Model comparison
Claude Fable 5.1 vs GPT-5.3 Codex
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 45.8 on the Noometry Index. GPT-5.3 Codex costs 4.2× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Last verified . 5 shared benchmarks.
Summary
- They share 5 benchmarks with published results for both. Claude Fable 5.1 scores higher in 2 categories and GPT-5.3 Codex in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Fable 5.1 leads 74.7 to 48.6.
- The biggest single-benchmark swing is WeirdML: 92.9% for Claude Fable 5.1 and 79.3% for GPT-5.3 Codex.
- GPT-5.3 Codex is cheaper at $1.75 / $14 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- Claude Fable 5.1 accepts more context: 1M tokens versus 400K.
Side by side
| Claude Fable 5.1 | GPT-5.3 Codex | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 69.0 | 45.8 |
| Released | 2026-09-01 | 2026-02-05 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 400K |
| Max output | 128K | 128K |
| Input $ / M tokens | $10 | $1.75 |
| Output $ / M tokens | $50 | $14 |
| Results tracked | 52 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5.1 leads
Claude Fable 5.1: 74.7 (#1), GPT-5.3 Codex: 48.6 (#56)
| Benchmark | Claude Fable 5.1 | GPT-5.3 Codex |
|---|---|---|
| LMArena WebDev | 1744 | 1409 |
| WeirdML | 92.9% | 79.3% |
| ALE-Bench | 2,143 | 1,655 |
| SWE-bench Verified | — | 74.8% |
| FrontierCode | 50.9% | — |
| CursorBench | 51.8% | — |
| FrontierSWE | 56.3% | — |
| SciCode | 63.1% | — |
| GSO | 88.2% | — |
| LMArena Coding | 1528 | — |
| MirrorCode | 73.3% | — |
Agentic & Tool Use Claude Fable 5.1 leads
Claude Fable 5.1: 50.7 (#5), GPT-5.3 Codex: 48.0 (#9)
| Benchmark | Claude Fable 5.1 | GPT-5.3 Codex |
|---|---|---|
| Vending-Bench 2 | 5,422 | 5,940 |
| Terminal-Bench | — | 78.4% |
| APEX-Agents | 68.6% | — |
| Remote Labor Index | 17.9% | — |
| GDP.pdf | 29.6% | — |
| METR Time Horizons | — | 74.5% |
Reasoning Not comparable
Claude Fable 5.1: 76.7 (#7), GPT-5.3 Codex: —
| Benchmark | Claude Fable 5.1 | GPT-5.3 Codex |
|---|---|---|
| Epoch Capabilities Index | 164.7 | 156.77 |
| ARC-AGI-2 | 90% | — |
| NYT Connections (extended) | 90% | — |
| ARC-AGI-1 | 97.5% | — |
| CritPt | 31.1% | — |
| Chess Puzzles | 47% | — |
| EBR-Bench | 57.1% | — |
| LMArena Hard Prompts | 1526 | — |
| Mystery Game Puzzles | 58% | — |
| DTBench | 97.6% | — |
| LMCA | 65.5% | — |
Math Not comparable
Claude Fable 5.1: 89.6 (#4), GPT-5.3 Codex: —
| Benchmark | Claude Fable 5.1 | GPT-5.3 Codex |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | — |
| FrontierMath Tier 4 | 87.8% | — |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 100% | — |
| LMArena Math | 1525 | — |
| FrontierMath Erdős | 0% | — |
Knowledge Not comparable
Claude Fable 5.1: 69.6 (#6), GPT-5.3 Codex: —
| Benchmark | Claude Fable 5.1 | GPT-5.3 Codex |
|---|---|---|
| Humanity's Last Exam | 46.5% | — |
| SimpleQA Verified | 70.8% | — |
| LMArena Expert | 1535 | — |
Multimodal Not comparable
Claude Fable 5.1: 53.9 (#4), GPT-5.3 Codex: —
| Benchmark | Claude Fable 5.1 | GPT-5.3 Codex |
|---|---|---|
| LMArena Vision | 1318 | — |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |
Multilingual Not comparable
Claude Fable 5.1: 59.1 (#3), GPT-5.3 Codex: —
| Benchmark | Claude Fable 5.1 | GPT-5.3 Codex |
|---|---|---|
| LMArena Non-English | 1507 | — |
| LMArena Chinese | 1586 | — |
| LMArena French | 1525 | — |
| LMArena German | 1500 | — |
| LMArena Japanese | 1543 | — |
| LMArena Korean | 1534 | — |
| LMArena Russian | 1521 | — |
| LMArena Spanish | 1516 | — |
Instruction Following Not comparable
Claude Fable 5.1: 79.2 (#6), GPT-5.3 Codex: —
| Benchmark | Claude Fable 5.1 | GPT-5.3 Codex |
|---|---|---|
| LMArena Instruction Following | 1517 | — |
Long Context Not comparable
Claude Fable 5.1: 46.7 (#20), GPT-5.3 Codex: —
| Benchmark | Claude Fable 5.1 | GPT-5.3 Codex |
|---|---|---|
| LMArena Longer Query | 1522 | — |
Writing & Preference Not comparable
Claude Fable 5.1: 79.2 (#2), GPT-5.3 Codex: —
| Benchmark | Claude Fable 5.1 | GPT-5.3 Codex |
|---|---|---|
| LMArena Text | 1510 | — |
| LMArena Creative Writing | 1507 | — |
| EQ-Bench Creative Writing | 2162 | — |
| LMArena Multi-Turn | 1492 | — |
Frequently asked questions
Is Claude Fable 5.1 better than GPT-5.3 Codex?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 45.8 on the Noometry Index. GPT-5.3 Codex costs 4.2× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Which is cheaper, Claude Fable 5.1 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 Fable 5.1 lists at $10 and $50.
Is Claude Fable 5.1 or GPT-5.3 Codex better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 48.6 in the Noometry coding category.
Which has the bigger context window?
Claude Fable 5.1 does, with 1M tokens against 400K.
How many benchmarks do Claude Fable 5.1 and GPT-5.3 Codex share?
5 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and GPT-5.3 Codex has 8.