# Claude 2.1 vs GPT-5-Codex

> GPT-5-Codex is the stronger model overall, scoring 37.9 to 25.2 on the Noometry Index.

- Canonical page: https://noometry.com/compare/claude-2-1-vs-gpt-5-codex
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. Claude 2.1 scores higher in 0 categories and GPT-5-Codex in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where GPT-5-Codex leads 42.4 to 26.2.
- The biggest single-benchmark swing is WeirdML: 7.1% for Claude 2.1 and 54.5% for GPT-5-Codex.

## Snapshot

| | Claude 2.1 | GPT-5-Codex |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 25.2 | 37.9 |
| Rank | 345 | 192 |
| Context | — | 400K |
| Input $/M | — | $1.25 |
| Output $/M | — | $10 |
| Weights | Proprietary | Proprietary |

## Coding

- Claude 2.1: 26.2 (#327)
- GPT-5-Codex: 42.4 (#103)

| Benchmark | Claude 2.1 | GPT-5-Codex |
|---|---|---|
| WeirdML | 7.1% | 54.5% |

## Agentic & Tool Use

- Claude 2.1: —
- GPT-5-Codex: 31.0 (#72)

| Benchmark | Claude 2.1 | GPT-5-Codex |
|---|---|---|
| Terminal-Bench | — | 44.3% |

## Reasoning

- Claude 2.1: 21.4 (#221)
- GPT-5-Codex: 30.9 (#83)

| Benchmark | Claude 2.1 | GPT-5-Codex |
|---|---|---|
| Kagi LLM Benchmark | — | 70.3% |
| DTBench | 51% | — |
| Epoch Capabilities Index | 119.27 | — |
| ForecastBench | 54.2 | — |

## Math

- Claude 2.1: 10.2 (#315)
- GPT-5-Codex: —

| Benchmark | Claude 2.1 | GPT-5-Codex |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.9% | — |

## Knowledge

- Claude 2.1: 15.4 (#292)
- GPT-5-Codex: —

| Benchmark | Claude 2.1 | GPT-5-Codex |
|---|---|---|
| GPQA Diamond | 33% | — |
| MMLU | 73.5% | — |

## FAQ

### Is Claude 2.1 better than GPT-5-Codex?

GPT-5-Codex is the stronger model overall, scoring 37.9 to 25.2 on the Noometry Index.

### Is Claude 2.1 or GPT-5-Codex better for coding?

GPT-5-Codex scores higher on coding benchmarks: 42.4 versus 26.2 in the Noometry coding category.

### How many benchmarks do Claude 2.1 and GPT-5-Codex share?

1 benchmark has published results for both models. Claude 2.1 has 7 scored results on Noometry and GPT-5-Codex has 3.