# Gemma 3 1B vs GPT-5.3 Codex

> GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 21.1 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gemma-3-1b-vs-gpt-5-3-codex
- Last updated: 2026-10-11
- Shared benchmarks: 0

## Summary

- The widest gap is in agentic & tool use, where GPT-5.3 Codex leads 48.0 to 13.7.
- Gemma 3 1B has downloadable open weights; the other is API-only.

## Snapshot

| | Gemma 3 1B | GPT-5.3 Codex |
|---|---|---|
| Provider | Google | OpenAI |
| Noometry Index | 21.1 | 45.8 |
| Rank | 353 | 69 |
| Context | — | 400K |
| Input $/M | — | $1.75 |
| Output $/M | — | $14 |
| Weights | Open | Proprietary |

## Coding

- Gemma 3 1B: —
- GPT-5.3 Codex: 48.6 (#56)

| Benchmark | Gemma 3 1B | GPT-5.3 Codex |
|---|---|---|
| SWE-bench Verified | — | 74.8% |
| LMArena WebDev | — | 1409 |
| WeirdML | — | 79.3% |
| ALE-Bench | — | 1,655 |

## Agentic & Tool Use

- Gemma 3 1B: 13.7 (#152)
- GPT-5.3 Codex: 48.0 (#9)

| Benchmark | Gemma 3 1B | GPT-5.3 Codex |
|---|---|---|
| Terminal-Bench | — | 78.4% |
| Berkeley Function Calling Leaderboard | 7.2% | — |
| METR Time Horizons | — | 74.5% |
| Vending-Bench 2 | — | 5,940 |

## Reasoning

- Gemma 3 1B: 19.2 (#264)
- GPT-5.3 Codex: —

| Benchmark | Gemma 3 1B | GPT-5.3 Codex |
|---|---|---|
| Chess Puzzles | 0% | — |
| Epoch Capabilities Index | — | 156.77 |

## Math

- Gemma 3 1B: 10.2 (#316)
- GPT-5.3 Codex: —

| Benchmark | Gemma 3 1B | GPT-5.3 Codex |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 1.1% | — |

## Knowledge

- Gemma 3 1B: 7.0 (#314)
- GPT-5.3 Codex: —

| Benchmark | Gemma 3 1B | GPT-5.3 Codex |
|---|---|---|
| GPQA Diamond | 19.9% | — |

## FAQ

### Is Gemma 3 1B better than GPT-5.3 Codex?

GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 21.1 on the Noometry Index.

### How many benchmarks do Gemma 3 1B and GPT-5.3 Codex share?

0 benchmarks have published results for both models. Gemma 3 1B has 4 scored results on Noometry and GPT-5.3 Codex has 8.