Compare / head-to-head
Claude Opus 4.5vs
GPT-5.5
GPT-5.5 leads 23 of 26 shared benchmarks. Claude Opus 4.5 is 1.2x cheaper per token. GPT-5.5 has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
3 – 23
GPT-5.5 leads
Cheaper per token
Claude Opus 4.5
1.2x cheaper, input + output
Larger context
GPT-5.5
1M tokens
Providers
2 providers
Anthropic · OpenAI
Claude Opus 4.5
Anthropic · released 2025-11-24
textvision
Quality
Benchmark matrix
26 shared · 12 only Claude Opus 4.5 · 18 only GPT-5.5| Benchmark | Claude Opus 4.5 | GPT-5.5 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 26 | ||||
| GPQA Diamond | 87% ↗ | 90.7% ↗epoch run | -3.7 pt | GPT-5.5 |
| LMArena Elo | 1473.6 ↗ | 1465.6 ↗ | +8 | Claude Opus 4.5 |
| ARC-AGI-2 (Verified) | 37.6% ↗ | 85% ↗ | -47.4 pt | GPT-5.5 |
| Chess Puzzles (Epoch AI run) | 12% ↗epoch run | 26% ↗epoch run | -14 pt | GPT-5.5 |
| EBR-bench (Epoch AI run) | 14.3% ↗epoch run | 34.3% ↗epoch run | -20 pt | GPT-5.5 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 4.9% ↗epoch run | 72.5% ↗epoch run | -67.6 pt | GPT-5.5 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 34.4% ↗epoch run | 85.3% ↗epoch run | -50.9 pt | GPT-5.5 |
| Furniture Assembly (Epoch AI run) | 28.3% ↗epoch run | 44.2% ↗epoch run | -15.9 pt | GPT-5.5 |
| GSO Opt@1 (GSO) | 24.5% ↗ | 37.3% ↗ | -12.8 pt | GPT-5.5 |
| LiveBench Agentic Coding (LiveBench) | 39.7% ↗ | 54% ↗ | -14.3 pt | GPT-5.5 |
| LiveBench Coding (LiveBench) | 79.7% ↗ | 82.1% ↗ | -2.4 pt | GPT-5.5 |
| LiveBench Data Analysis (LiveBench) | 74.4% ↗ | 81.6% ↗ | -7.2 pt | GPT-5.5 |
| LiveBench Instruction Following (LiveBench) | 62.5% ↗ | 70.7% ↗ | -8.2 pt | GPT-5.5 |
| LiveBench Language (LiveBench) | 81.3% ↗ | 87.4% ↗ | -6.1 pt | GPT-5.5 |
| LiveBench Mathematics (LiveBench) | 90.4% ↗ | 95.9% ↗ | -5.5 pt | GPT-5.5 |
| LiveBench Reasoning (LiveBench) | 80.1% ↗ | 89.7% ↗ | -9.6 pt | GPT-5.5 |
| MCP Atlas | 62.3% ↗ | 75.3% ↗ | -13 pt | GPT-5.5 |
| Mystery Game Puzzles (Epoch AI run) | 22% ↗epoch run | 56% ↗epoch run | -34 pt | GPT-5.5 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 86.1% ↗epoch run | 84.4% ↗epoch run | +1.7 pt | Claude Opus 4.5 |
| SAGE (Vals AI) | 52.1% ↗ | 51.5% ↗ | +0.6 pt | Claude Opus 4.5 |
| SimpleBench (SimpleBench) | 62% ↗ | 69% ↗ | -7 pt | GPT-5.5 |
| SimpleQA Verified | 45.7% ↗epoch run | 63% ↗epoch run | -17.3 pt | GPT-5.5 |
| tau2-bench Banking Knowledge (Sierra) | 24.7% ↗ | 44.6% ↗ | -19.9 pt | GPT-5.5 |
| Terminal-Bench 2.0 | 59.3% ↗ | 82.7% ↗ | -23.4 pt | GPT-5.5 |
| Vending-Bench 2 (Andon Labs) | 4967.06 ↗ | 7523.84 ↗ | -2556.8 | GPT-5.5 |
| WeirdML (Håvard Tveit Ihle) | 63.7% ↗ | 84.9% ↗ | -21.2 pt | GPT-5.5 |
| Only Claude Opus 4.5 reports · 12 | ||||
| SWE-bench Verified | 80.9% ↗ | not reported | — | — |
| BALROG (BALROG) | 43.5% ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1493.3 ↗ | not reported | — | — |
| MMMLU | 90.8% ↗ | not reported | — | — |
| MMMU (validation) | 80.7% ↗ | not reported | — | — |
| OSWorld | 66.3% ↗ | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 76.7% ↗epoch run | not reported | — | — |
| tau2-bench Airline (Sierra) | 84% ↗ | not reported | — | — |
| tau2-bench Retail (Sierra) | 79.6% ↗ | not reported | — | — |
| tau2-bench Telecom (Sierra) | 92.3% ↗ | not reported | — | — |
| τ2-bench (Retail) | 88.9% ↗ | not reported | — | — |
| τ2-bench (Telecom) | 98.2% ↗ | not reported | — | — |
| Only GPT-5.5 reports · 18 | ||||
| AIME 2026 | not reported | 100% ↗matharena ⚠ | — | — |
| APEX-Agents (Mercor) | not reported | 55.1% ↗ | — | — |
| ARC-AGI-1 (Verified) | not reported | 95% ↗ | — | — |
| BrowseComp | not reported | 84.4% ↗ | — | — |
| DeepSWE v1.1 (Datacurve) | not reported | 67% ↗ | — | — |
| FrontierMath Tier 1-3 | not reported | 51.7% ↗ | — | — |
| FrontierMath Tier 4 | not reported | 35.4% ↗ | — | — |
| GDPval (wins or ties) | not reported | 84.9% ↗ | — | — |
| LMArena Agent (LMArena) | not reported | 0.0415 ↗ | — | — |
| LMArena Vision (LMArena) | not reported | 1286.5 ↗ | — | — |
| MirrorCode (Epoch AI run) | not reported | 10% ↗epoch run | — | — |
| MMMU-Pro (no tools) | not reported | 81.2% ↗ | — | — |
| MMMU-Pro (with tools) | not reported | 83.2% ↗ | — | — |
| OSWorld-Verified | not reported | 78.7% ↗ | — | — |
| SWE-Bench Pro | not reported | 58.6% ↗ | — | — |
| Tau2-bench Telecom | not reported | 98% ↗ | — | — |
| Toolathlon | not reported | 55.6% ↗ | — | — |
| Toolathlon-Verified (HKUST) | not reported | 73.5% ↗ | — | — |
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 4.5 minus GPT-5.5 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 4.5 | GPT-5.5 | Edge |
|---|---|---|---|
| Context window | 200K tokens | 1M tokens | GPT-5.5 |
| Max output | 64K tokens | 128K tokens | GPT-5.5 |
| Input price / 1M | $5 ↗ | $5 ↗ | Tie |
| Output price / 1M | $25 ↗ | $30 ↗ | Claude Opus 4.5 |
| Cached input / 1M | $0.5 ↗ | $0.5 ↗ | Tie |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $30 | $35 | Claude Opus 4.5 |
| Modalities | text · vision | text · vision | Tie |
| Released | 2025-11-24 | 2026-04-23 | — |
| Cited benchmark scores | 39 | 50 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Opus 4.5 vs …
Models sharing the most benchmarksMore matchups
GPT-5.5 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Opus 4.5 and GPT-5.5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.