Model comparison
Gemini 2.0 Pro vs GPT-5.4 Pro
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 39.1 on the Noometry Index.
Last verified . 3 shared benchmarks.
GoogleSummary
- They share 3 benchmarks with published results for both. Gemini 2.0 Pro scores higher in 0 categories and GPT-5.4 Pro in 4 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where GPT-5.4 Pro leads 70.7 to 22.3.
- The biggest single-benchmark swing is GPQA Diamond: 65.7% for Gemini 2.0 Pro and 94.6% for GPT-5.4 Pro.
Side by side
| Gemini 2.0 Pro | GPT-5.4 Pro | |
|---|---|---|
| Provider | OpenAI | |
| Noometry Index | 39.1 | 58.9 |
| Released | 2025-02-05 | 2026-03-05 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.05M |
| Max output | — | 128K |
| Input $ / M tokens | — | $30 |
| Output $ / M tokens | — | $180 |
| Results tracked | 14 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.4 Pro leads
Gemini 2.0 Pro: 37.8 (#187), GPT-5.4 Pro: 43.2 (#90)
| Benchmark | Gemini 2.0 Pro | GPT-5.4 Pro |
|---|---|---|
| Aider Polyglot | 35.6% | — |
| WeirdML | — | 57.4% |
| LiveBench Coding | 63.5% | — |
Reasoning GPT-5.4 Pro leads
Gemini 2.0 Pro: 22.3 (#198), GPT-5.4 Pro: 70.7 (#13)
| Benchmark | Gemini 2.0 Pro | GPT-5.4 Pro |
|---|---|---|
| EnigmaEval | 0.7% | 23.8% |
| Epoch Capabilities Index | 135.06 | 158.93 |
| ARC-AGI-2 | — | 83.3% |
| SimpleBench | — | 74.1% |
| ARC-AGI-1 | — | 94.5% |
| CritPt | — | 30% |
| Chess Puzzles | — | 58.6% |
| LiveBench Reasoning | 60.1% | — |
| LiveBench Data Analysis | 68% | — |
| LiveBench | 65.1% | — |
Math GPT-5.4 Pro leads
Gemini 2.0 Pro: 39.7 (#100), GPT-5.4 Pro: 72.4 (#22)
| Benchmark | Gemini 2.0 Pro | GPT-5.4 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 82.5% |
| FrontierMath Tier 4 | — | 58.5% |
| LiveBench Math | 71% | — |
| MATH Level 5 | 83.5% | — |
| FrontierMath (Feb 2025 set) | — | 50% |
| FrontierMath Tier 4 (v1) | — | 37.5% |
Knowledge GPT-5.4 Pro leads
Gemini 2.0 Pro: 36.5 (#167), GPT-5.4 Pro: 68.3 (#7)
| Benchmark | Gemini 2.0 Pro | GPT-5.4 Pro |
|---|---|---|
| GPQA Diamond | 65.7% | 94.6% |
| Humanity's Last Exam | — | 44.3% |
| SimpleQA Verified | — | 46.3% |
| Confabulations | 18.4% | — |
| Vectara Hallucination Rate | — | 8.3% |
Instruction Following Not comparable
Gemini 2.0 Pro: 75.5 (#59), GPT-5.4 Pro: —
| Benchmark | Gemini 2.0 Pro | GPT-5.4 Pro |
|---|---|---|
| LiveBench Instruction Following | 83.4% | — |
Long Context Not comparable
Gemini 2.0 Pro: 29.2 (#292), GPT-5.4 Pro: —
| Benchmark | Gemini 2.0 Pro | GPT-5.4 Pro |
|---|---|---|
| Fiction.LiveBench | 41.7% | — |
Writing & Preference Not comparable
Gemini 2.0 Pro: 52.7 (#165), GPT-5.4 Pro: —
| Benchmark | Gemini 2.0 Pro | GPT-5.4 Pro |
|---|---|---|
| LiveBench Language | 44.9% | — |
Frequently asked questions
Is Gemini 2.0 Pro better than GPT-5.4 Pro?
GPT-5.4 Pro is the stronger model overall, scoring 58.9 to 39.1 on the Noometry Index.
Is Gemini 2.0 Pro or GPT-5.4 Pro better for coding?
GPT-5.4 Pro scores higher on coding benchmarks: 43.2 versus 37.8 in the Noometry coding category.
How many benchmarks do Gemini 2.0 Pro and GPT-5.4 Pro share?
3 benchmarks have published results for both models. Gemini 2.0 Pro has 14 scored results on Noometry and GPT-5.4 Pro has 16.