Compare / head-to-head
Claude Opus 4.6vsGPT-5.4
GPT-5.4 leads 10 of 14 shared benchmarks. GPT-5.4 is 1.7x cheaper per token. GPT-5.4 has the larger context window (1.1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
4 – 10
GPT-5.4 leads
Cheaper per token
GPT-5.4
1.7x cheaper, input + output
Larger context
GPT-5.4
1.1M tokens
Provider uptime (30d)
100% · 95.5679%
Anthropic · OpenAI
Claude Opus 4.6
Anthropic · released 2026-02-05
textvision
Quality
Benchmark matrix
14 shared · 4 only Claude Opus 4.6 · 6 only GPT-5.4| Benchmark | Claude Opus 4.6 | GPT-5.4 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 14 | ||||
| GPQA Diamond | 91.3% ↗ | 92.8% ↗ | -1.5 pt | GPT-5.4 |
| AIME 2026 | 96.7% ↗matharena | 99.2% ↗matharena ⚠ | -2.5 pt | GPT-5.4 |
| LMArena Elo | 1497.5 ↗ | 1452.6 ↗ | +44.9 | Claude Opus 4.6 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 26.8% ↗epoch | 49% ↗epoch | -22.2 pt | GPT-5.4 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 66% ↗epoch | 78.6% ↗epoch | -12.6 pt | GPT-5.4 |
| MCP Atlas | 59.5% ↗ | 67.2% ↗ | -7.7 pt | GPT-5.4 |
| MMMU-Pro (no tools) | 73.9% ↗ | 81.2% ↗ | -7.3 pt | GPT-5.4 |
| MMMU-Pro (with tools) | 77.3% ↗ | 82.1% ↗ | -4.8 pt | GPT-5.4 |
| OSWorld-Verified | 72.7% ↗ | 75% ↗ | -2.3 pt | GPT-5.4 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 94.4% ↗epoch | 97.8% ↗epoch | -3.4 pt | GPT-5.4 |
| SimpleQA Verified | 47% ↗epoch | 45.1% ↗epoch | +1.9 pt | Claude Opus 4.6 |
| SWE-bench Verified (Epoch AI run) | 78.7% ↗epoch | 76.9% ↗epoch | +1.8 pt | Claude Opus 4.6 |
| Tau2-bench Telecom | 99.3% ↗ | 98.9% ↗ | +0.4 pt | Claude Opus 4.6 |
| Terminal-Bench 2.0 | 65.4% ↗ | 75.1% ↗ | -9.7 pt | GPT-5.4 |
| Only Claude Opus 4.6 reports · 4 | ||||
| SWE-bench Verified | 80.8% ↗ | not reported | — | — |
| ARC-AGI-2 (Verified) | 68.8% ↗ | not reported | — | — |
| MMMLU | 91.1% ↗ | not reported | — | — |
| Tau2-bench Retail | 91.9% ↗ | not reported | — | — |
| Only GPT-5.4 reports · 6 | ||||
| Humanity's Last Exam (no tools) | not reported | 39.8% ↗ | — | — |
| BrowseComp | not reported | 82.7% ↗ | — | — |
| GDPval (wins or ties) | not reported | 83% ↗ | — | — |
| Humanity's Last Exam (with tools) | not reported | 52.1% ↗ | — | — |
| SWE-Bench Pro | not reported | 57.7% ↗ | — | — |
| Toolathlon | not reported | 54.6% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Claude Opus 4.6 minus GPT-5.4 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Claude Opus 4.6 | GPT-5.4 | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1.1M tokens | GPT-5.4 |
| Max output | 128K tokens | 128K tokens | Tie |
| Input price / 1M | $5 ↗ | $2.5 ↗ | GPT-5.4 |
| Output price / 1M | $25 ↗ | $15 ↗ | GPT-5.4 |
| Cached input / 1M | $0.5 ↗ | $0.25 ↗ | GPT-5.4 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $30 | $17.5 | GPT-5.4 |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-02-05 | 2026-03-05 | — |
| Cited benchmark scores | 19 | 21 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Claude Opus 4.6 vs …
Models sharing the most benchmarksMore matchups
GPT-5.4 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Opus 4.6 and GPT-5.4 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.