Claude Fable 5 vs GLM 5.2
Claude Fable 5 
GLM 5.2 Verdict
- Claude Fable 5 leads on quality: 68.8 vs 57.7.
- Claude Fable 5 is stronger in agents & tools, coding, composite, human preference, instruction following, knowledge, long context, multimodal, reasoning.
- GLM 5.2 (max) is stronger in maths.
- GLM 5.2 (max) is 9.3× cheaper ($2.15 vs $20.00 per 1M blended).
| Metric | Claude Fable 5 | GLM 5.2 (max) |
|---|---|---|
| BenchLeader Index | 68.8 | 57.7 |
| Agents & tools score | 73.6 | 56.9 |
| Coding score | 68.7 | 63.8 |
| Composite score | 84.1 | – |
| Human preference score | 71.4 | 67.3 |
| Instruction following score | 59.7 | – |
| Knowledge score | 70.7 | 44.8 |
| Long context score | 65.4 | – |
| Multimodal score | 69.7 | – |
| Reasoning score | 75.8 | 66.8 |
| Maths score | – | 55.8 |
| Blended price $/M | $20.00 | $2.15 |
| Output speed | 63 tok/s | 75 tok/s |
| Time to first answer | 81.4 s | 34.2 s |
| Context window | 1M | 1M |
| GPQA Diamond | – | 91.9% |
| FrontierMath Tiers 1–3 | – | 59.2% |
| FrontierMath Tier 4 | – | 29.3% |
| OTIS Mock AIME | – | 86.4% |
| SWE-bench Verified (Epoch) | – | 78.7% |
| SimpleQA Verified | – | 34.2% |
| SciCode | – | 50.5% |
| Remote Labor Index | 16.1% | – |
| WeirdML | – | 70.1% |
| APEX-Agents | 45.0% | – |
| FrontierCode | 53.5% | – |
| ProofBench | – | 35.0% |
| Epoch Capabilities Index | 163.4 | – |
| LMArena Text | 1506 | 1472 |
| LMArena Hard Prompts | 1532 | 1493 |
| LMArena Coding | 1552 | 1510 |
| LMArena WebDev | 1628 | 1592 |
| LMArena Vision | 1330 | – |
| LMArena Agent | – | 4.6 |
| AA Intelligence Index | 49.7 | – |
| IFBench | 63.5% | – |
| AA-LCR | 82.3% | – |
| AA-Omniscience | 43.3 | – |
| Terminal-Bench Hard | 62.9% | – |
| GPQA Diamond (AA) | 92.6% | – |
| Humanity's Last Exam (AA) | 55.5% | – |
| SciCode (AA) | 61.0% | – |
| τ²-Bench Telecom (AA) | 98.5% | – |
| LiveCodeBench | 89.8% | – |
| MMLU-Pro | 91.5% | – |
| LegalBench | 88.6% | – |
| CorpFin | 71.8% | – |
| TaxEval | 76.9% | – |
| Terminal-Bench 2.1 (Vals) | 80.5% | 67.8% |
| SWE-bench (Vals) | 95.0% | 82.8% |
| GPQA Diamond (Vals) | 93.2% | – |
| Vals Index | 66.0 | – |
| MCP Atlas | 83.3% | – |
| PRBench Finance | 53.9% | – |
| PRBench Legal | 52.6% | – |
| HiL-Bench | 56.3% | – |
| EQ-Bench 4 | 1340 | – |
| Kagi LLM Benchmark | 88.8% | – |
Data as of 2026-09-13. Best configuration of each model; every score links to its source on the model pages.
Claude Fable 5 vs GLM 5.2: questions
- Is Claude Fable 5 better than GLM 5.2?
- Claude Fable 5 leads on quality: 68.8 vs 57.7. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5 is ahead overall as of 2026-09-13, but check the category scores for your use.
- Is Claude Fable 5 better than GLM 5.2 for coding?
- Claude Fable 5 scores higher in coding (69 vs 64 on the category index, where 50 is average).
- Is Claude Fable 5 better than GLM 5.2 for agentic tasks?
- Claude Fable 5 scores higher in agentic tasks (74 vs 57 on the category index, where 50 is average).
- Which is cheaper, Claude Fable 5 or GLM 5.2?
- GLM 5.2 is cheaper: $2.15 against $20.00 per million tokens, blended at three input tokens per output token.
- Which is faster, Claude Fable 5 or GLM 5.2?
- GLM 5.2 streams faster: 75 against 63 output tokens per second.
- Which has the larger context window?
- Both accept 1M tokens of context.