GPT-5vsGemini 2.5-Pro
Across 20 shared benchmarks, GPT-5 leads overall: GPT-5 wins 18, Gemini 2.5-Pro wins 2, with 0 ties and an average score difference of +23.48.
GPT-5
OpenAI · 2025-08-07 · Foundation model
Gemini 2.5-Pro
Google Deep Mind · 2025-06-05 · Reasoning model
GPT-518 wins(90%)(10%)2 winsGemini 2.5-Pro
Benchmark scores
Grouped by capability, sorted by largest gap within each. 20 shared benchmarks.
Math and Reasoning
GPT-5 6/7| 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 / 107 | 8844 / 107 | +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 |
| IMO-ProofBench | 592 / 16 | 55.203 / 16 | +3.80 |
| IMO-ProofBench Advanced | 202 / 8 | 17.604 / 8 | +2.40 |
General Knowledge
GPT-5 4/4| Benchmark | GPT-5 | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| ARC-AGI | 65.7033 / 68 | 3750 / 68 | +28.70 |
| HLE | 35.2073 / 172 | 21.60112 / 172 | +13.60 |
| ARC-AGI-2 | 9.9040 / 62 | 4.9047 / 62 | +5 |
| GPQA Diamond | 87.3040 / 187 | 86.4045 / 187 | +0.90 |
Agent Level Benchmark
GPT-5 2/2| Benchmark | GPT-5 | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| τ²-Bench - Telecom | 95.8013 / 35 | 5432 / 35 | +41.80 |
| Aider-Polyglot | 881 / 59Thinking High (No Tools) | 83.104 / 59Thinking (No Tools, 32K Budget) | +4.90 |
Coding and Software Engineer
GPT-5 2/2| Benchmark | GPT-5 | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| CodeClash | 1,3602 / 8Normal (With Tools) | 1,1256 / 8Normal (With Tools) | +235 |
| SWE-bench Verified | 72.8050 / 112 | 67.2072 / 112 | +5.60 |
AI Agent - Information Search
GPT-5 1/1| Benchmark | GPT-5 | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| BrowseComp | 54.9039 / 53 | 7.8052 / 53 | +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 |
Commonsense Reasoning
Gemini 2.5-Pro 1/1| Benchmark | GPT-5 | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| Simple Bench | 56.7020 / 63Thinking High (No Tools) | 62.4011 / 63Thinking (No Tools) | -5.70 |
Instruction Following
GPT-5 1/1| Benchmark | GPT-5 | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| IF Bench | 73.109 / 30 | 4929 / 30 | +24.10 |
Multimodal Understanding
GPT-5 1/1| Benchmark | GPT-5 | Gemini 2.5-Pro | Diff |
|---|---|---|---|
| MMMU | 84.206 / 29 | 8210 / 29 | +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 |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | GPT-5 | Gemini 2.5-Pro |
|---|---|---|
| Text input | $1.25 / 1M tokens | $1.25 / 1M tokens |
| Text output | $10 / 1M tokens | $10 / 1M tokens |
| Cache read | $0.125 / 1M tokens | Not public |
| Cache write | $0 / 1M tokens | Not public |
Summary
- GPT-5leads in:Math and Reasoning (6/7), General Knowledge (4/4), Agent Level Benchmark (2/2), Coding and Software Engineer (2/2), AI Agent - Information Search (1/1), AI Agent - Tool Usage (1/1), Instruction Following (1/1), Multimodal Understanding (1/1)
- Gemini 2.5-Proleads in:Commonsense Reasoning (1/1)
On average across the 20 shared benchmarks, GPT-5 scores 23.48 higher.
Largest single-benchmark gap: CodeClash — GPT-5 1,360 vs Gemini 2.5-Pro 1,125 (+235).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.