Model comparison
Claude Fable 5.1 vs GPT-5.6 Sol
Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 64.4 on the Noometry Index. GPT-5.6 Sol costs 2.5× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Last verified . 48 shared benchmarks.
Summary
- They share 48 benchmarks with published results for both. Claude Fable 5.1 scores higher in 10 categories and GPT-5.6 Sol in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Fable 5.1 leads 70.5 to 61.1.
- The biggest single-benchmark swing is MirrorCode: 73.3% for Claude Fable 5.1 and 20% for GPT-5.6 Sol.
- GPT-5.6 Sol is cheaper at $4 / $20 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- GPT-5.6 Sol accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Fable 5.1 | GPT-5.6 Sol | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 68.5 | 64.4 |
| Released | 2026-09-01 | 2026-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $10 | $4 |
| Output $ / M tokens | $50 | $20 |
| Results tracked | 50 | 64 |
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: 70.5 (#2), GPT-5.6 Sol: 61.1 (#7)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Sol |
|---|---|---|
| FrontierCode | 50.9% | 47.5% |
| CursorBench | 51.8% | 41.7% |
| LMArena WebDev | 1753 | 1619 |
| FrontierSWE | 56.3% | 32.2% |
| SciCode | 63.1% | 57.1% |
| WeirdML | 92.9% | 89.4% |
| LMArena Coding | 1523 | 1493 |
| MirrorCode | 73.3% | 20% |
| ALE-Bench | 2,143 | 2,177 |
| DeepSWE | — | 72.7% |
Agentic & Tool Use Too close to call
Claude Fable 5.1: 50.8 (#5), GPT-5.6 Sol: 50.2 (#7)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Sol |
|---|---|---|
| APEX-Agents | 68.6% | 51.4% |
| GDP.pdf | 29.6% | 30.7% |
| Vending-Bench 2 | 5,422 | 9,619 |
| OSWorld 2.0 | — | 27.3% |
| Remote Labor Index | 17.9% | — |
| τ²-bench Banking | — | 46.9% |
| PostTrainBench | — | 36.2% |
| BALROG | — | 60% |
| GBAEval | — | 52.6% |
| LMArena Search | — | 1257 |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#5), GPT-5.6 Sol: 74.7 (#6)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Sol |
|---|---|---|
| ARC-AGI-2 | 90% | 92.5% |
| NYT Connections (extended) | 90% | 93.8% |
| ARC-AGI-1 | 97.5% | 97.5% |
| CritPt | 31.1% | 32.3% |
| Chess Puzzles | 47% | 64% |
| EBR-Bench | 57.1% | 44.8% |
| LMArena Hard Prompts | 1526 | 1481 |
| Mystery Game Puzzles | 58% | 58% |
| DTBench | 97.6% | 96% |
| LMCA | 65.5% | 59.2% |
| Epoch Capabilities Index | 165 | 161.99 |
| SimpleBench | — | 71.7% |
| Kagi LLM Benchmark | — | 67% |
| EnigmaEval | — | 37.1% |
| Surface Evolver Bench | — | 93.1% |
| Bench to the Future 3 | — | 0.14 |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.5 (#3), GPT-5.6 Sol: 85.5 (#7)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | 89.1% |
| FrontierMath Tier 4 | 87.8% | 82.9% |
| OTIS Mock AIME 2024-2025 | 100% | 100% |
| ProofBench | 100% | 83% |
| LMArena Math | 1519 | 1472 |
| FrontierMath Erdős | 0% | 0% |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.3 (#5), GPT-5.6 Sol: 64.3 (#16)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Sol |
|---|---|---|
| SimpleQA Verified | 70.8% | 69.7% |
| LMArena Expert | 1528 | 1517 |
| GPQA Diamond | — | 93.5% |
| Humanity's Last Exam | 46.5% | — |
| Vectara Hallucination Rate | — | 12.4% |
Multimodal Claude Fable 5.1 leads
Claude Fable 5.1: 54.1 (#4), GPT-5.6 Sol: 48.9 (#8)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Sol |
|---|---|---|
| LMArena Vision | 1319 | 1281 |
| Blueprint-Bench 2 | 41.9% | 33.6% |
| Furniture Assembly | 70% | 56.7% |
| LMArena Document | 1513 | 1483 |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.5 (#2), GPT-5.6 Sol: 55.4 (#32)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Sol |
|---|---|---|
| LMArena Non-English | 1509 | 1450 |
| LMArena Chinese | 1589 | 1523 |
| LMArena French | 1532 | 1475 |
| LMArena German | 1495 | 1476 |
| LMArena Japanese | 1565 | 1475 |
| LMArena Russian | 1525 | 1466 |
| LMArena Spanish | 1503 | 1449 |
| LMArena Korean | — | 1434 |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.3 (#6), GPT-5.6 Sol: 77.8 (#16)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Sol |
|---|---|---|
| LMArena Instruction Following | 1515 | 1480 |
Long Context Claude Fable 5.1 leads
Claude Fable 5.1: 46.8 (#19), GPT-5.6 Sol: 45.3 (#42)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Sol |
|---|---|---|
| LMArena Longer Query | 1524 | 1479 |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.3 (#1), GPT-5.6 Sol: 73.5 (#12)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Sol |
|---|---|---|
| LMArena Text | 1511 | 1456 |
| LMArena Creative Writing | 1507 | 1450 |
| EQ-Bench Creative Writing | 2162 | 1972 |
| LMArena Multi-Turn | 1492 | 1456 |
| EQ-Bench 4 | — | 1250 |
Frequently asked questions
Is Claude Fable 5.1 better than GPT-5.6 Sol?
Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 64.4 on the Noometry Index. GPT-5.6 Sol costs 2.5× 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-5.6 Sol?
GPT-5.6 Sol is cheaper. It lists at $4 per million input tokens and $20 per million output tokens; Claude Fable 5.1 lists at $10 and $50.
Is Claude Fable 5.1 or GPT-5.6 Sol better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 61.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Sol does, with 1.05M tokens against 1M.
How many benchmarks do Claude Fable 5.1 and GPT-5.6 Sol share?
48 benchmarks have published results for both models. Claude Fable 5.1 has 50 scored results on Noometry and GPT-5.6 Sol has 64.