Model comparison
Claude Opus 5.5 vs GPT-5.3 Codex
Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 45.8 on the Noometry Index. GPT-5.3 Codex costs 1.7× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Summary
- They share 4 benchmarks with published results for both. Claude Opus 5.5 scores higher in 1 category and GPT-5.3 Codex in 1 category; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Opus 5.5 leads 71.9 to 48.6.
- GPT-5.3 Codex is cheaper at $1.75 / $14 per million input/output tokens, against $4 / $20 for Claude Opus 5.5.
- Claude Opus 5.5 accepts more context: 1M tokens versus 400K.
Side by side
| Claude Opus 5.5 | GPT-5.3 Codex | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 68.6 | 45.8 |
| Released | 2026-09-22 | 2026-02-05 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $4 | $1.75 |
| Output $ / M tokens | $20 | $14 |
| Results tracked | 44 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Opus 5.5 leads
Claude Opus 5.5: 71.9 (#3), GPT-5.3 Codex: 48.6 (#56)
| Benchmark | Claude Opus 5.5 | GPT-5.3 Codex |
|---|---|---|
| LMArena WebDev | 1813 | 1409 |
| ALE-Bench | 2,147 | 1,655 |
| SWE-bench Verified | — | 74.8% |
| FrontierCode | 54.6% | — |
| CursorBench | 57.8% | — |
| FrontierSWE | 62.3% | — |
| SciCode | 66.9% | — |
| WeirdML | — | 79.3% |
| LMArena Coding | 1547 | — |
| MirrorCode | 77.4% | — |
Agentic & Tool Use GPT-5.3 Codex leads
Claude Opus 5.5: 45.3 (#15), GPT-5.3 Codex: 48.0 (#9)
| Benchmark | Claude Opus 5.5 | GPT-5.3 Codex |
|---|---|---|
| Vending-Bench 2 | 9,235 | 5,940 |
| Terminal-Bench | — | 78.4% |
| APEX-Agents | 73.5% | — |
| GDP.pdf | 30.6% | — |
| METR Time Horizons | — | 74.5% |
Reasoning Not comparable
Claude Opus 5.5: 80.2 (#3), GPT-5.3 Codex: —
| Benchmark | Claude Opus 5.5 | GPT-5.3 Codex |
|---|---|---|
| Epoch Capabilities Index | 167.33 | 156.77 |
| ARC-AGI-2 | 93.3% | — |
| NYT Connections (extended) | 88.5% | — |
| ARC-AGI-1 | 98.5% | — |
| CritPt | 31.7% | — |
| EBR-Bench | 71.4% | — |
| LMArena Hard Prompts | 1535 | — |
| Mystery Game Puzzles | 71% | — |
| DTBench | 98.9% | — |
| LMCA | 68.2% | — |
Math Not comparable
Claude Opus 5.5: 91.8 (#3), GPT-5.3 Codex: —
| Benchmark | Claude Opus 5.5 | GPT-5.3 Codex |
|---|---|---|
| FrontierMath (Tiers 1-3) | 91.2% | — |
| FrontierMath Tier 4 | 95% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 100% | — |
| LMArena Math | 1506 | — |
| FrontierMath Erdős | 2.9% | — |
Knowledge Not comparable
Claude Opus 5.5: 66.4 (#10), GPT-5.3 Codex: —
| Benchmark | Claude Opus 5.5 | GPT-5.3 Codex |
|---|---|---|
| GPQA Diamond | 90.6% | — |
| SimpleQA Verified | 72.2% | — |
| LMArena Expert | 1547 | — |
Multimodal Not comparable
Claude Opus 5.5: 57.8 (#1), GPT-5.3 Codex: —
| Benchmark | Claude Opus 5.5 | GPT-5.3 Codex |
|---|---|---|
| LMArena Vision | 1321 | — |
| Blueprint-Bench 2 | 51.2% | — |
| Furniture Assembly | 83.3% | — |
Multilingual Not comparable
Claude Opus 5.5: 59.1 (#2), GPT-5.3 Codex: —
| Benchmark | Claude Opus 5.5 | GPT-5.3 Codex |
|---|---|---|
| LMArena Non-English | 1507 | — |
| LMArena Chinese | 1588 | — |
| LMArena French | 1514 | — |
| LMArena Russian | 1520 | — |
| LMArena Spanish | 1507 | — |
Instruction Following Not comparable
Claude Opus 5.5: 80.0 (#3), GPT-5.3 Codex: —
| Benchmark | Claude Opus 5.5 | GPT-5.3 Codex |
|---|---|---|
| LMArena Instruction Following | 1537 | — |
Long Context Not comparable
Claude Opus 5.5: 47.1 (#19), GPT-5.3 Codex: —
| Benchmark | Claude Opus 5.5 | GPT-5.3 Codex |
|---|---|---|
| LMArena Longer Query | 1532 | — |
Writing & Preference Not comparable
Claude Opus 5.5: 78.2 (#3), GPT-5.3 Codex: —
| Benchmark | Claude Opus 5.5 | GPT-5.3 Codex |
|---|---|---|
| LMArena Text | 1515 | — |
| LMArena Creative Writing | 1533 | — |
| EQ-Bench Creative Writing | 2050 | — |
| LMArena Multi-Turn | 1499 | — |
Frequently asked questions
Is Claude Opus 5.5 better than GPT-5.3 Codex?
Claude Opus 5.5 is the stronger model overall, scoring 68.6 to 45.8 on the Noometry Index. GPT-5.3 Codex costs 1.7× less per token, which makes it the better buy when Claude Opus 5.5's lead doesn't matter for your workload.
Which is cheaper, Claude Opus 5.5 or GPT-5.3 Codex?
GPT-5.3 Codex is cheaper. It lists at $1.75 per million input tokens and $14 per million output tokens; Claude Opus 5.5 lists at $4 and $20.
Is Claude Opus 5.5 or GPT-5.3 Codex better for coding?
Claude Opus 5.5 scores higher on coding benchmarks: 71.9 versus 48.6 in the Noometry coding category.
Which has the bigger context window?
Claude Opus 5.5 does, with 1M tokens against 400K.
How many benchmarks do Claude Opus 5.5 and GPT-5.3 Codex share?
4 benchmarks have published results for both models. Claude Opus 5.5 has 44 scored results on Noometry and GPT-5.3 Codex has 8.