Model comparison
GPT-5.3 Codex vs Qwen3.6-35B-A3B
Head-to-head evidence from 17 shared benchmark results across 6 categories. Overall scores shown here use the public BenchAlign v5 ranking lane.
Verified leaderboard positions: GPT-5.3 Codex unranked; Qwen3.6-35B-A3B #31
BenchAlign evidence: GPT-5.3 Codex supported; Qwen3.6-35B-A3B estimated. Intervals and evidence labels describe ranking uncertainty, not a guarantee for a specific workload.
Evidence parity. GPT-5.3 Codex and Qwen3.6-35B-A3B share 17 comparable benchmark results. 2 of 8 categories are comparable. 5 results are unique to GPT-5.3 Codex; 41 to Qwen3.6-35B-A3B.
Updated July 15, 2026- Shared results
- 17
- GPT-5.3 Codex only
- 5
- Qwen3.6-35B-A3B only
- 41
- Comparable categories
- 2 / 8
Pick GPT-5.3 Codex if you want the stronger benchmark profile. Qwen3.6-35B-A3B only becomes the better choice if coding is the priority.
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
GPT-5.3 Codex is clearly ahead on the provisional aggregate, 82 to 59. The gap is large enough that you do not need to squint at the spreadsheet to see the difference.
GPT-5.3 Codex's sharpest advantage is in agentic, where it averages 71.4 against 51.5. The single biggest benchmark swing on the page is Terminal-Bench 2.0, 77.3% to 51.5%. Qwen3.6-35B-A3B does hit back in coding, so the answer changes if that is the part of the workload you care about most.
GPT-5.3 Codex gives you the larger context window at 400K, compared with 262K for Qwen3.6-35B-A3B.
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 | Qwen3.6-35B-A3B |
|---|---|---|---|
| Agentic | GPT-5.3 Codex71.4 | Margin← 19.9 | Qwen3.6-35B-A3B51.5 |
| Coding | GPT-5.3 Codex67.2 | Margin→ 6.6 | Qwen3.6-35B-A3B73.8 |
| Knowledge | GPT-5.3 CodexNot measured | MarginNo overlap | Qwen3.6-35B-A3B51.8 |
| Math | GPT-5.3 CodexNot measured | MarginNo overlap | Qwen3.6-35B-A3B88.2 |
| Multimodal | GPT-5.3 CodexNot measured | MarginNo overlap | Qwen3.6-35B-A3B76.3 |
Decisive benchmark drivers
The largest measured benchmark gaps in this matchup, with exact reported values.
More
- Source ↗
Terminal-Bench 2.0
AgenticA 77.3%B 51.5%Winner: GPT-5.3 CodexΔ 25.8Terminal-Bench 2.0: GPT-5.3 Codex scored 77.3%; Qwen3.6-35B-A3B scored 51.5%. GPT-5.3 Codex wins this benchmark. - Source ↗
SWE-bench Verified
CodingA 85%B 73.4%Winner: GPT-5.3 CodexΔ 11.6SWE-bench Verified: GPT-5.3 Codex scored 85%; Qwen3.6-35B-A3B scored 73.4%. GPT-5.3 Codex wins this benchmark. - Source ↗
SWE-bench Pro
CodingA 56.8%B 49.5%Winner: GPT-5.3 CodexΔ 7.3SWE-bench Pro: GPT-5.3 Codex scored 56.8%; Qwen3.6-35B-A3B scored 49.5%. GPT-5.3 Codex 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 | Qwen3.6-35B-A3B | Comparison |
|---|---|---|---|
| Input / output priceUSD per 1M tokens | GPT-5.3 Codex$1.75 input / $14 output | Qwen3.6-35B-A3BNot available | A complete price comparison is not available. |
| Generation speedtokens per second | GPT-5.3 Codex79 tok/s | Qwen3.6-35B-A3BNot available | A complete speed comparison is not available. |
| First-answer latencyseconds to first token | GPT-5.3 Codex88.26 s | Qwen3.6-35B-A3BNot available | A complete latency comparison is not available. |
| Context windowmaximum listed tokens | GPT-5.3 Codex400K | Qwen3.6-35B-A3B262K | GPT-5.3 Codex lists the larger context window. |
Benchmark Deep Dive
AgenticGPT-5.3 Codex wins17 benchmarks
| Benchmark | GPT-5.3 Codex | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| Terminal-Bench 2.0Source | 77.3% | 51.5% | GPT-5.3 Codex leads |
| OSWorld-VerifiedSource | 64.7% | — | Not comparable |
| τ²-bench resultsSource | 86% | 95.3% | Qwen3.6-35B-A3B leads |
| Gert LabsSource | 57.47% | 42.65% | GPT-5.3 Codex leads |
| JobBenchSource | 33.7% | — | Not comparable |
| Claw-EvalSource | — | 68.7% | Not comparable |
| QwenClawBenchSource | — | 52.6% | Not comparable |
| QwenWebBenchSource | — | 1397 | Not comparable |
| τ³-bench resultsSource | — | 67.2% | Not comparable |
| VITA-BenchSource | — | 35.6% | Not comparable |
