GPT-5vsGemini 2.5-Pro
Across 19 shared benchmarks, GPT-5 leads overall: GPT-5 wins 17, Gemini 2.5-Pro wins 2, with 0 ties and an average score difference of +12.47.
GPT-5
OpenAI · 2025-08-07 · Foundation model
Gemini 2.5-Pro
Google Deep Mind · 2025-06-05 · Reasoning model
GPT-517 wins(89%)(11%)2 winsGemini 2.5-Pro
Benchmark scores
Grouped by capability, sorted by largest gap within each. 19 shared benchmarks.
Math and Reasoning
GPT-5 6/8| Benchmark | GPT-5 | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| IMO 2025 | 292 / 9 | 15.203 / 9 | +13.80 |
| FrontierMath | 24.8015 / 60 | 1123 / 60 | +13.80 |
| AIME2025 | 99.609 / 106 | 8843 / 106 | +11.60 |
| FrontierMath - Tier 4 | 12.5029 / 80Thinking High (No Tools) | 2.1056 / 80Normal (No Tools) | +10.40 |
| IMO 2024 | 114 / 10 | 192 / 10 | -8 |
| Simple Bench | 56.708 / 27 | 62.402 / 27 | -5.70 |
| IMO-ProofBench | 592 / 16 | 55.203 / 16 | +3.80 |
| IMO-ProofBench Advanced | 202 / 8 | 17.604 / 8 | +2.40 |
General Knowledge
GPT-5 5/5| Benchmark | GPT-5 | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| ARC-AGI | 65.7030 / 65 | 3747 / 65 | +28.70 |
| HLE | 35.2060 / 157 | 21.6097 / 157 | +13.60 |
| LiveBench | 79.331 / 52 | 71.9213 / 52 | +7.41 |
| ARC-AGI-2 | 9.9037 / 59 | 4.9044 / 59 | +5 |
| GPQA Diamond | 87.3037 / 178 | 86.4041 / 178 | +0.90 |
Agent Level Benchmark
GPT-5 1/1| Benchmark | GPT-5 | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| τ²-Bench - Telecom | 95.8013 / 35 | 5432 / 35 | +41.80 |
AI Agent - Information Search
GPT-5 1/1| Benchmark | GPT-5 | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| BrowseComp | 54.9032 / 45 | 7.8044 / 45 | +47.10 |
AI Agent - Tool Usage
GPT-5 1/1| Benchmark | GPT-5 | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| Terminal-Bench | 43.808 / 35 | 25.3028 / 35 | +18.50 |
Coding and Software Engineer
GPT-5 1/1| Benchmark | GPT-5 | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| SWE-bench Verified | 72.8046 / 108 | 67.2068 / 108 | +5.60 |
Instruction Following
GPT-5 1/1| Benchmark | GPT-5 | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| IF Bench | 73.108 / 29 | 4928 / 29 | +24.10 |
Multimodal Understanding
GPT-5 1/1| Benchmark | GPT-5 | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| MMMU | 84.205 / 28 | 829 / 28 | +2.20 |
Specs
| Field | GPT-5 | Gemini 2.5-Pro |
|---|---|---|
| Publisher | OpenAI | Google Deep Mind |
| Release date | 2025-08-07 | 2025-06-05 |
| Model type | Foundation model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 400K | 1000K |
| Max output | 128K | 64K |
Summary
- GPT-5leads in:Math and Reasoning (6/8), General Knowledge (5/5), Agent Level Benchmark (1/1), AI Agent - Information Search (1/1), AI Agent - Tool Usage (1/1), Coding and Software Engineer (1/1), Instruction Following (1/1), Multimodal Understanding (1/1)
On average across the 19 shared benchmarks, GPT-5 scores 12.47 higher.
Largest single-benchmark gap: BrowseComp — GPT-5 54.90 vs Gemini 2.5-Pro 7.80 (+47.10).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.