Model comparison
Claude Fable 5 vs GPT-6 Sol
Claude Fable 5 is the stronger model overall, scoring 66.8 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's lead doesn't matter for your workload.
Last verified . 44 shared benchmarks.
Summary
- They share 44 benchmarks with published results for both. Claude Fable 5 scores higher in 8 categories and GPT-6 Sol in 2 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where Claude Fable 5 leads 54.0 to 37.2.
- The biggest single-benchmark swing is Furniture Assembly: 35.8% for Claude Fable 5 and 58.3% for GPT-6 Sol.
- GPT-6 Sol is cheaper at $2 / $10 per million input/output tokens, against $10 / $50 for Claude Fable 5.
- GPT-6 Sol accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Fable 5 | GPT-6 Sol | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 66.8 | 61.8 |
| Released | 2026-06-07 | 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 | 62 | 45 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Fable 5 leads
Claude Fable 5: 70.6 (#4), GPT-6 Sol: 60.1 (#11)
| Benchmark | Claude Fable 5 | GPT-6 Sol |
|---|---|---|
| DeepSWE | 69.9% | 68.8% |
| FrontierCode | 53.5% | 49.3% |
| LMArena WebDev | 1625 | 1688 |
| SciCode | 61% | 57.6% |
| LMArena Coding | 1519 | 1447 |
| ALE-Bench | 2,041 | 2,462 |
| FrontierSWE | 47% | — |
| GSO | 78.4% | — |
| WeirdML | 91.9% | — |
| MirrorCode | 63.9% | — |
Agentic & Tool Use Claude Fable 5 leads
Claude Fable 5: 54.0 (#2), GPT-6 Sol: 37.2 (#36)
| Benchmark | Claude Fable 5 | GPT-6 Sol |
|---|---|---|
| APEX-Agents | 63.6% | 54.3% |
| GDP.pdf | 30% | 26.4% |
| Vending-Bench 2 | 5,680 | 14,428 |
| Remote Labor Index | 16.1% | — |
| τ²-bench Banking | 39.7% | — |
| PostTrainBench | 41.8% | — |
| GBAEval | 74.5% | — |
| LMArena Search | 1230 | — |
Reasoning Claude Fable 5 leads
Claude Fable 5: 76.8 (#6), GPT-6 Sol: 74.0 (#9)
| Benchmark | Claude Fable 5 | GPT-6 Sol |
|---|---|---|
| ARC-AGI-2 | 89.2% | 89.6% |
| NYT Connections (extended) | 92.7% | 90.1% |
| ARC-AGI-1 | 98.5% | 95.5% |
| CritPt | 28.6% | 30.9% |
| EBR-Bench | 39.5% | 53.3% |
| LMArena Hard Prompts | 1508 | 1418 |
| Mystery Game Puzzles | 52% | 56% |
| DTBench | 98.4% | 97.3% |
| LMCA | 61.1% | 59.1% |
| Epoch Capabilities Index | 162.06 | 162.72 |
| SimpleBench | 81.9% | — |
| Kagi LLM Benchmark | 91.4% | — |
| Chess Puzzles | 41% | — |
| EnigmaEval | 39.3% | — |
| Surface Evolver Bench | 95% | — |
| Bench to the Future 3 | 0.13 | — |
Math Claude Fable 5 leads
Claude Fable 5: 88.5 (#5), GPT-6 Sol: 87.2 (#7)
| Benchmark | Claude Fable 5 | GPT-6 Sol |
|---|---|---|
| FrontierMath (Tiers 1-3) | 87% | 89.8% |
| FrontierMath Tier 4 | 90.2% | 90% |
| OTIS Mock AIME 2024-2025 | 100% | 100% |
| ProofBench | 95% | 83% |
| LMArena Math | 1519 | 1402 |
| FrontierMath Erdős | 0% | — |
Knowledge GPT-6 Sol leads
Claude Fable 5: 62.2 (#25), GPT-6 Sol: 64.8 (#15)
| Benchmark | Claude Fable 5 | GPT-6 Sol |
|---|---|---|
| GPQA Diamond | 85.9% | 94.3% |
| SimpleQA Verified | 70.7% | 60.7% |
| LMArena Expert | 1534 | 1439 |
| Vectara Hallucination Rate | — | 6.5% |
Multimodal GPT-6 Sol leads
Claude Fable 5: 45.3 (#17), GPT-6 Sol: 47.6 (#10)
| Benchmark | Claude Fable 5 | GPT-6 Sol |
|---|---|---|
| LMArena Vision | 1324 | 1245 |
| Blueprint-Bench 2 | 38.6% | 36.9% |
| Furniture Assembly | 35.8% | 58.3% |
| LMArena Document | 1496 | — |
Multilingual Claude Fable 5 leads
Claude Fable 5: 57.3 (#9), GPT-6 Sol: 50.5 (#118)
| Benchmark | Claude Fable 5 | GPT-6 Sol |
|---|---|---|
| LMArena Non-English | 1481 | 1385 |
| LMArena Chinese | 1543 | 1405 |
| LMArena French | 1505 | 1410 |
| LMArena German | 1486 | 1390 |
| LMArena Japanese | 1506 | 1385 |
| LMArena Korean | 1488 | 1341 |
| LMArena Russian | 1504 | 1401 |
| LMArena Spanish | 1498 | 1384 |
Instruction Following Claude Fable 5 leads
Claude Fable 5: 78.6 (#8), GPT-6 Sol: 74.5 (#94)
| Benchmark | Claude Fable 5 | GPT-6 Sol |
|---|---|---|
| LMArena Instruction Following | 1502 | 1412 |
Long Context Claude Fable 5 leads
Claude Fable 5: 46.3 (#23), GPT-6 Sol: 43.1 (#108)
| Benchmark | Claude Fable 5 | GPT-6 Sol |
|---|---|---|
| LMArena Longer Query | 1509 | 1411 |
Writing & Preference Claude Fable 5 leads
Claude Fable 5: 75.9 (#5), GPT-6 Sol: 71.9 (#18)
| Benchmark | Claude Fable 5 | GPT-6 Sol |
|---|---|---|
| LMArena Text | 1491 | 1395 |
| LMArena Creative Writing | 1494 | 1378 |
| EQ-Bench Creative Writing | 1943 | 2125 |
| LMArena Multi-Turn | 1504 | 1412 |
| EQ-Bench 4 | 1340 | — |
Frequently asked questions
Is Claude Fable 5 better than GPT-6 Sol?
Claude Fable 5 is the stronger model overall, scoring 66.8 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's lead doesn't matter for your workload.
Which is cheaper, Claude Fable 5 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 lists at $10 and $50.
Is Claude Fable 5 or GPT-6 Sol better for coding?
Claude Fable 5 scores higher on coding benchmarks: 70.6 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 and GPT-6 Sol share?
44 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and GPT-6 Sol has 45.