Model comparison
Gemma 4 31B IT vs GPT-5.3 Codex
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 32× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
GoogleSummary
- They share 4 benchmarks with published results for both. Gemma 4 31B IT scores higher in 0 categories and GPT-5.3 Codex in 1 category; one gap is clear of the uncertainty.
- The widest gap is in coding, where GPT-5.3 Codex leads 48.6 to 42.3.
- The biggest single-benchmark swing is WeirdML: 52.3% for Gemma 4 31B IT and 79.3% for GPT-5.3 Codex.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
- GPT-5.3 Codex accepts more context: 400K tokens versus 262K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 4 31B IT | GPT-5.3 Codex | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 43.5 | 45.8 |
| Released | 2026-04-02 | 2026-02-05 |
| Weights | Open | Proprietary |
| Context window | 262K | 400K |
| Max output | 33K | 128K |
| Input $ / M tokens | $0.09 | $1.75 |
| Output $ / M tokens | $0.34 | $14 |
| Results tracked | 35 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Codex leads
Gemma 4 31B IT: 42.3 (#108), GPT-5.3 Codex: 48.6 (#56)
| Benchmark | Gemma 4 31B IT | GPT-5.3 Codex |
|---|---|---|
| LMArena WebDev | 1366 | 1409 |
| WeirdML | 52.3% | 79.3% |
| ALE-Bench | 925.5 | 1,655 |
| SWE-bench Verified | — | 74.8% |
| SciCode | 43.4% | — |
| LMArena Coding | 1459 | — |
Agentic & Tool Use Not comparable
Gemma 4 31B IT: —, GPT-5.3 Codex: 48.0 (#9)
| Benchmark | Gemma 4 31B IT | GPT-5.3 Codex |
|---|---|---|
| Terminal-Bench | — | 78.4% |
| METR Time Horizons | — | 74.5% |
| Vending-Bench 2 | — | 5,940 |
Reasoning Not comparable
Gemma 4 31B IT: 27.2 (#122), GPT-5.3 Codex: —
| Benchmark | Gemma 4 31B IT | GPT-5.3 Codex |
|---|---|---|
| Epoch Capabilities Index | 142.74 | 156.77 |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| CritPt | 1.4% | — |
| Chess Puzzles | 5% | — |
| Thematic Generalization | 53% | — |
| LMArena Hard Prompts | 1448 | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
Math Not comparable
Gemma 4 31B IT: 43.2 (#81), GPT-5.3 Codex: —
| Benchmark | Gemma 4 31B IT | GPT-5.3 Codex |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| LMArena Math | 1465 | — |
Knowledge Not comparable
Gemma 4 31B IT: 37.9 (#151), GPT-5.3 Codex: —
| Benchmark | Gemma 4 31B IT | GPT-5.3 Codex |
|---|---|---|
| GPQA Diamond | 75.8% | — |
| SimpleQA Verified | 10.4% | — |
| Vectara Hallucination Rate | 7.4% | — |
| LMArena Expert | 1465 | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.6 (#34), GPT-5.3 Codex: —
| Benchmark | Gemma 4 31B IT | GPT-5.3 Codex |
|---|---|---|
| LMArena Vision | 1277 | — |
| LMArena Document | 1425 | — |
Multilingual Not comparable
Gemma 4 31B IT: 53.8 (#57), GPT-5.3 Codex: —
| Benchmark | Gemma 4 31B IT | GPT-5.3 Codex |
|---|---|---|
| LMArena Non-English | 1431 | — |
| LMArena Chinese | 1476 | — |
| LMArena French | 1435 | — |
| LMArena Russian | 1460 | — |
| LMArena Spanish | 1444 | — |
Instruction Following Not comparable
Gemma 4 31B IT: 75.5 (#61), GPT-5.3 Codex: —
| Benchmark | Gemma 4 31B IT | GPT-5.3 Codex |
|---|---|---|
| LMArena Instruction Following | 1433 | — |
Long Context Not comparable
Gemma 4 31B IT: 44.2 (#71), GPT-5.3 Codex: —
| Benchmark | Gemma 4 31B IT | GPT-5.3 Codex |
|---|---|---|
| LMArena Longer Query | 1446 | — |
Writing & Preference Not comparable
Gemma 4 31B IT: 60.5 (#96), GPT-5.3 Codex: —
| Benchmark | Gemma 4 31B IT | GPT-5.3 Codex |
|---|---|---|
| LMArena Text | 1443 | — |
| LMArena Creative Writing | 1415 | — |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
| LMArena Multi-Turn | 1452 | — |
Frequently asked questions
Is Gemma 4 31B IT better than GPT-5.3 Codex?
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 43.5 on the Noometry Index. Gemma 4 31B IT costs 32× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.
Which is cheaper, Gemma 4 31B IT or GPT-5.3 Codex?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.
Is Gemma 4 31B IT or GPT-5.3 Codex better for coding?
GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 42.3 in the Noometry coding category.
Which has the bigger context window?
GPT-5.3 Codex does, with 400K tokens against 262K.
How many benchmarks do Gemma 4 31B IT and GPT-5.3 Codex share?
4 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and GPT-5.3 Codex has 8.