# GPT-5.3 Codex vs GPT-OSS 120B

> Side-by-side benchmark comparison for GPT-5.3 Codex and GPT-OSS 120B across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gpt-5-3-codex-vs-gpt-oss-120b
- Last updated: October 17, 2026

- Shared sourced benchmarks: 2
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Evidence is too thin for a benchmark verdict: GPT-5.3 Codex and GPT-OSS 120B share only 2 sourced benchmark rows.

## Summary

- Only 2 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- GPT-OSS 120B has the lower published output-token price.
- GPT-5.3 Codex has the larger published context window at 400K.

## Model Snapshot

| Property | GPT-5.3 Codex | GPT-OSS 120B |
|----------|----------|----------|
| Creator | OpenAI | OpenAI |
| Type | Proprietary | Open Weight |
| Reasoning | Reasoning | Non-Reasoning |
| Context | 400K | 128K |
| Independent public score (not head-to-head) | 60.48 | 37.32 |
| Benchmarks Covered | 11 | 8 |
| Pricing (input/output) | $1.75 / $14.00 | $0.00 / $0.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- GPT-5.3 Codex public-lane score: 55.5 (Estimated · #41/128)
- GPT-OSS 120B public-lane score: 19.5 (Estimated · #110/128)

| Benchmark | GPT-5.3 Codex | GPT-OSS 120B | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 77.3% | Coming soon | Coming soon |
| OSWorld-Verified | 64.7% | Coming soon | Coming soon |
| Gert Labs | 57.47% | 29.61% | GPT-5.3 Codex |
| JobBench | 33.7% | Coming soon | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- GPT-5.3 Codex public-lane score: 53.5 (Supported · #35/150)
- GPT-OSS 120B public-lane score: 23 (Estimated · #111/150)

| Benchmark | GPT-5.3 Codex | GPT-OSS 120B | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 85% | 62.4% | GPT-5.3 Codex |
| SWE-bench Pro | 56.8% | Coming soon | Coming soon |
| SWE-Rebench | 58.2% | Coming soon | Coming soon |
| Terminal-Bench 2.0 | 77.3% | Coming soon | Coming soon |
| Vibe Code Bench | 61.77% | Coming soon | Coming soon |
| LiveCodeBench (Vals) | 87.3% | Coming soon | Coming soon |
| SWE-bench (Vals) | 78.0% | Coming soon | Coming soon |
| React Native Evals | Coming soon | 71.6% | Coming soon |

### Reasoning

- Winner: Insufficient shared evidence
- GPT-5.3 Codex public-lane score: 83.1 (Unranked · 2 rankable rows)
- GPT-OSS 120B public-lane score: 61.6 (Unranked · 2 rankable rows)

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- GPT-5.3 Codex public-lane score: 80.1 (Unranked · 1 rankable row)
- GPT-OSS 120B public-lane score: Coming soon

### Knowledge

- Winner: Insufficient shared evidence
- GPT-5.3 Codex public-lane score: 65.4 (Estimated · #33/184)
- GPT-OSS 120B public-lane score: 38.6 (Supported · #122/184)

| Benchmark | GPT-5.3 Codex | GPT-OSS 120B | Winner |
|-----------|-----------|-----------|--------|
| MMLU | Coming soon | 90% | Coming soon |
| GPQA | Coming soon | 80.1% | Coming soon |
| HLE | Coming soon | 14.9% | Coming soon |

### Instruction Following

- Winner: Insufficient shared evidence
- GPT-5.3 Codex public-lane score: 92.6 (#18/148)
- GPT-OSS 120B public-lane score: 84.3 (#50/148)

### Mathematics

- Winner: Insufficient shared evidence
- GPT-5.3 Codex public-lane score: Coming soon
- GPT-OSS 120B public-lane score: Coming soon

| Benchmark | GPT-5.3 Codex | GPT-OSS 120B | Winner |
|-----------|-----------|-----------|--------|
| AIME 2024 | Coming soon | 95.8% | Coming soon |
| AIME 2025 | Coming soon | 92.5% | Coming soon |

## FAQ

### Is there enough evidence to pick between GPT-5.3 Codex and GPT-OSS 120B?

Not yet. The models share only 2 sourced benchmark rows, 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-5.3 Codex vs GPT-5.3-Codex-Spark](/compare/gpt-5-3-codex-vs-gpt-5-3-codex-spark)
- [GPT-OSS 120B vs GPT-5.3-Codex-Spark](/compare/gpt-5-3-codex-spark-vs-gpt-oss-120b)
- [GPT-5.3 Codex vs GPT-OSS 20B](/compare/gpt-5-3-codex-vs-gpt-oss-20b)
- [GPT-OSS 120B vs GPT-OSS 20B](/compare/gpt-oss-120b-vs-gpt-oss-20b)

## Explore More

- [GPT-5.3 Codex profile](/models/gpt-5-3-codex)
- [GPT-OSS 120B profile](/models/gpt-oss-120b)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)