Gemini 2.0 Pro ExperimentalvsGPT-4o(2024-11-20)
Across 5 shared benchmarks, Gemini 2.0 Pro Experimental leads overall: Gemini 2.0 Pro Experimental wins 5, GPT-4o(2024-11-20) wins 0, with 0 ties and an average score difference of +9.64.
Gemini 2.0 Pro Experimental
DeepMind · 2025-02-05 · Chat model
GPT-4o(2024-11-20)
OpenAI · 2024-11-20 · Chat model
Gemini 2.0 Pro Experimental5 wins(100%)(0%)0 winsGPT-4o(2024-11-20)
Benchmark scores
Grouped by capability, sorted by largest gap within each. 5 shared benchmarks.
General Knowledge
Gemini 2.0 Pro Experimental 2/2| Benchmark | Gemini 2.0 Pro Experimental | GPT-4o(2024-11-20) | Diff |
|---|---|---|---|
| MMLU Pro | 79.1065 / 132 | 77.9075 / 132 | +1.20 |
| MMLU | 86.5028 / 66 | 85.7037 / 66 | +0.80 |
Agent Level Benchmark
Gemini 2.0 Pro Experimental 1/1| Benchmark | Gemini 2.0 Pro Experimental | GPT-4o(2024-11-20) | Diff |
|---|---|---|---|
| Aider-Polyglot | 35.6041 / 59Normal (No Tools) | 18.2050 / 59Normal (No Tools) | +17.40 |
Common Sense
Gemini 2.0 Pro Experimental 1/1| Benchmark | Gemini 2.0 Pro Experimental | GPT-4o(2024-11-20) | Diff |
|---|---|---|---|
| SimpleQA | 44.3016 / 47 | 38.8021 / 47 | +5.50 |
Math and Reasoning
Gemini 2.0 Pro Experimental 1/1| Benchmark | Gemini 2.0 Pro Experimental | GPT-4o(2024-11-20) | Diff |
|---|---|---|---|
| MATH | 91.804 / 42 | 68.5024 / 42 | +23.30 |
Specs
| Field | Gemini 2.0 Pro Experimental | GPT-4o(2024-11-20) |
|---|---|---|
| Publisher | DeepMind | OpenAI |
| Release date | 2025-02-05 | 2024-11-20 |
| Model type | Chat model | Chat model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 2000K | 128K |
| Max output | 8K | Not available |
Summary
- Gemini 2.0 Pro Experimentalleads in:General Knowledge (2/2), Agent Level Benchmark (1/1), Common Sense (1/1), Math and Reasoning (1/1)
On average across the 5 shared benchmarks, Gemini 2.0 Pro Experimental scores 9.64 higher.
Largest single-benchmark gap: MATH — Gemini 2.0 Pro Experimental 91.80 vs GPT-4o(2024-11-20) 68.50 (+23.30).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.