Compare / head-to-head
Claude Sonnet 4.5vs
GPT-5.3-Codex
GPT-5.3-Codex leads 5 of 5 shared benchmarks. GPT-5.3-Codex is 1.1x cheaper per token. GPT-5.3-Codex has the larger context window (400K tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 5
GPT-5.3-Codex leads
Cheaper per token
GPT-5.3-Codex
1.1x cheaper, input + output
Larger context
GPT-5.3-Codex
400K tokens
Providers
2 providers
Anthropic · OpenAI
Claude Sonnet 4.5
Anthropic · released 2025-09-29
textvision
GPT-5.3-Codex
OpenAI · released 2026-02-05
textvision
Quality
Benchmark matrix
5 shared · 31 only Claude Sonnet 4.5 · 4 only GPT-5.3-Codex| Benchmark | Claude Sonnet 4.5 | GPT-5.3-Codex | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 5 | ||||
| OSWorld-Verified | 61.4% ↗ | 64.7% ↗ | -3.3 pt | GPT-5.3-Codex |
| SWE-bench Verified (Epoch AI run) | 71.3% ↗epoch run | 74.8% ↗epoch run | -3.5 pt | GPT-5.3-Codex |
| Terminal-Bench 2.0 | 51% ↗ | 77.3% ↗ | -26.3 pt | GPT-5.3-Codex |
| Vending-Bench 2 (Andon Labs) | 3838.74 ↗ | 5940.12 ↗ | -2101.4 | GPT-5.3-Codex |
| WeirdML (Håvard Tveit Ihle) | 47.7% ↗ | 79.3% ↗ | -31.6 pt | GPT-5.3-Codex |
| Only Claude Sonnet 4.5 reports · 31 | ||||
| SWE-bench Verified | 77.2% ↗ | not reported | — | — |
| GPQA Diamond | 83.4% ↗ | not reported | — | — |
| AIME 2025 | 84.2% ↗matharena ⚠ | not reported | — | — |
| Humanity's Last Exam (no tools) | 17.7% ↗ | not reported | — | — |
| LMArena Elo | 1456.6 ↗ | not reported | — | — |
| ARC-AGI-2 (Verified) | 13.6% ↗ | not reported | — | — |
| Chess Puzzles (Epoch AI run) | 12% ↗epoch run | not reported | — | — |
| EBR-bench (Epoch AI run) | 2.4% ↗epoch run | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 2.4% ↗epoch run | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 23.9% ↗epoch run | not reported | — | — |
| GDPval-AA | 1276 ↗ | not reported | — | — |
| GSO Opt@1 (GSO) | 12.7% ↗ | not reported | — | — |
| Humanity's Last Exam (with tools) | 33.6% ↗ | not reported | — | — |
| LMArena WebDev (LMArena) | 1393 ↗ | not reported | — | — |
| MATH Level 5 (Epoch AI run) | 97.7% ↗epoch run | not reported | — | — |
| MCP Atlas | 43.8% ↗ | not reported | — | — |
| MMMLU | 89.5% ↗ | not reported | — | — |
| MMMU-Pro (no tools) | 63.4% ↗ | not reported | — | — |
| MMMU-Pro (with tools) | 68.9% ↗ | not reported | — | — |
| Mystery Game Puzzles (Epoch AI run) | 17% ↗epoch run | not reported | — | — |
| OSWorld-Verified (XLANG) | 62.9% ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 77.8% ↗epoch run | not reported | — | — |
| SAGE (Vals AI) | 36.1% ↗ | not reported | — | — |
| SimpleBench (SimpleBench) | 54.3% ↗ | not reported | — | — |
| SimpleQA Verified | 30.7% ↗epoch run | not reported | — | — |
| tau2-bench Airline (Sierra) | 72% ↗ | not reported | — | — |
| tau2-bench Banking Knowledge (Sierra) | 25.3% ↗ | not reported | — | — |
| Tau2-bench Retail | 86.2% ↗ | not reported | — | — |
| tau2-bench Retail (Sierra) | 72.4% ↗ | not reported | — | — |
| Tau2-bench Telecom | 98% ↗ | not reported | — | — |
| tau2-bench Telecom (Sierra) | 84.9% ↗ | not reported | — | — |
| Only GPT-5.3-Codex reports · 4 | ||||
| Cybersecurity Capture The Flag Challenges | not reported | 77.6% ↗ | — | — |
| GDPval (wins or ties) | not reported | 70.9% ↗ | — | — |
| SWE-Bench Pro (Public) | not reported | 56.8% ↗ | — | — |
| SWE-Lancer IC Diamond | not reported | 81.4% ↗ | — | — |
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 Sonnet 4.5 minus GPT-5.3-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 Sonnet 4.5 | GPT-5.3-Codex | Edge |
|---|---|---|---|
| Context window | 200K tokens | 400K tokens | GPT-5.3-Codex |
| Max output | 64K tokens | 128K tokens | GPT-5.3-Codex |
| Input price / 1M | $3 ↗ | $1.75 ↗ | GPT-5.3-Codex |
| Output price / 1M | $15 ↗ | $14 ↗ | GPT-5.3-Codex |
| Cached input / 1M | $0.3 ↗ | $0.175 ↗ | GPT-5.3-Codex |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $18 | $15.75 | GPT-5.3-Codex |
| Modalities | text · vision | text · vision | Tie |
| Released | 2025-09-29 | 2026-02-05 | — |
| Cited benchmark scores | 43 | 9 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Sonnet 4.5 vs …
Models sharing the most benchmarksMore matchups
GPT-5.3-Codex vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Sonnet 4.5 and GPT-5.3-Codex on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.