Model comparison
Claude Fable 5.1 vs GPT-6 Sol
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 61.8 on the Noometry Index. GPT-6 Sol costs 5.0× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Last verified . 42 shared benchmarks.
Summary
- They share 42 benchmarks with published results for both. Claude Fable 5.1 scores higher in 10 categories and GPT-6 Sol in 0 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in coding, where Claude Fable 5.1 leads 74.7 to 60.1.
- The biggest single-benchmark swing is ProofBench: 100% for Claude Fable 5.1 and 83% for GPT-6 Sol.
- GPT-6 Sol is cheaper at $2 / $10 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- GPT-6 Sol accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Fable 5.1 | GPT-6 Sol | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 69.0 | 61.8 |
| Released | 2026-09-01 | 2026-09-22 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $10 | $2 |
| Output $ / M tokens | $50 | $10 |
| Results tracked | 52 | 45 |
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-6 Sol: 60.1 (#11)
| Benchmark | Claude Fable 5.1 | GPT-6 Sol |
|---|---|---|
| FrontierCode | 50.9% | 49.3% |
| LMArena WebDev | 1744 | 1688 |
| SciCode | 63.1% | 57.6% |
| LMArena Coding | 1528 | 1447 |
| ALE-Bench | 2,143 | 2,462 |
| DeepSWE | — | 68.8% |
| CursorBench | 51.8% | — |
| FrontierSWE | 56.3% | — |
| GSO | 88.2% | — |
| WeirdML | 92.9% | — |
| MirrorCode | 73.3% | — |
Agentic & Tool Use Claude Fable 5.1 leads
Claude Fable 5.1: 50.7 (#5), GPT-6 Sol: 37.2 (#36)
| Benchmark | Claude Fable 5.1 | GPT-6 Sol |
|---|---|---|
| APEX-Agents | 68.6% | 54.3% |
| GDP.pdf | 29.6% | 26.4% |
| Vending-Bench 2 | 5,422 | 14,428 |
| Remote Labor Index | 17.9% | — |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#7), GPT-6 Sol: 74.0 (#9)
| Benchmark | Claude Fable 5.1 | GPT-6 Sol |
|---|---|---|
| ARC-AGI-2 | 90% | 89.6% |
| NYT Connections (extended) | 90% | 90.1% |
| ARC-AGI-1 | 97.5% | 95.5% |
| CritPt | 31.1% | 30.9% |
| EBR-Bench | 57.1% | 53.3% |
| LMArena Hard Prompts | 1526 | 1418 |
| Mystery Game Puzzles | 58% | 56% |
| DTBench | 97.6% | 97.3% |
| LMCA | 65.5% | 59.1% |
| Epoch Capabilities Index | 164.7 | 162.72 |
| Chess Puzzles | 47% | — |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.6 (#4), GPT-6 Sol: 87.2 (#7)
| Benchmark | Claude Fable 5.1 | GPT-6 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | 89.8% |
| FrontierMath Tier 4 | 87.8% | 90% |
| OTIS Mock AIME 2024-2025 | 100% | 100% |
| ProofBench | 100% | 83% |
| LMArena Math | 1525 | 1402 |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.6 (#6), GPT-6 Sol: 64.8 (#15)
| Benchmark | Claude Fable 5.1 | GPT-6 Sol |
|---|---|---|
| SimpleQA Verified | 70.8% | 60.7% |
| LMArena Expert | 1535 | 1439 |
| GPQA Diamond | — | 94.3% |
| Humanity's Last Exam | 46.5% | — |
| Vectara Hallucination Rate | — | 6.5% |
Multimodal Claude Fable 5.1 leads
Claude Fable 5.1: 53.9 (#4), GPT-6 Sol: 47.6 (#10)
| Benchmark | Claude Fable 5.1 | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1318 | 1245 |
| Blueprint-Bench 2 | 41.9% | 36.9% |
| Furniture Assembly | 70% | 58.3% |
| LMArena Document | 1513 | — |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.1 (#3), GPT-6 Sol: 50.5 (#118)
| Benchmark | Claude Fable 5.1 | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1507 | 1385 |
| LMArena Chinese | 1586 | 1405 |
| LMArena French | 1525 | 1410 |
| LMArena German | 1500 | 1390 |
| LMArena Japanese | 1543 | 1385 |
| LMArena Korean | 1534 | 1341 |
| LMArena Russian | 1521 | 1401 |
| LMArena Spanish | 1516 | 1384 |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#6), GPT-6 Sol: 74.5 (#94)
| Benchmark | Claude Fable 5.1 | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1517 | 1412 |
Long Context Claude Fable 5.1 leads
Claude Fable 5.1: 46.7 (#20), GPT-6 Sol: 43.1 (#108)
| Benchmark | Claude Fable 5.1 | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1522 | 1411 |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#2), GPT-6 Sol: 71.9 (#18)
| Benchmark | Claude Fable 5.1 | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1510 | 1395 |
| LMArena Creative Writing | 1507 | 1378 |
| EQ-Bench Creative Writing | 2162 | 2125 |
| LMArena Multi-Turn | 1492 | 1412 |
Frequently asked questions
Is Claude Fable 5.1 better than GPT-6 Sol?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 61.8 on the Noometry Index. GPT-6 Sol costs 5.0× 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-6 Sol?
GPT-6 Sol is cheaper. It lists at $2 per million input tokens and $10 per million output tokens; Claude Fable 5.1 lists at $10 and $50.
Is Claude Fable 5.1 or GPT-6 Sol better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 60.1 in the Noometry coding category.
Which has the bigger context window?
GPT-6 Sol does, with 1.05M tokens against 1M.
How many benchmarks do Claude Fable 5.1 and GPT-6 Sol share?
42 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and GPT-6 Sol has 45.