Model comparison
Gemma 4 31B IT vs GPT-5.4 Pro
GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 443× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Last verified . 7 shared benchmarks.
GoogleSummary
- They share 7 benchmarks with published results for both. Gemma 4 31B IT scores higher in 0 categories and GPT-5.4 Pro in 4 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 Pro leads 71.0 to 26.4.
- The biggest single-benchmark swing is Chess Puzzles: 5% for Gemma 4 31B IT and 58.6% for GPT-5.4 Pro.
- Gemma 4 31B IT is cheaper at $0.09 / $0.34 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
- GPT-5.4 Pro accepts more context: 1.05M tokens versus 262K.
- Gemma 4 31B IT has downloadable open weights; the other is API-only.
Side by side
| Gemma 4 31B IT | GPT-5.4 Pro | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 43.2 | 58.8 |
| Released | 2026-04-02 | 2026-03-05 |
| Weights | Open | Proprietary |
| Context window | 262K | 1.05M |
| Max output | 33K | 128K |
| Input $ / M tokens | $0.09 | $30 |
| Output $ / M tokens | $0.34 | $180 |
| Results tracked | 35 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 4 31B IT: 41.9 (#98), GPT-5.4 Pro: 42.6 (#89)
| Benchmark | Gemma 4 31B IT | GPT-5.4 Pro |
|---|---|---|
| WeirdML | 52.3% | 57.4% |
| LMArena WebDev | 1364 | — |
| SciCode | 43.4% | — |
| LMArena Coding | 1459 | — |
| ALE-Bench | 925.5 | — |
Reasoning GPT-5.4 Pro leads
Gemma 4 31B IT: 26.4 (#119), GPT-5.4 Pro: 71.0 (#10)
| Benchmark | Gemma 4 31B IT | GPT-5.4 Pro |
|---|---|---|
| CritPt | 1.4% | 30% |
| Chess Puzzles | 5% | 58.6% |
| Epoch Capabilities Index | 142.74 | 159.12 |
| ARC-AGI-2 | — | 83.3% |
| SimpleBench | — | 74.1% |
| Kagi LLM Benchmark | 63.5% | — |
| NYT Connections (extended) | 70.6% | — |
| ARC-AGI-1 | — | 94.5% |
| EnigmaEval | — | 23.8% |
| Thematic Generalization | 53% | — |
| LMArena Hard Prompts | 1448 | — |
| DTBench | 82.7% | — |
| LMCA | 39.3% | — |
| Surface Evolver Bench | 30.6% | — |
Math GPT-5.4 Pro leads
Gemma 4 31B IT: 41.3 (#72), GPT-5.4 Pro: 72.0 (#17)
| Benchmark | Gemma 4 31B IT | GPT-5.4 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 82.5% |
| FrontierMath Tier 4 | — | 58.5% |
| OTIS Mock AIME 2024-2025 | 73.3% | — |
| LMArena Math | 1464 | — |
| FrontierMath (Feb 2025 set) | — | 50% |
| FrontierMath Tier 4 (v1) | — | 37.5% |
Knowledge GPT-5.4 Pro leads
Gemma 4 31B IT: 37.9 (#141), GPT-5.4 Pro: 68.3 (#6)
| Benchmark | Gemma 4 31B IT | GPT-5.4 Pro |
|---|---|---|
| GPQA Diamond | 75.8% | 94.6% |
| SimpleQA Verified | 10.4% | 46.3% |
| Vectara Hallucination Rate | 7.4% | 8.3% |
| Humanity's Last Exam | — | 44.3% |
| LMArena Expert | 1465 | — |
Multimodal Not comparable
Gemma 4 31B IT: 41.0 (#32), GPT-5.4 Pro: —
| Benchmark | Gemma 4 31B IT | GPT-5.4 Pro |
|---|---|---|
| LMArena Vision | 1278 | — |
| LMArena Document | 1425 | — |
Multilingual Not comparable
Gemma 4 31B IT: 54.0 (#52), GPT-5.4 Pro: —
| Benchmark | Gemma 4 31B IT | GPT-5.4 Pro |
|---|---|---|
| LMArena Non-English | 1431 | — |
| LMArena Chinese | 1478 | — |
| LMArena French | 1436 | — |
| LMArena Russian | 1462 | — |
| LMArena Spanish | 1443 | — |
Instruction Following Not comparable
Gemma 4 31B IT: 75.6 (#58), GPT-5.4 Pro: —
| Benchmark | Gemma 4 31B IT | GPT-5.4 Pro |
|---|---|---|
| LMArena Instruction Following | 1433 | — |
Long Context Not comparable
Gemma 4 31B IT: 44.2 (#67), GPT-5.4 Pro: —
| Benchmark | Gemma 4 31B IT | GPT-5.4 Pro |
|---|---|---|
| LMArena Longer Query | 1446 | — |
Writing & Preference Not comparable
Gemma 4 31B IT: 60.7 (#92), GPT-5.4 Pro: —
| Benchmark | Gemma 4 31B IT | GPT-5.4 Pro |
|---|---|---|
| LMArena Text | 1443 | — |
| LMArena Creative Writing | 1416 | — |
| EQ-Bench Creative Writing | 1368 | — |
| EQ-Bench 4 | 1120 | — |
| LMArena Multi-Turn | 1452 | — |
Frequently asked questions
Is Gemma 4 31B IT better than GPT-5.4 Pro?
GPT-5.4 Pro is the stronger model overall, scoring 58.8 to 43.2 on the Noometry Index. Gemma 4 31B IT costs 443× less per token, which makes it the better buy when GPT-5.4 Pro's lead doesn't matter for your workload.
Which is cheaper, Gemma 4 31B IT or GPT-5.4 Pro?
Gemma 4 31B IT is cheaper. It lists at $0.09 per million input tokens and $0.34 per million output tokens; GPT-5.4 Pro lists at $30 and $180.
Is Gemma 4 31B IT or GPT-5.4 Pro better for coding?
They score almost the same on coding (41.9 vs 42.6); test both on your own repository before choosing.
Which has the bigger context window?
GPT-5.4 Pro does, with 1.05M tokens against 262K.
How many benchmarks do Gemma 4 31B IT and GPT-5.4 Pro share?
7 benchmarks have published results for both models. Gemma 4 31B IT has 35 scored results on Noometry and GPT-5.4 Pro has 16.