# Claude Sonnet 4.5 vs GPT-5.3 Codex

> Side-by-side benchmark comparison for Claude Sonnet 4.5 and GPT-5.3 Codex across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/claude-sonnet-4-5-vs-gpt-5-3-codex
- Last updated: October 17, 2026

- Shared sourced benchmarks: 6
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

GPT-5.3 Codex leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- GPT-5.3 Codex has the higher overall point estimate 60.48 to 47.96. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in reasoning, where the averages are 22.9 for Claude Sonnet 4.5 and 83.1 for GPT-5.3 Codex.
- The biggest single benchmark swing is Terminal-Bench 2.0 in Agentic, with scores of 50% and 77.3%.
- GPT-5.3 Codex is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- GPT-5.3 Codex also has the larger context window at 400K.

## Model Snapshot

| Property | Claude Sonnet 4.5 | GPT-5.3 Codex |
|----------|----------|----------|
| Creator | Anthropic | OpenAI |
| Type | Proprietary | Proprietary |
| Reasoning | Non-Reasoning | Reasoning |
| Context | 200K | 400K |
| Overall Score | 47.96 | 60.48 |
| Benchmarks Covered | 12 | 11 |
| Pricing (input/output) | $3.00 / $15.00 | $1.75 / $14.00 |

## Category Breakdown

### Agentic

- Winner: Directional only
- Claude Sonnet 4.5 public-lane score: 35.1 (Estimated · #81/128)
- GPT-5.3 Codex public-lane score: 55.5 (Estimated · #41/128)

| Benchmark | Claude Sonnet 4.5 | GPT-5.3 Codex | Winner |
|-----------|-----------|-----------|--------|
| Terminal-Bench 2.0 | 50% | 77.3% | GPT-5.3 Codex |
| OSWorld-Verified | 61.4% | 64.7% | GPT-5.3 Codex |
| VITA-Bench | 17.0% | Coming soon | Coming soon |
| Gert Labs | 48.51% | 57.47% | GPT-5.3 Codex |
| JobBench | 27.7% | 33.7% | GPT-5.3 Codex |

### Coding

- Winner: Not comparable
- Claude Sonnet 4.5 public-lane score: Coming soon
- GPT-5.3 Codex public-lane score: 53.5 (Supported · #35/150)

| Benchmark | Claude Sonnet 4.5 | GPT-5.3 Codex | Winner |
|-----------|-----------|-----------|--------|
| SWE-bench Verified | 77.2% | 85% | GPT-5.3 Codex |
| Terminal-Bench 2.0 | 50.0% | 77.3% | GPT-5.3 Codex |
| SWE-bench Pro | Coming soon | 56.8% | Coming soon |
| SWE-Rebench | Coming soon | 58.2% | Coming soon |
| Vibe Code Bench | Coming soon | 61.77% | Coming soon |
| LiveCodeBench (Vals) | Coming soon | 87.3% | Coming soon |
| SWE-bench (Vals) | Coming soon | 78.0% | Coming soon |

### Reasoning

- Winner: Not comparable
- Claude Sonnet 4.5 public-lane score: 22.9 (Unranked · 1 rankable row)
- GPT-5.3 Codex public-lane score: 83.1 (Unranked · 2 rankable rows)

| Benchmark | Claude Sonnet 4.5 | GPT-5.3 Codex | Winner |
|-----------|-----------|-----------|--------|
| ARC-AGI-2 | 13.6% | Coming soon | Coming soon |

### Multimodal & Grounded

- Winner: Not comparable
- Claude Sonnet 4.5 public-lane score: Coming soon
- GPT-5.3 Codex public-lane score: 80.1 (Unranked · 1 rankable row)

### Knowledge

- Winner: Not comparable
- Claude Sonnet 4.5 public-lane score: Coming soon
- GPT-5.3 Codex public-lane score: 65.4 (Estimated · #33/184)

| Benchmark | Claude Sonnet 4.5 | GPT-5.3 Codex | Winner |
|-----------|-----------|-----------|--------|
| GPQA | 83.4% | Coming soon | Coming soon |

### Instruction Following

- Winner: Not comparable
- Claude Sonnet 4.5 public-lane score: Coming soon
- GPT-5.3 Codex public-lane score: 92.6 (#18/148)

### Mathematics

- Winner: Not comparable
- Claude Sonnet 4.5 public-lane score: 36.4 (Unranked · 2 rankable rows)
- GPT-5.3 Codex public-lane score: Coming soon

| Benchmark | Claude Sonnet 4.5 | GPT-5.3 Codex | Winner |
|-----------|-----------|-----------|--------|
| AIME 2025 | 87% | Coming soon | Coming soon |
| FrontierMath v2 (Tiers 1-3) | 23.860% | Coming soon | Coming soon |
| FrontierMath v2 (Tier 4) | 2.439% | Coming soon | Coming soon |

## FAQ

### Which is better overall, Claude Sonnet 4.5 or GPT-5.3 Codex?

GPT-5.3 Codex has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between Claude Sonnet 4.5 and GPT-5.3 Codex?

The widest category gap is in reasoning, where the averages are 22.9 for Claude Sonnet 4.5 and 83.1 for GPT-5.3 Codex.

### How many benchmarks does Claude Sonnet 4.5 cover on BenchLM?

Claude Sonnet 4.5 currently has 12 sourced benchmark scores on BenchLM.

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

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

## Related Comparisons

- [Claude Sonnet 4.5 vs Claude Sonnet 4.5 Thinking](/compare/claude-sonnet-4-5-vs-claude-sonnet-4-5-thinking)
- [GPT-5.3 Codex vs Claude Sonnet 4.5 Thinking](/compare/claude-sonnet-4-5-thinking-vs-gpt-5-3-codex)
- [Claude Sonnet 4.5 vs GPT-5.3-Codex-Spark](/compare/claude-sonnet-4-5-vs-gpt-5-3-codex-spark)
- [GPT-5.3 Codex vs GPT-5.3-Codex-Spark](/compare/gpt-5-3-codex-vs-gpt-5-3-codex-spark)

## Explore More

- [Claude Sonnet 4.5 profile](/models/claude-sonnet-4-5)
- [GPT-5.3 Codex profile](/models/gpt-5-3-codex)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)