Model comparison
Claude Fable 5.1 vs GPT-5.6 Terra
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 59.2 on the Noometry Index. GPT-5.6 Terra costs 4.4× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Last verified . 45 shared benchmarks.
Summary
- They share 45 benchmarks with published results for both. Claude Fable 5.1 scores higher in 10 categories and GPT-5.6 Terra 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 57.7.
- The biggest single-benchmark swing is SimpleQA Verified: 70.8% for Claude Fable 5.1 and 43.2% for GPT-5.6 Terra.
- GPT-5.6 Terra is cheaper at $2 / $12 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- GPT-5.6 Terra accepts more context: 1.05M tokens versus 1M.
Side by side
| Claude Fable 5.1 | GPT-5.6 Terra | |
|---|---|---|
| Provider | Anthropic | OpenAI |
| Noometry Index | 69.0 | 59.2 |
| Released | 2026-09-01 | 2026-07-09 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.05M |
| Max output | 128K | 128K |
| Input $ / M tokens | $10 | $2 |
| Output $ / M tokens | $50 | $12 |
| Results tracked | 52 | 52 |
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-5.6 Terra: 57.7 (#19)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Terra |
|---|---|---|
| FrontierCode | 50.9% | 41.3% |
| CursorBench | 51.8% | 41.3% |
| LMArena WebDev | 1744 | 1522 |
| SciCode | 63.1% | 55% |
| WeirdML | 92.9% | 78.3% |
| LMArena Coding | 1528 | 1484 |
| ALE-Bench | 2,143 | 1,951 |
| DeepSWE | — | 69.6% |
| FrontierSWE | 56.3% | — |
| GSO | 88.2% | — |
| MirrorCode | 73.3% | — |
Agentic & Tool Use Claude Fable 5.1 leads
Claude Fable 5.1: 50.7 (#5), GPT-5.6 Terra: 40.1 (#25)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Terra |
|---|---|---|
| APEX-Agents | 68.6% | 58.2% |
| GDP.pdf | 29.6% | 24.7% |
| Vending-Bench 2 | 5,422 | 7,343 |
| Remote Labor Index | 17.9% | — |
| BALROG | — | 53.2% |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#7), GPT-5.6 Terra: 60.7 (#21)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Terra |
|---|---|---|
| ARC-AGI-2 | 90% | 83.9% |
| NYT Connections (extended) | 90% | 78.4% |
| ARC-AGI-1 | 97.5% | 96.5% |
| CritPt | 31.1% | 30% |
| Chess Puzzles | 47% | 54% |
| LMArena Hard Prompts | 1526 | 1468 |
| Mystery Game Puzzles | 58% | 35% |
| DTBench | 97.6% | 93.3% |
| LMCA | 65.5% | 55% |
| Epoch Capabilities Index | 164.7 | 159.62 |
| SimpleBench | — | 48.9% |
| Kagi LLM Benchmark | — | 51.3% |
| EBR-Bench | 57.1% | — |
| Surface Evolver Bench | — | 83.8% |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.6 (#4), GPT-5.6 Terra: 81.6 (#12)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Terra |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | 86% |
| FrontierMath Tier 4 | 87.8% | 70.7% |
| OTIS Mock AIME 2024-2025 | 100% | 99.7% |
| ProofBench | 100% | 74% |
| LMArena Math | 1525 | 1466 |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.6 (#6), GPT-5.6 Terra: 61.2 (#30)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Terra |
|---|---|---|
| SimpleQA Verified | 70.8% | 43.2% |
| LMArena Expert | 1535 | 1492 |
| GPQA Diamond | — | 93.3% |
| Humanity's Last Exam | 46.5% | — |
Multimodal Claude Fable 5.1 leads
Claude Fable 5.1: 53.9 (#4), GPT-5.6 Terra: 47.3 (#11)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Terra |
|---|---|---|
| LMArena Vision | 1318 | 1271 |
| Blueprint-Bench 2 | 41.9% | 30.8% |
| Furniture Assembly | 70% | 54.2% |
| LMArena Document | 1513 | 1472 |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.1 (#3), GPT-5.6 Terra: 54.4 (#44)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Terra |
|---|---|---|
| LMArena Non-English | 1507 | 1439 |
| LMArena Chinese | 1586 | 1513 |
| LMArena French | 1525 | 1471 |
| LMArena German | 1500 | 1460 |
| LMArena Japanese | 1543 | 1457 |
| LMArena Korean | 1534 | 1425 |
| LMArena Russian | 1521 | 1450 |
| LMArena Spanish | 1516 | 1448 |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#6), GPT-5.6 Terra: 76.4 (#40)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Terra |
|---|---|---|
| LMArena Instruction Following | 1517 | 1454 |
Long Context Claude Fable 5.1 leads
Claude Fable 5.1: 46.7 (#20), GPT-5.6 Terra: 44.4 (#68)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Terra |
|---|---|---|
| LMArena Longer Query | 1522 | 1451 |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.2 (#2), GPT-5.6 Terra: 70.2 (#23)
| Benchmark | Claude Fable 5.1 | GPT-5.6 Terra |
|---|---|---|
| LMArena Text | 1510 | 1447 |
| LMArena Creative Writing | 1507 | 1410 |
| EQ-Bench Creative Writing | 2162 | 1855 |
| LMArena Multi-Turn | 1492 | 1449 |
| EQ-Bench 4 | — | 1234 |
Frequently asked questions
Is Claude Fable 5.1 better than GPT-5.6 Terra?
Claude Fable 5.1 is the stronger model overall, scoring 69.0 to 59.2 on the Noometry Index. GPT-5.6 Terra costs 4.4× 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 Terra?
GPT-5.6 Terra is cheaper. It lists at $2 per million input tokens and $12 per million output tokens; Claude Fable 5.1 lists at $10 and $50.
Is Claude Fable 5.1 or GPT-5.6 Terra better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 74.7 versus 57.7 in the Noometry coding category.
Which has the bigger context window?
GPT-5.6 Terra does, with 1.05M tokens against 1M.
How many benchmarks do Claude Fable 5.1 and GPT-5.6 Terra share?
45 benchmarks have published results for both models. Claude Fable 5.1 has 52 scored results on Noometry and GPT-5.6 Terra has 52.