Compare / head-to-head
Claude Opus 4.6vs
GPT-5.2-Codex
Claude Opus 4.6 leads 6 of 10 shared benchmarks. GPT-5.2-Codex is 1.9x cheaper per token. Claude Opus 4.6 has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
6 – 4
Claude Opus 4.6 leads
Cheaper per token
GPT-5.2-Codex
1.9x cheaper, input + output
Larger context
Claude Opus 4.6
1M tokens
Providers
2 providers
Anthropic · OpenAI
Claude Opus 4.6
Anthropic · released 2026-02-05
textvision
GPT-5.2-Codex
OpenAI · released 2025-12-18
textvision
Quality
Benchmark matrix
10 shared · 28 only Claude Opus 4.6 · 3 only GPT-5.2-Codex| Benchmark | Claude Opus 4.6 | GPT-5.2-Codex | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 10 | ||||
| LiveBench Agentic Coding (LiveBench) | 49% ↗ | 49.4% ↗ | -0.4 pt | GPT-5.2-Codex |
| LiveBench Coding (LiveBench) | 78.2% ↗ | 83.6% ↗ | -5.4 pt | GPT-5.2-Codex |
| LiveBench Data Analysis (LiveBench) | 69.9% ↗ | 78.2% ↗ | -8.3 pt | GPT-5.2-Codex |
| LiveBench Instruction Following (LiveBench) | 63.3% ↗ | 66.4% ↗ | -3.1 pt | GPT-5.2-Codex |
| LiveBench Language (LiveBench) | 83.3% ↗ | 73.7% ↗ | +9.6 pt | Claude Opus 4.6 |
| LiveBench Mathematics (LiveBench) | 89.3% ↗ | 88.8% ↗ | +0.5 pt | Claude Opus 4.6 |
| LiveBench Reasoning (LiveBench) | 88.7% ↗ | 77.7% ↗ | +11 pt | Claude Opus 4.6 |
| LMArena WebDev (LMArena) | 1545.9 ↗ | 1338.9 ↗ | +207 | Claude Opus 4.6 |
| OSWorld-Verified | 72.7% ↗ | 38.2% ↗ | +34.5 pt | Claude Opus 4.6 |
| Terminal-Bench 2.0 | 65.4% ↗ | 64% ↗ | +1.4 pt | Claude Opus 4.6 |
| Only Claude Opus 4.6 reports · 28 | ||||
| SWE-bench Verified | 80.8% ↗ | not reported | — | — |
| GPQA Diamond | 91.3% ↗ | not reported | — | — |
| AIME 2026 | 96.7% ↗matharena | not reported | — | — |
| LMArena Elo | 1497.5 ↗ | not reported | — | — |
| APEX-Agents (Mercor) | 46.3% ↗ | not reported | — | — |
| ARC-AGI-2 (Verified) | 68.8% ↗ | not reported | — | — |
| Chess Puzzles (Epoch AI run) | 17% ↗epoch run | not reported | — | — |
| EBR-bench (Epoch AI run) | 12.7% ↗epoch run | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 26.8% ↗epoch run | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 66% ↗epoch run | not reported | — | — |
| Furniture Assembly (Epoch AI run) | 28.3% ↗epoch run | not reported | — | — |
| GSO Opt@1 (GSO) | 37.3% ↗ | not reported | — | — |
| LMArena Vision (LMArena) | 1299.4 ↗ | not reported | — | — |
| MCP Atlas | 59.5% ↗ | not reported | — | — |
| MMMLU | 91.1% ↗ | not reported | — | — |
| MMMU-Pro (no tools) | 73.9% ↗ | not reported | — | — |
| MMMU-Pro (with tools) | 77.3% ↗ | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 25% ↗epoch run | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 94.4% ↗epoch run | not reported | — | — |
| SAGE (Vals AI) | 51.6% ↗ | not reported | — | — |
| SimpleBench (SimpleBench) | 67.6% ↗ | not reported | — | — |
| SimpleQA Verified | 47% ↗epoch run | not reported | — | — |
| SWE-bench Verified (Epoch AI run) | 78.7% ↗epoch run | not reported | — | — |
| tau2-bench Banking Knowledge (Sierra) | 27.3% ↗ | not reported | — | — |
| Tau2-bench Retail | 91.9% ↗ | not reported | — | — |
| Tau2-bench Telecom | 99.3% ↗ | not reported | — | — |
| Vending-Bench 2 (Andon Labs) | 8017.59 ↗ | not reported | — | — |
| WeirdML (Håvard Tveit Ihle) | 78% ↗ | not reported | — | — |
| Only GPT-5.2-Codex reports · 3 | ||||
| Cybersecurity Capture The Flag Challenges | not reported | 67.4% ↗ | — | — |
| SWE-Bench Pro | not reported | 56.4% ↗ | — | — |
| SWE-Lancer IC Diamond | not reported | 76% ↗ | — | — |
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-5.2-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 4.6 | GPT-5.2-Codex | Edge |
|---|---|---|---|
| Context window | 1M tokens | 400K tokens | Claude Opus 4.6 |
| Max output | 128K tokens | 128K tokens | Tie |
| Input price / 1M | $5 ↗ | $1.75 ↗ | GPT-5.2-Codex |
| Output price / 1M | $25 ↗ | $14 ↗ | GPT-5.2-Codex |
| Cached input / 1M | $0.5 ↗ | $0.175 ↗ | GPT-5.2-Codex |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $30 | $15.75 | GPT-5.2-Codex |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-02-05 | 2025-12-18 | — |
| Cited benchmark scores | 46 | 13 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Opus 4.6 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 4.6 and GPT-5.2-Codex on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.