# GPT-5.3 Codex vs Inkling

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

- Canonical page: https://benchlm.ai/compare/gpt-5-3-codex-vs-inkling
- Last updated: October 14, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

Pick GPT-5.3 Codex if you want the stronger benchmark profile. Inkling only makes more sense when its price, context window, or workload-specific category wins matter more than the overall score.

## Summary

- GPT-5.3 Codex leads overall 59.84 to 52.13.
- The clearest category separation is in coding, where the averages are 54.5 for GPT-5.3 Codex and 34 for Inkling.
- The biggest single benchmark swing is SWE-bench Verified in Coding, with scores of 85% and 77.6%.
- Inkling is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- Inkling also has the larger context window at 1M.

## Model Snapshot

| Property | GPT-5.3 Codex | Inkling |
|----------|----------|----------|
| Creator | OpenAI | Thinking Machines Lab |
| Type | Proprietary | Open Weight |
| Reasoning | Reasoning | Hybrid |
| Context | 400K | 1M |
| Overall Score | 59.84 | 52.13 |
| Benchmarks Covered | 11 | 24 |
| Pricing (input/output) | $1.75 / $14.00 | $1.87 / $4.68 |

## Category Breakdown

### Agentic

- Winner: Directional only
- GPT-5.3 Codex public-lane score: 55.2 (Estimated · #35/124)
- Inkling public-lane score: 36.2 (Supported · #72/124)

| Benchmark | GPT-5.3 Codex | Inkling | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 77.3% | Coming soon | Coming soon |
| OSWorld-Verified | 64.7% | Coming soon | Coming soon |
| Gert Labs | 57.47% | Coming soon | Coming soon |
| JobBench | 33.7% | Coming soon | Coming soon |
| Terminal-Bench 2.1 | Coming soon | 63.8% | Coming soon |
| BrowseComp | Coming soon | 77.1% | Coming soon |
| MCP Atlas | Coming soon | 74.1% | Coming soon |
| Terminal-Bench 2.1 (Vals) | Coming soon | 47.6% | Coming soon |
| CWE-bench v1 | Coming soon | 37.0% | Coming soon |

### Coding

- Winner: GPT-5.3 Codex
- GPT-5.3 Codex public-lane score: 54.5 (Supported · #31/149)
- Inkling public-lane score: 34 (Supported · #80/149)

| Benchmark | GPT-5.3 Codex | Inkling | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 85% | 77.6% | GPT-5.3 Codex |
| SWE-bench Pro | 56.8% | 54.3% | GPT-5.3 Codex |
| 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% | 85.5% | GPT-5.3 Codex |
| SWE-bench (Vals) | 78.0% | 77.6% | GPT-5.3 Codex |
| Terminal-Bench 2.1 | Coming soon | 63.8% | Coming soon |
| FrontierSWE v2 | Coming soon | 4.1% | Coming soon |

### Reasoning

- Winner: Not comparable
- GPT-5.3 Codex public-lane score: 83.1 (Unranked · 2 rankable rows)
- Inkling public-lane score: 79 (#14/29)

### Multimodal & Grounded

- Winner: Not comparable
- GPT-5.3 Codex public-lane score: 80.1 (Unranked · 1 rankable row)
- Inkling public-lane score: 67.5 (#35/54)

| Benchmark | GPT-5.3 Codex | Inkling | Winner |
|-----------|-----------|-----------|--------|
| MMMU-Pro | Coming soon | 73.5% | Coming soon |
| CharXiv | Coming soon | 82% | Coming soon |
| CharXiv w/o tools | Coming soon | 78.1% | Coming soon |

### Knowledge

- Winner: Directional only
- GPT-5.3 Codex public-lane score: 65.3 (Estimated · #31/181)
- Inkling public-lane score: 54.5 (Supported · #62/181)

| Benchmark | GPT-5.3 Codex | Inkling | Winner |
|-----------|-----------|-----------|--------|
| GPQA | Coming soon | 87.9% | Coming soon |
| GPQA-D | Coming soon | 87.9% | Coming soon |
| HLE | Coming soon | 46% | Coming soon |
| HLE w/o tools | Coming soon | 30% | Coming soon |
| GPQA Diamond (Vals) | Coming soon | 87.1% | Coming soon |
| MMLU-Pro (Vals) | Coming soon | 86.3% | Coming soon |

### Instruction Following

- Winner: Directional only
- GPT-5.3 Codex public-lane score: 92.6 (#18/128)
- Inkling public-lane score: 87.6 (#35/128)

| Benchmark | GPT-5.3 Codex | Inkling | Winner |
|-----------|-----------|-----------|--------|
| IFBench | Coming soon | 79.8% | Coming soon |

### Mathematics

- Winner: Not comparable
- GPT-5.3 Codex public-lane score: Coming soon
- Inkling public-lane score: 58.3 (#11/12)

| Benchmark | GPT-5.3 Codex | Inkling | Winner |
|-----------|-----------|-----------|--------|
| AIME26 | Coming soon | 97.1% | Coming soon |
| FrontierMath v2 (Tiers 1-3) | Coming soon | 33.333% | Coming soon |
| FrontierMath v2 (Tier 4) | Coming soon | 4.878% | Coming soon |

## FAQ

### Which is better overall, GPT-5.3 Codex or Inkling?

GPT-5.3 Codex is ahead overall on BenchLM right now.

### Where is the biggest gap between GPT-5.3 Codex and Inkling?

The widest category gap is in coding, where the averages are 54.5 for GPT-5.3 Codex and 34 for Inkling.

### How many benchmarks does GPT-5.3 Codex cover on BenchLM?

GPT-5.3 Codex currently has 11 sourced benchmark scores on BenchLM.

### How many benchmarks does Inkling cover on BenchLM?

Inkling currently has 24 sourced benchmark scores on BenchLM.

## Related Comparisons

- [GPT-5.3 Codex vs GPT-5.3-Codex-Spark](/compare/gpt-5-3-codex-vs-gpt-5-3-codex-spark)
- [Inkling vs GPT-5.3-Codex-Spark](/compare/gpt-5-3-codex-spark-vs-inkling)
- [GPT-5.3 Codex vs Inkling-Small](/compare/gpt-5-3-codex-vs-inkling-small)
- [Inkling vs Inkling-Small](/compare/inkling-vs-inkling-small)

## Explore More

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