Compare / head-to-head
Claude Opus 5.5vs
GPT-5.2-Codex
Claude Opus 5.5 leads 8 of 8 shared benchmarks. GPT-5.2-Codex is 1.5x cheaper per token. Claude Opus 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
8 – 0
Claude Opus 5.5 leads
Cheaper per token
GPT-5.2-Codex
1.5x cheaper, input + output
Larger context
Claude Opus 5.5
1M tokens
Providers
2 providers
Anthropic · OpenAI
Claude Opus 5.5
Anthropic · released 2026-09-22
textvision
GPT-5.2-Codex
OpenAI · released 2025-12-18
textvision
Quality
Benchmark matrix
8 shared · 26 only Claude Opus 5.5 · 5 only GPT-5.2-Codex| Benchmark | Claude Opus 5.5 | GPT-5.2-Codex | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 8 | ||||
| LiveBench Agentic Coding (LiveBench) | 71.7% ↗ | 49.4% ↗ | +22.3 pt | Claude Opus 5.5 |
| LiveBench Coding (LiveBench) | 89.3% ↗ | 83.6% ↗ | +5.7 pt | Claude Opus 5.5 |
| LiveBench Data Analysis (LiveBench) | 80.3% ↗ | 78.2% ↗ | +2.1 pt | Claude Opus 5.5 |
| LiveBench Instruction Following (LiveBench) | 67% ↗ | 66.4% ↗ | +0.6 pt | Claude Opus 5.5 |
| LiveBench Language (LiveBench) | 86.3% ↗ | 73.7% ↗ | +12.6 pt | Claude Opus 5.5 |
| LiveBench Mathematics (LiveBench) | 97.1% ↗ | 88.8% ↗ | +8.3 pt | Claude Opus 5.5 |
| LiveBench Reasoning (LiveBench) | 92.2% ↗ | 77.7% ↗ | +14.5 pt | Claude Opus 5.5 |
| LMArena WebDev (LMArena) | 1815.4 ↗ | 1338.9 ↗ | +476.5 | Claude Opus 5.5 |
| Only Claude Opus 5.5 reports · 26 | ||||
| GPQA Diamond | 90.6% ↗epoch run | not reported | — | — |
| LMArena Elo | 1503.7 ↗ | not reported | — | — |
| APEX-Agents (Mercor) | 73.5% ↗ | not reported | — | — |
| AutomationBench 1.0.6 | 40% ↗ | not reported | — | — |
| Chartography (with tools) | 89% ↗ | not reported | — | — |
| CursorBench 4.0 | 57.8% ↗ | not reported | — | — |
| EBR-bench (Epoch AI run) | 71.4% ↗epoch run | not reported | — | — |
| FrontierCode v1.1 (Main) | 54.4% ↗ | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 95% ↗epoch run | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 91.2% ↗epoch run | not reported | — | — |
| FrontierSWE V2 (Proximal Labs) | 62.3% ↗ | not reported | — | — |
| Furniture Assembly (Epoch AI run) | 83.3% ↗epoch run | not reported | — | — |
| GDPval-AA v2.1 | 1846 ↗ | not reported | — | — |
| Humanity's Last Exam (with tools) | 67.7% ↗ | not reported | — | — |
| LMArena Agent (LMArena) | 0.1382 ↗ | not reported | — | — |
| MirrorCode (Epoch AI run) | 77.4% ↗epoch run | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 71% ↗epoch run | not reported | — | — |
| OSWorld 2.0 (partial) | 81.8% ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 100% ↗epoch run | not reported | — | — |
| SAGE (Vals AI) | 45.8% ↗ | not reported | — | — |
| SimpleBench (SimpleBench) | 88.4% ↗ | not reported | — | — |
| SimpleQA Verified | 72.2% ↗epoch run | not reported | — | — |
| Terminal-Bench 4.0 | 66.4% ↗ | not reported | — | — |
| Terminal-Bench 4.0 (Vals AI) | 65.2% ↗ | not reported | — | — |
| Terminal-Bench Science 0.1 | 58.7% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 9235.25 ↗ | not reported | — | — |
| Only GPT-5.2-Codex reports · 5 | ||||
| Cybersecurity Capture The Flag Challenges | not reported | 67.4% ↗ | — | — |
| OSWorld-Verified | not reported | 38.2% ↗ | — | — |
| SWE-Bench Pro | not reported | 56.4% ↗ | — | — |
| SWE-Lancer IC Diamond | not reported | 76% ↗ | — | — |
| Terminal-Bench 2.0 | not reported | 64% ↗ | — | — |
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 5.5 minus GPT-5.2-Codex 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 5.5 | GPT-5.2-Codex | Edge |
|---|---|---|---|
| Context window | 1M tokens | 400K tokens | Claude Opus 5.5 |
| Max output | 128K tokens | 128K tokens | Tie |
| Input price / 1M | $4 ↗ | $1.75 ↗ | GPT-5.2-Codex |
| Output price / 1M | $20 ↗ | $14 ↗ | GPT-5.2-Codex |
| Cached input / 1M | $0.2 ↗ | $0.175 ↗ | GPT-5.2-Codex |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $24 | $15.75 | GPT-5.2-Codex |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-09-22 | 2025-12-18 | — |
| Cited benchmark scores | 34 | 13 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Opus 5.5 vs …
Models sharing the most benchmarksMore matchups
GPT-5.2-Codex vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Opus 5.5 and GPT-5.2-Codex on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.