Model comparison
Claude Fable 5 vs GPT-5.4 Pro
Claude Fable 5 is the stronger model overall, scoring 66.3 to 58.8 on the Noometry Index.
Last verified . 12 shared benchmarks.
Summary
- They share 12 benchmarks with published results for both. Claude Fable 5 scores higher in 3 categories and GPT-5.4 Pro in 1 category; 4 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Fable 5 leads 67.0 to 42.6.
- The biggest single-benchmark swing is WeirdML: 91.9% for Claude Fable 5 and 57.4% for GPT-5.4 Pro.
- Claude Fable 5 is cheaper at $10 / $50 per million input/output tokens, against $30 / $180 for GPT-5.4 Pro.
- GPT-5.4 Pro accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Fable 5 | GPT-5.4 Pro | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 66.3 | 58.8 |
| Released | 2026-06-07 | 2026-03-05 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $10 | $30 |
| Output $ / M tokens | $50 | $180 |
| Results tracked | 61 | 16 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5 leads
Claude Fable 5: 67.0 (#4), GPT-5.4 Pro: 42.6 (#89)
| Benchmark | Claude Fable 5 | GPT-5.4 Pro |
|---|---|---|
| WeirdML | 91.9% | 57.4% |
| DeepSWE | 69.9% | — |
| FrontierCode | 53.5% | — |
| LMArena WebDev | 1626 | — |
| FrontierSWE | 47% | — |
| SciCode | 61% | — |
| LMArena Coding | 1519 | — |
| MirrorCode | 63.9% | — |
| ALE-Bench | 2,041 | — |
Agentic & Tool Use Not comparable
Claude Fable 5: 54.1 (#2), GPT-5.4 Pro: —
| Benchmark | Claude Fable 5 | GPT-5.4 Pro |
|---|---|---|
| APEX-Agents | 63.6% | — |
| Remote Labor Index | 16.1% | — |
| τ²-bench Banking | 39.7% | — |
| PostTrainBench | 41.8% | — |
| GBAEval | 74.5% | — |
| GDP.pdf | 30% | — |
| LMArena Search | 1230 | — |
| Vending-Bench 2 | 5,680 | — |
Reasoning Claude Fable 5 leads
Claude Fable 5: 76.8 (#4), GPT-5.4 Pro: 71.0 (#10)
| Benchmark | Claude Fable 5 | GPT-5.4 Pro |
|---|---|---|
| ARC-AGI-2 | 89.2% | 83.3% |
| SimpleBench | 81.9% | 74.1% |
| ARC-AGI-1 | 98.5% | 94.5% |
| CritPt | 28.6% | 30% |
| Chess Puzzles | 41% | 58.6% |
| EnigmaEval | 39.3% | 23.8% |
| Epoch Capabilities Index | 163.6 | 159.12 |
| Kagi LLM Benchmark | 91.4% | — |
| NYT Connections (extended) | 92.7% | — |
| EBR-Bench | 39.5% | — |
| LMArena Hard Prompts | 1508 | — |
| Mystery Game Puzzles | 52% | — |
| DTBench | 98.4% | — |
| LMCA | 61.1% | — |
| Surface Evolver Bench | 95% | — |
| Bench to the Future 3 | 0.13 | — |
Math Claude Fable 5 leads
Claude Fable 5: 88.4 (#5), GPT-5.4 Pro: 72.0 (#17)
| Benchmark | Claude Fable 5 | GPT-5.4 Pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 87% | 82.5% |
| FrontierMath Tier 4 | 90.2% | 58.5% |
| OTIS Mock AIME 2024-2025 | 100% | — |
| ProofBench | 95% | — |
| LMArena Math | 1519 | — |
| FrontierMath (Feb 2025 set) | — | 50% |
| FrontierMath Erdős | 0% | — |
| FrontierMath Tier 4 (v1) | — | 37.5% |
Knowledge GPT-5.4 Pro leads
Claude Fable 5: 62.3 (#22), GPT-5.4 Pro: 68.3 (#6)
| Benchmark | Claude Fable 5 | GPT-5.4 Pro |
|---|---|---|
| GPQA Diamond | 85.9% | 94.6% |
| SimpleQA Verified | 70.7% | 46.3% |
| Humanity's Last Exam | — | 44.3% |
| Vectara Hallucination Rate | — | 8.3% |
| LMArena Expert | 1534 | — |
Multimodal Not comparable
Claude Fable 5: 45.6 (#14), GPT-5.4 Pro: —
| Benchmark | Claude Fable 5 | GPT-5.4 Pro |
|---|---|---|
| LMArena Vision | 1326 | — |
| Blueprint-Bench 2 | 38.6% | — |
| Furniture Assembly | 35.8% | — |
| LMArena Document | 1496 | — |
Multilingual Not comparable
Claude Fable 5: 57.6 (#8), GPT-5.4 Pro: —
| Benchmark | Claude Fable 5 | GPT-5.4 Pro |
|---|---|---|
| LMArena Non-English | 1483 | — |
| LMArena Chinese | 1546 | — |
| LMArena French | 1509 | — |
| LMArena German | 1486 | — |
| LMArena Japanese | 1507 | — |
| LMArena Korean | 1493 | — |
| LMArena Russian | 1507 | — |
| LMArena Spanish | 1503 | — |
Instruction Following Not comparable
Claude Fable 5: 78.8 (#7), GPT-5.4 Pro: —
| Benchmark | Claude Fable 5 | GPT-5.4 Pro |
|---|---|---|
| LMArena Instruction Following | 1503 | — |
Long Context Not comparable
Claude Fable 5: 46.3 (#22), GPT-5.4 Pro: —
| Benchmark | Claude Fable 5 | GPT-5.4 Pro |
|---|---|---|
| LMArena Longer Query | 1510 | — |
Writing & Preference Not comparable
Claude Fable 5: 76.1 (#5), GPT-5.4 Pro: —
| Benchmark | Claude Fable 5 | GPT-5.4 Pro |
|---|---|---|
| LMArena Text | 1491 | — |
| LMArena Creative Writing | 1494 | — |
| EQ-Bench Creative Writing | 1943 | — |
| EQ-Bench 4 | 1340 | — |
| LMArena Multi-Turn | 1505 | — |
Frequently asked questions
Is Claude Fable 5 better than GPT-5.4 Pro?
Claude Fable 5 is the stronger model overall, scoring 66.3 to 58.8 on the Noometry Index.
Which is cheaper, Claude Fable 5 or GPT-5.4 Pro?
Claude Fable 5 is cheaper. It lists at $10 per million input tokens and $50 per million output tokens; GPT-5.4 Pro lists at $30 and $180.
Is Claude Fable 5 or GPT-5.4 Pro better for coding?
Claude Fable 5 scores higher on coding benchmarks: 67.0 versus 42.6 in the Noometry coding category.
Which has the bigger context window?
GPT-5.4 Pro does, with 1.05M tokens against 1M.
How many benchmarks do Claude Fable 5 and GPT-5.4 Pro share?
12 benchmarks have published results for both models. Claude Fable 5 has 61 scored results on Noometry and GPT-5.4 Pro has 16.