot measured | MarginNo overlap | Qwen3.7 Plus92.9 |
| Multilingual | GPT-5.3 CodexNot measured | MarginNo overlap | Qwen3.7 Plus85.4 |
| Multimodal | GPT-5.3 CodexNot measured | MarginNo overlap | Qwen3.7 Plus81.5 |
| Inst. Following | GPT-5.3 CodexNot measured | MarginNo overlap | Qwen3.7 Plus84.5 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
OSWorld-Verified
AgenticA 64.7%B 73.3%Winner: Qwen3.7 PlusΔ 8.6OSWorld-Verified: GPT-5.3 Codex scored 64.7%; Qwen3.7 Plus scored 73.3%. Qwen3.7 Plus wins this benchmark. - Source ↗
SWE-bench Verified
CodingA 85%B 77.7%Winner: GPT-5.3 CodexΔ 7.3SWE-bench Verified: GPT-5.3 Codex scored 85%; Qwen3.7 Plus scored 77.7%. GPT-5.3 Codex wins this benchmark. - Source ↗
Terminal-Bench 2.0
AgenticA 77.3%B 70.3%Winner: GPT-5.3 CodexΔ 7Terminal-Bench 2.0: GPT-5.3 Codex scored 77.3%; Qwen3.7 Plus scored 70.3%. GPT-5.3 Codex wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 56.8%B 57.6%Winner: Qwen3.7 PlusΔ 0.8SWE-bench Pro: GPT-5.3 Codex scored 56.8%; Qwen3.7 Plus scored 57.6%. Qwen3.7 Plus wins this benchmark.
Operational comparison
Runtime and commercial metrics are compared only when both models have a complete sourced value.
| Metric | GPT-5.3 Codex | Qwen3.7 Plus | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-5.3 Codex$1.75 input / $14 output | Qwen3.7 PlusNot available | A complete price comparison is not available. |
| Generation speedtokens per second | GPT-5.3 Codex79 tok/s | Qwen3.7 PlusNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GPT-5.3 Codex88.26 s | Qwen3.7 PlusNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GPT-5.3 Codex400K | Qwen3.7 Plus1M | Qwen3.7 Plus lists the larger context window. |
Benchmark Deep Dive
AgenticQwen3.7 Plus wins18 benchmarks
| Benchmark | GPT-5.3 Codex | Qwen3.7 Plus | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 77.3% | 70.3% | GPT-5.3 Codex leads |
| OSWorld-VerifiedSource | 64.7% | 73.3% | Qwen3.7 Plus leads |
| τ²-bench resultsSource | 86% | 93% | Qwen3.7 Plus leads |
| Gert LabsSource | 57.47% | — | Not comparable |
| JobBenchSource | 33.7% | — | Not comparable |
| QwenClawBenchSource | — | 61.8% | Not comparable |
| QwenWebBenchSource | — | 1536 | Not comparable |
| Claw-EvalSource | — | 62.7% | Not comparable |
| BFCL v4Source | — | 72.9% | Not comparable |
| MCP AtlasSource | — | 73.2% | Not comparable |
| VITA-BenchSource | — | 45.6% | Not comparable |
| DeepPlanningSource | — | 62.3% | Not comparable |
| AndroidWorldSource | — | 81.0% | Not comparable |
| AA Agentic IndexSource | — | 20.8% | Not comparable |
| APEX-Agents-AASource | — | 22.4% | Not comparable |
| GDPval-AASource | — | 21.8% | Not comparable |
| GDPval-AASource | — | 936 | Not comparable |
| OSWorld 2.0Source | — | 2.8% | Not comparable |
CodingQwen3.7 Plus wins11 benchmarks
| Benchmark | GPT-5.3 Codex | Qwen3.7 Plus | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 85% | 77.7% | GPT-5.3 Codex leads |
| SWE-bench ProSource | 56.8% | 57.6% | Qwen3.7 Plus leads |
| SWE-RebenchSource | 58.2% | — | Not comparable |
| Vibe Code BenchSource | 61.77% | — | Not comparable |
| AA-SciCodeSource | 53.2% | 45.5% | GPT-5.3 Codex leads |
| Terminal-Bench 2.0Source | — | 70.3% | Not comparable |
| SWE MultilingualSource | — | 75.8% | Not comparable |
| NL2RepoSource | — | 41.1% | Not comparable |
| SciCodeSource | — | 51.3% | Not comparable |
| LiveCodeBenchSource | — | 89.6% | Not comparable |
| AA Coding IndexSource | — | 55.9% | Not comparable |
Reasoning3 benchmarks
Knowledge13 benchmarks
| Benchmark | GPT-5.3 Codex | Qwen3.7 Plus | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 44.3% | 39.0% | GPT-5.3 Codex leads |
| AA-GPQA DiamondSource | 91.5% | 90.0% | GPT-5.3 Codex leads |
| AA-HLESource | 39.9% | 33.4% | GPT-5.3 Codex leads |
| AA-Omniscience IndexSource | 9.9% | 2.4% | GPT-5.3 Codex leads |
| AA-Omniscience AccuracySource | 51.8% | 22.2% | GPT-5.3 Codex leads |
| AA-Omniscience Hallucination RateSource | 86.9% | 25.5% | Qwen3.7 Plus leads |
| GPQASource | — | 90.3% | Not comparable |
| GPQA-DSource | — | 90.3% | Not comparable |
| HLESource | — | 34.7% | Not comparable |
| MMLU-ProSource | — | 88.5% | Not comparable |
| MMLU-ReduxSource | — | 94.5% | Not comparable |
| SuperGPQASource | — | 71.4% | Not comparable |
| MMMLUSource | — | 89.0% | Not comparable |
Math3 benchmarks
Multilingual5 benchmarks
Multimodal17 benchmarks
| Benchmark | GPT-5.3 Codex | Qwen3.7 Plus | Result |
|---|---|---|---|
| AA-MMMU-ProSource | 78.5% | 80.5% | Qwen3.7 Plus leads |
| Design Arena WebsiteSource | 1193 | 1288 | Qwen3.7 Plus leads |
| MMMU-ProSource | — | 79% | Not comparable |
| 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 |
Frequently Asked Questions (3)
Which is better, GPT-5.3 Codex or Qwen3.7 Plus?
Qwen3.7 Plus is ahead on BenchLM's BenchAlign leaderboard, 67.22 to 66.69. The biggest single separator in this matchup is OSWorld-Verified, where the scores are 64.7% and 73.3%.
Which is better for coding, GPT-5.3 Codex or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for coding in this comparison, averaging 75.6 versus 67.2. Inside this category, AA-SciCode is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GPT-5.3 Codex or Qwen3.7 Plus?
Qwen3.7 Plus has the edge for agentic tasks in this comparison, averaging 71.7 versus 71.4. Inside this category, OSWorld-Verified 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.