# GPT-5-Codex vs Sonar

> GPT-5-Codex and Sonar score almost the same on the Noometry Index (37.9 vs 38.5), so choose on price, context window or the category you care about most.

- Canonical page: https://noometry.com/compare/gpt-5-codex-vs-sonar
- Last updated: 2026-10-10
- Shared benchmarks: 0

## Summary

- The widest gap is in reasoning, where GPT-5-Codex leads 30.9 to 21.1.
- Sonar is cheaper at $1 / $1 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- GPT-5-Codex accepts more context: 400K tokens versus 128K.

## Snapshot

| | GPT-5-Codex | Sonar |
|---|---|---|
| Provider | OpenAI | Perplexity |
| Noometry Index | 37.9 | 38.5 |
| Rank | 192 | 187 |
| Context | 400K | 128K |
| Input $/M | $1.25 | $1 |
| Output $/M | $10 | $1 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5-Codex: 42.4 (#103)
- Sonar: 35.7 (#221)

| Benchmark | GPT-5-Codex | Sonar |
|---|---|---|
| WeirdML | 54.5% | — |
| LiveBench Coding | — | 35.1% |

## Agentic & Tool Use

- GPT-5-Codex: 31.0 (#72)
- Sonar: —

| Benchmark | GPT-5-Codex | Sonar |
|---|---|---|
| Terminal-Bench | 44.3% | — |

## Reasoning

- GPT-5-Codex: 30.9 (#83)
- Sonar: 21.1 (#227)

| Benchmark | GPT-5-Codex | Sonar |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | — |
| LiveBench Reasoning | — | 46.3% |
| LiveBench Data Analysis | — | 37.9% |
| LiveBench | — | 46.9% |

## Math

- GPT-5-Codex: —
- Sonar: 33.7 (#200)

| Benchmark | GPT-5-Codex | Sonar |
|---|---|---|
| LiveBench Math | — | 41.6% |

## Instruction Following

- GPT-5-Codex: —
- Sonar: 71.4 (#150)

| Benchmark | GPT-5-Codex | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |

## Writing & Preference

- GPT-5-Codex: —
- Sonar: 52.6 (#167)

| Benchmark | GPT-5-Codex | Sonar |
|---|---|---|
| LiveBench Language | — | 44.1% |

## FAQ

### Is GPT-5-Codex better than Sonar?

GPT-5-Codex and Sonar score almost the same on the Noometry Index (37.9 vs 38.5), so choose on price, context window or the category you care about most.

### Which is cheaper, GPT-5-Codex or Sonar?

Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; GPT-5-Codex lists at $1.25 and $10.

### Is GPT-5-Codex or Sonar better for coding?

GPT-5-Codex scores higher on coding benchmarks: 42.4 versus 35.7 in the Noometry coding category.

### Which has the bigger context window?

GPT-5-Codex does, with 400K tokens against 128K.

### How many benchmarks do GPT-5-Codex and Sonar share?

0 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Sonar has 7.