| DeepPlanningSource | — | 25.9% | Not comparable |
| ToolathlonSource | — | 26.9% | Not comparable |
| MCP AtlasSource | — | 62.8% | Not comparable |
| WideResearchSource | — | 60.1% | Not comparable |
| AA Agentic IndexSource | — | 21.4% | Not comparable |
| GDPval-AASource | — | 27.4% | Not comparable |
| GDPval-AASource | — | 1049 | Not comparable |
CodingQwen3.6-35B-A3B wins11 benchmarks
| Benchmark | GPT-5.3 Codex | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| SWE-bench VerifiedSource | 85% | 73.4% | GPT-5.3 Codex leads |
| SWE-bench ProSource | 56.8% | 49.5% | GPT-5.3 Codex leads |
| SWE-RebenchSource | 58.2% | — | Not comparable |
| Vibe Code BenchSource | 61.77% | — | Not comparable |
| Terminal-Bench HardSource | 53.0% | 34.8% | GPT-5.3 Codex leads |
| AA-SciCodeSource | 53.2% | 35.8% | GPT-5.3 Codex leads |
| SWE MultilingualSource | — | 67.2% | Not comparable |
| Terminal-Bench 2.0Source | — | 51.5% | Not comparable |
| LiveCodeBenchSource | — | 80.4% | Not comparable |
| NL2RepoSource | — | 29.4% | Not comparable |
| AA Coding IndexSource | — | 41.9% | Not comparable |
Reasoning2 benchmarks
Knowledge11 benchmarks
| Benchmark | GPT-5.3 Codex | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| Artificial Analysis Intelligence IndexSource | 44.3% | 31.6% | GPT-5.3 Codex leads |
| AA-GPQA DiamondSource | 91.5% | 84.1% | GPT-5.3 Codex leads |
| AA-HLESource | 39.9% | 20.2% | GPT-5.3 Codex leads |
| AA-Omniscience IndexSource | 9.9% | -21.4% | GPT-5.3 Codex leads |
| AA-Omniscience AccuracySource | 51.8% | 18.9% | GPT-5.3 Codex leads |
| AA-Omniscience Hallucination RateSource | 86.9% | 49.7% | Qwen3.6-35B-A3B leads |
| MMLU-ProSource | — | 85.2% | Not comparable |
| SuperGPQASource | — | 64.7% | Not comparable |
| C-EvalSource | — | 90% | Not comparable |
| GPQASource | — | 86% | Not comparable |
| HLESource | — | 21.4% | Not comparable |
Math5 benchmarks
Multimodal16 benchmarks
| Benchmark | GPT-5.3 Codex | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| AA-MMMU-ProSource | 78.5% | 75.0% | GPT-5.3 Codex leads |
| Design Arena WebsiteSource | 1197 | — | Not comparable |
| MMMUSource | — | 81.7% | Not comparable |
| MMMU-ProSource | — | 75.3% | Not comparable |
| RealWorldQASource | — | 85.3% | Not comparable |
| OmniDocBench 1.5Source | — | 89.9% | Not comparable |
| CharXivSource | — | 78% | Not comparable |
| SimpleVQASource | — | 58.9% | Not comparable |
| CC-OCRSource | — | 81.9% | Not comparable |
| AI2D_TESTSource | — | 92.7% | Not comparable |
| RefCOCO (avg)Source | — | 92.0% | Not comparable |
| ODINW13Source | — | 50.8% | Not comparable |
| Video-MME (with subtitle)Source | — | 86.6% | Not comparable |
| Video-MME (w/o subtitle)Source | — | 82.5% | Not comparable |
| VideoMMMUSource | — | 83.7% | Not comparable |
| MLVU (M-Avg)Source | — | 86.2% | Not comparable |
Inst. Following1 benchmarks
| Benchmark | GPT-5.3 Codex | Qwen3.6-35B-A3B | Result |
|---|---|---|---|
| AA-IFBenchSource | 75.4% | 64.4% | GPT-5.3 Codex leads |
Frequently Asked Questions (3)
Which is better, GPT-5.3 Codex or Qwen3.6-35B-A3B?
GPT-5.3 Codex is ahead on BenchLM's provisional leaderboard, 82 to 59. The biggest single separator in this matchup is Terminal-Bench 2.0, where the scores are 77.3% and 51.5%.
Which is better for coding, GPT-5.3 Codex or Qwen3.6-35B-A3B?
Qwen3.6-35B-A3B has the edge for coding in this comparison, averaging 73.8 versus 67.2. Inside this category, Terminal-Bench Hard is the benchmark that creates the most daylight between them.
Which is better for agentic tasks, GPT-5.3 Codex or Qwen3.6-35B-A3B?
GPT-5.3 Codex has the edge for agentic tasks in this comparison, averaging 71.4 versus 51.5. Inside this category, Terminal-Bench 2.0 is the benchmark that creates the most daylight between them.
Related Comparisons
Explore More
The AI models change fast. We track them for you.
A weekly brief for engineers and researchers covering new models, ranking shifts, and pricing changes.
Free. No spam. Unsubscribe anytime.