GPT-5vsClaude Opus 4
Across 9 shared benchmarks, GPT-5 leads overall: GPT-5 wins 5, Claude Opus 4 wins 4, with 0 ties and an average score difference of +9.31.
GPT-5
OpenAI · 2025-08-07 · Foundation model
Claude Opus 4
Anthropic · 2025-05-23 · Reasoning model
GPT-55 wins(56%)(44%)4 winsClaude Opus 4
Benchmark scores
Grouped by capability, sorted by largest gap within each. 9 shared benchmarks.
Math and Reasoning
GPT-5 2/3| Benchmark | GPT-5 | Claude Opus 4 | Diff |
|---|---|---|---|
| IMO-ProofBench | 592 / 16Thinking (No Tools) | 2.9016 / 16Thinking (No Tools) | +56.10 |
| IMO-ProofBench Advanced | 2011 / 24Thinking (No Tools) | 2.9024 / 24Thinking (No Tools) | +17.10 |
| AIME2025 | 61.90135 / 215Normal (No Tools) | 75.50106 / 215Normal (No Tools) | -13.60 |
Agent Level Benchmark
GPT-5 1/1| Benchmark | GPT-5 | Claude Opus 4 | Diff |
|---|---|---|---|
| τ²-Bench | 8015 / 44Thinking (With Tools) | 72.5024 / 44Thinking (With Tools) | +7.50 |
Coding and Software Engineer
Claude Opus 4 1/1| Benchmark | GPT-5 | Claude Opus 4 | Diff |
|---|---|---|---|
| LiveCodeBench | 55.80149 / 250Normal (No Tools) | 56.60143 / 250Normal (No Tools) | -0.80 |
General Evaluation
Claude Opus 4 1/1| Benchmark | GPT-5 | Claude Opus 4 | Diff |
|---|---|---|---|
| GPQA Diamond | 77.80257 / 462Normal (No Tools) | 79.60241 / 462Normal (No Tools) | -1.80 |
General Knowledge
Claude Opus 4 1/1| Benchmark | GPT-5 | Claude Opus 4 | Diff |
|---|---|---|---|
| ARC-AGI-1 | 6142 / 147Normal (No Tools) | 35.67119 / 147Normal (No Tools) | -29.67 |
Instruction Following
GPT-5 1/1| Benchmark | GPT-5 | Claude Opus 4 | Diff |
|---|---|---|---|
| IF Bench | 45.60178 / 282Normal (No Tools) | 43.30191 / 282Normal (No Tools) | +2.30 |
Writing and Creative Capabilities
GPT-5 1/1| Benchmark | GPT-5 | Claude Opus 4 | Diff |
|---|---|---|---|
| Creative Writing | 1,62436 / 106Normal (No Tools) | 1,57741 / 106Normal (No Tools) | +46.70 |
Specs
| Field | GPT-5 | Claude Opus 4 |
|---|---|---|
| Publisher | OpenAI | Anthropic |
| Release date | 2025-08-07 | 2025-05-23 |
| Model type | Foundation model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 400K | 200K |
| Max output | 128K | 32K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | GPT-5 | Claude Opus 4 |
|---|---|---|
| Text input | $1.25 / 1M tokens | $15 / 1M tokens |
| Text output | $10 / 1M tokens | $75 / 1M tokens |
| Cache read | $0.125 / 1M tokens | $1.5 / 1M tokens |
| Cache write | $0 / 1M tokens | $18.75 / 1M tokens |
Summary
- GPT-5leads in:Math and Reasoning (2/3), Agent Level Benchmark (1/1), Instruction Following (1/1), Writing and Creative Capabilities (1/1)
- Claude Opus 4leads in:Coding and Software Engineer (1/1), General Evaluation (1/1), General Knowledge (1/1)
On average across the 9 shared benchmarks, GPT-5 scores 9.31 higher.
Largest single-benchmark gap: IMO-ProofBench — GPT-5 59 vs Claude Opus 4 2.90 (+56.10).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.