Model comparison
Claude Fable 5.1 vs GLM-5.2
Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 50.9 on the Noometry Index. GLM-5.2 costs 9.3× less per token, which makes it the better buy when Claude Fable 5.1's lead doesn't matter for your workload.
Last verified . 38 shared benchmarks.
Summary
- They share 38 benchmarks with published results for both. Claude Fable 5.1 scores higher in 9 categories and GLM-5.2 in 0 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Claude Fable 5.1 leads 76.7 to 42.1.
- The biggest single-benchmark swing is ARC-AGI-2: 90% for Claude Fable 5.1 and 22.8% for GLM-5.2.
- GLM-5.2 is cheaper at $1.40 / $4.40 per million input/output tokens, against $10 / $50 for Claude Fable 5.1.
- GLM-5.2 has downloadable open weights; the other is API-only.
Side by side
| Claude Fable 5.1 | GLM-5.2 | |
|---|---|---|
| Provider | Anthropic | Z.ai (Zhipu) |
| Noometry Index | 68.5 | 50.9 |
| Released | 2026-09-01 | 2026-06-13 |
| Weights | Proprietary | Open |
| Context window | 1M | 1M |
| Max output | 128K | 131K |
| Input $ / M tokens | $10 | $1.40 |
| Output $ / M tokens | $50 | $4.40 |
| Results tracked | 50 | 50 |
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), GLM-5.2: 50.9 (#37)
| Benchmark | Claude Fable 5.1 | GLM-5.2 |
|---|---|---|
| FrontierCode | 50.9% | 24.5% |
| LMArena WebDev | 1753 | 1604 |
| SciCode | 63.1% | 50.5% |
| WeirdML | 92.9% | 70.1% |
| LMArena Coding | 1523 | 1484 |
| ALE-Bench | 2,143 | 1,047 |
| SWE-bench Verified | — | 78.7% |
| DeepSWE | — | 43.8% |
| CursorBench | 51.8% | — |
| FrontierSWE | 56.3% | — |
| MirrorCode | 73.3% | — |
Agentic & Tool Use Claude Fable 5.1 leads
Claude Fable 5.1: 50.8 (#5), GLM-5.2: 31.6 (#63)
| Benchmark | Claude Fable 5.1 | GLM-5.2 |
|---|---|---|
| Vending-Bench 2 | 5,422 | 8,314 |
| APEX-Agents | 68.6% | — |
| Remote Labor Index | 17.9% | — |
| τ²-bench Banking | — | 37.1% |
| PostTrainBench | — | 31.7% |
| GBAEval | — | 0% |
| GDP.pdf | 29.6% | — |
Reasoning Claude Fable 5.1 leads
Claude Fable 5.1: 76.7 (#5), GLM-5.2: 42.1 (#46)
| Benchmark | Claude Fable 5.1 | GLM-5.2 |
|---|---|---|
| ARC-AGI-2 | 90% | 22.8% |
| NYT Connections (extended) | 90% | 74.3% |
| ARC-AGI-1 | 97.5% | 77% |
| CritPt | 31.1% | 20.9% |
| Chess Puzzles | 47% | 21% |
| EBR-Bench | 57.1% | 9.5% |
| LMArena Hard Prompts | 1526 | 1480 |
| Mystery Game Puzzles | 58% | 19% |
| DTBench | 97.6% | 93.6% |
| LMCA | 65.5% | 45.8% |
| Epoch Capabilities Index | 165 | 151.76 |
| SimpleBench | — | 58.8% |
| Kagi LLM Benchmark | — | 62.6% |
| Surface Evolver Bench | — | 55.6% |
Math Claude Fable 5.1 leads
Claude Fable 5.1: 89.5 (#3), GLM-5.2: 55.4 (#35)
| Benchmark | Claude Fable 5.1 | GLM-5.2 |
|---|---|---|
| FrontierMath (Tiers 1-3) | 90.2% | 59.2% |
| FrontierMath Tier 4 | 87.8% | 29.3% |
| OTIS Mock AIME 2024-2025 | 100% | 86.4% |
| ProofBench | 100% | 35% |
| LMArena Math | 1519 | 1482 |
| MathArena Final-Answer Competitions | — | 67.6% |
| FrontierMath Erdős | 0% | — |
Knowledge Claude Fable 5.1 leads
Claude Fable 5.1: 69.3 (#5), GLM-5.2: 57.1 (#36)
| Benchmark | Claude Fable 5.1 | GLM-5.2 |
|---|---|---|
| SimpleQA Verified | 70.8% | 34.2% |
| LMArena Expert | 1528 | 1484 |
| GPQA Diamond | — | 91.9% |
| Humanity's Last Exam | 46.5% | — |
Multimodal Not comparable
Claude Fable 5.1: 54.1 (#4), GLM-5.2: —
| Benchmark | Claude Fable 5.1 | GLM-5.2 |
|---|---|---|
| LMArena Vision | 1319 | — |
| Blueprint-Bench 2 | 41.9% | — |
| Furniture Assembly | 70% | — |
| LMArena Document | 1513 | — |
Multilingual Claude Fable 5.1 leads
Claude Fable 5.1: 59.5 (#2), GLM-5.2: 56.0 (#25)
| Benchmark | Claude Fable 5.1 | GLM-5.2 |
|---|---|---|
| LMArena Non-English | 1509 | 1459 |
| LMArena Chinese | 1589 | 1518 |
| LMArena French | 1532 | 1476 |
| LMArena German | 1495 | 1470 |
| LMArena Japanese | 1565 | 1451 |
| LMArena Russian | 1525 | 1467 |
| LMArena Spanish | 1503 | 1477 |
| LMArena Korean | — | 1445 |
Instruction Following Claude Fable 5.1 leads
Claude Fable 5.1: 79.3 (#6), GLM-5.2: 77.1 (#32)
| Benchmark | Claude Fable 5.1 | GLM-5.2 |
|---|---|---|
| LMArena Instruction Following | 1515 | 1465 |
Long Context Claude Fable 5.1 leads
Claude Fable 5.1: 46.8 (#19), GLM-5.2: 45.3 (#43)
| Benchmark | Claude Fable 5.1 | GLM-5.2 |
|---|---|---|
| LMArena Longer Query | 1524 | 1479 |
Writing & Preference Claude Fable 5.1 leads
Claude Fable 5.1: 79.3 (#1), GLM-5.2: 70.7 (#20)
| Benchmark | Claude Fable 5.1 | GLM-5.2 |
|---|---|---|
| LMArena Text | 1511 | 1470 |
| LMArena Creative Writing | 1507 | 1465 |
| EQ-Bench Creative Writing | 2162 | 1757 |
| LMArena Multi-Turn | 1492 | 1468 |
| EQ-Bench 4 | — | 1222 |
Frequently asked questions
Is Claude Fable 5.1 better than GLM-5.2?
Claude Fable 5.1 is the stronger model overall, scoring 68.5 to 50.9 on the Noometry Index. GLM-5.2 costs 9.3× 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 GLM-5.2?
GLM-5.2 is cheaper. It lists at $1.40 per million input tokens and $4.40 per million output tokens; Claude Fable 5.1 lists at $10 and $50.
Is Claude Fable 5.1 or GLM-5.2 better for coding?
Claude Fable 5.1 scores higher on coding benchmarks: 70.5 versus 50.9 in the Noometry coding category.
Which has the bigger context window?
Both accept 1M tokens.
How many benchmarks do Claude Fable 5.1 and GLM-5.2 share?
38 benchmarks have published results for both models. Claude Fable 5.1 has 50 scored results on Noometry and GLM-5.2 has 50.