# GPT-5.2-Codex vs Qwen3.5-35B-A3B

> Side-by-side benchmark comparison for GPT-5.2-Codex and Qwen3.5-35B-A3B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gpt-5-2-codex-vs-qwen3-5-35b-a3b
- Last updated: September 28, 2026

- Shared sourced benchmarks: 1
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.7

## Quick Verdict

Evidence is too thin for a benchmark verdict: GPT-5.2-Codex and Qwen3.5-35B-A3B share only 1 sourced benchmark row.

## Summary

- Only 1 shared sourced benchmark row is available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- Qwen3.5-35B-A3B has the lower published output-token price.
- GPT-5.2-Codex has the larger published context window at 400K.

## Model Snapshot

| Property | GPT-5.2-Codex | Qwen3.5-35B-A3B |
|----------|----------|----------|
| Creator | OpenAI | Alibaba |
| Type | Proprietary | Open Weight |
| Reasoning | Reasoning | Reasoning |
| Context | 400K | 262K |
| Independent public score (not head-to-head) | 50.09 | 47 |
| Benchmarks Covered | 5 | 16 |
| Pricing (input/output) | $1.75 / $14.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- GPT-5.2-Codex public-lane score: 34.6 (Estimated · #67/117)
- Qwen3.5-35B-A3B public-lane score: 29.4 (Estimated · #81/117)

| Benchmark | GPT-5.2-Codex | Qwen3.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| Gert Labs | 51.79% | 28.96% | GPT-5.2-Codex |
| JobBench | 26.0% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | Coming soon | 40.5% | Coming soon |
| BrowseComp | Coming soon | 61% | Coming soon |
| OSWorld-Verified | Coming soon | 54.5% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- GPT-5.2-Codex public-lane score: 45.2 (Supported · #51/142)
- Qwen3.5-35B-A3B public-lane score: 26.7 (Estimated · #100/142)

| Benchmark | GPT-5.2-Codex | Qwen3.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| Vibe Code Bench | 37.91% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 88.0% | Coming soon | Coming soon |
| SWE-bench (Vals) | 72.4% | Coming soon | Coming soon |
| SWE-bench Verified | Coming soon | 69.2% | Coming soon |
| SWE-Rebench | Coming soon | 53.7% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- GPT-5.2-Codex public-lane score: 78.9 (Unranked · 2 rankable rows)
- Qwen3.5-35B-A3B public-lane score: 41.4 (Unranked · 3 rankable rows)

| Benchmark | GPT-5.2-Codex | Qwen3.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| LongBench v2 | Coming soon | 59% | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- GPT-5.2-Codex public-lane score: 73.5 (Unranked · 1 rankable row)
- Qwen3.5-35B-A3B public-lane score: 68.2 (Unranked · 3 rankable rows)

| Benchmark | GPT-5.2-Codex | Qwen3.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| MMMU | Coming soon | 81.4% | Coming soon |
| MMVU | Coming soon | 72.3% | Coming soon |
| MathVision | Coming soon | 83.9% | Coming soon |
| V* | Coming soon | 92.7% | Coming soon |

### Knowledge

- Winner: Insufficient shared evidence
- GPT-5.2-Codex public-lane score: 52.1 (Estimated · #59/168)
- Qwen3.5-35B-A3B public-lane score: 39.7 (Supported · #100/168)

| Benchmark | GPT-5.2-Codex | Qwen3.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-Pro | Coming soon | 85.3% | Coming soon |
| SuperGPQA | Coming soon | 63.4% | Coming soon |
| GPQA | Coming soon | 84.2% | Coming soon |

### Multilingual

- Winner: Insufficient shared evidence
- GPT-5.2-Codex public-lane score: Coming soon
- Qwen3.5-35B-A3B public-lane score: 21.1 (#11/12)

| Benchmark | GPT-5.2-Codex | Qwen3.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| MMLU-ProX | Coming soon | 81% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- GPT-5.2-Codex public-lane score: 92.4 (#3/124)
- Qwen3.5-35B-A3B public-lane score: 87.4 (#30/124)

| Benchmark | GPT-5.2-Codex | Qwen3.5-35B-A3B | Winner |
|-----------|-----------|-----------|--------|
| IFEval | Coming soon | 91.9% | Coming soon |

## FAQ

### Is there enough evidence to pick between GPT-5.2-Codex and Qwen3.5-35B-A3B?

Not yet. The models share only 1 sourced benchmark row, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [GPT-5.2-Codex vs GPT-6 Astra](/compare/gpt-5-2-codex-vs-gpt-6-astra)
- [Qwen3.5-35B-A3B vs GPT-6 Astra](/compare/gpt-6-astra-vs-qwen3-5-35b-a3b)
- [GPT-5.2-Codex vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-gpt-5-2-codex)
- [Qwen3.5-35B-A3B vs Claude Opus 5.5](/compare/claude-opus-5-5-vs-qwen3-5-35b-a3b)

## Explore More

- [GPT-5.2-Codex profile](/models/gpt-5-2-codex)
- [Qwen3.5-35B-A3B profile](/models/qwen3-5-35b-a3b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)