# GPT-5-Codex vs Palm 2

> GPT-5-Codex is the stronger model overall, scoring 37.9 to 30.0 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-codex-vs-palm-2
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in coding, where GPT-5-Codex leads 42.4 to 29.0.

## Snapshot

| | GPT-5-Codex | Palm 2 |
|---|---|---|
| Provider | OpenAI | Google |
| Noometry Index | 37.9 | 30.0 |
| Rank | 192 | 298 |
| Context | 400K | — |
| Input $/M | $1.25 | — |
| Output $/M | $10 | — |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5-Codex: 42.4 (#103)
- Palm 2: 29.0 (#311)

| Benchmark | GPT-5-Codex | Palm 2 |
|---|---|---|
| WeirdML | 54.5% | — |
| LMArena Coding | — | 994 |

## Agentic & Tool Use

- GPT-5-Codex: 31.0 (#72)
- Palm 2: —

| Benchmark | GPT-5-Codex | Palm 2 |
|---|---|---|
| Terminal-Bench | 44.3% | — |

## Reasoning

- GPT-5-Codex: 30.9 (#83)
- Palm 2: 19.1 (#271)

| Benchmark | GPT-5-Codex | Palm 2 |
|---|---|---|
| Kagi LLM Benchmark | 70.3% | — |
| LMArena Hard Prompts | — | 1005 |

## Math

- GPT-5-Codex: —
- Palm 2: 30.8 (#231)

| Benchmark | GPT-5-Codex | Palm 2 |
|---|---|---|
| LMArena Math | — | 1049 |

## Multilingual

- GPT-5-Codex: —
- Palm 2: 20.9 (#295)

| Benchmark | GPT-5-Codex | Palm 2 |
|---|---|---|
| LMArena Non-English | — | 916 |
| LMArena Chinese | — | 887 |

## Instruction Following

- GPT-5-Codex: —
- Palm 2: 51.0 (#296)

| Benchmark | GPT-5-Codex | Palm 2 |
|---|---|---|
| LMArena Instruction Following | — | 1010 |

## Long Context

- GPT-5-Codex: —
- Palm 2: 30.8 (#285)

| Benchmark | GPT-5-Codex | Palm 2 |
|---|---|---|
| LMArena Longer Query | — | 1010 |

## Writing & Preference

- GPT-5-Codex: —
- Palm 2: 25.6 (#304)

| Benchmark | GPT-5-Codex | Palm 2 |
|---|---|---|
| LMArena Text | — | 1027 |
| LMArena Creative Writing | — | 991 |
| LMArena Multi-Turn | — | 994 |

## FAQ

### Is GPT-5-Codex better than Palm 2?

GPT-5-Codex is the stronger model overall, scoring 37.9 to 30.0 on the Noometry Index.

### Is GPT-5-Codex or Palm 2 better for coding?

GPT-5-Codex scores higher on coding benchmarks: 42.4 versus 29.0 in the Noometry coding category.

### How many benchmarks do GPT-5-Codex and Palm 2 share?

0 benchmarks have published results for both models. GPT-5-Codex has 3 scored results on Noometry and Palm 2 has 10.