GPT-5.4 ProvsClaude Opus 4.6
Across 8 shared benchmarks, GPT-5.4 Pro leads overall: GPT-5.4 Pro wins 7, Claude Opus 4.6 wins 1, with 0 ties and an average score difference of -183.31.
GPT-5.4 Pro
OpenAI · 2026-03-05 · Multimodal model
Claude Opus 4.6
Anthropic · 2026-02-05 · Reasoning model
GPT-5.4 Pro7 wins(88%)(13%)1 winClaude Opus 4.6
Benchmark scores
Grouped by capability, sorted by largest gap within each. 8 shared benchmarks.
General Knowledge
GPT-5.4 Pro 4/4| Benchmark | GPT-5.4 Pro | Claude Opus 4.6 | Diff |
|---|---|---|---|
| ARC-AGI-2 | 83.306 / 59Thinking High (No Tools) | 66.3015 / 59Extended (no tools) | +17 |
| HLE | 58.703 / 157Thinking High (With Tools) | 5311 / 157Extended (with tools, internet) | +5.70 |
| GPQA Diamond | 94.402 / 178Thinking High (No Tools) | 91.3114 / 178Extended (no tools) | +3.09 |
| ARC-AGI | 94.505 / 65Thinking High (No Tools) | 9211 / 65Extended (no tools) | +2.50 |
Math and Reasoning
GPT-5.4 Pro 2/2| Benchmark | GPT-5.4 Pro | Claude Opus 4.6 | Diff |
|---|---|---|---|
| FrontierMath - Tier 4 | 37.505 / 80Normal (With Tools + Internet) | 22.9012 / 80最高（无工具） | +14.60 |
| FrontierMath | 503 / 60Thinking High (No Tools) | 40.707 / 60最高（无工具） | +9.30 |
AI Agent - Information Search
GPT-5.4 Pro 1/1| Benchmark | GPT-5.4 Pro | Claude Opus 4.6 | Diff |
|---|---|---|---|
| BrowseComp | 89.302 / 45Thinking High (With Tools) | 847 / 45Thinking (With Tools + Internet) | +5.30 |
Productivity Knowledge
Claude Opus 4.6 1/1| Benchmark | GPT-5.4 Pro | Claude Opus 4.6 | Diff |
|---|---|---|---|
| GDPval-AA | 828 / 21Thinking High (With Tools) | 1,6063 / 21Extended (with tools, internet) | -1,524 |
Specs
| Field | GPT-5.4 Pro | Claude Opus 4.6 |
|---|---|---|
| Publisher | OpenAI | Anthropic |
| Release date | 2026-03-05 | 2026-02-05 |
| Model type | Multimodal model | Reasoning model |
| Architecture | Dense | Dense |
| Parameters | Not available | Not available |
| Context length | 1M | 1000K |
| Max output | 125K | 64K |
API pricing
Prices use DataLearner records when available; missing fields are not inferred.
| Item | GPT-5.4 Pro | Claude Opus 4.6 |
|---|---|---|
| Text input | $30 / 1M tokens | $0.5 / 1M tokens |
| Text output | $180 / 1M tokens | $25 / 1M tokens |
| Cache read | Not public | $0.5 / 1M tokens |
| Cache write | Not public | $10 / 1M tokens |
Summary
- GPT-5.4 Proleads in:General Knowledge (4/4), Math and Reasoning (2/2), AI Agent - Information Search (1/1)
- Claude Opus 4.6leads in:Productivity Knowledge (1/1)
On average across the 8 shared benchmarks, Claude Opus 4.6 scores 183.31 higher.
Largest single-benchmark gap: GDPval-AA — GPT-5.4 Pro 82 vs Claude Opus 4.6 1,606 (-1,524).
Page generated from structured model, pricing and benchmark records. No real-time LLM is used to write the prose.