Claude Fable 5.2 vs Claude Sonnet 5.5
Full profiles: Claude Fable 5.2 (Anthropic) and Claude Sonnet 5.5 (Anthropic): every benchmark, price and rank.
Updated · Data from 10 sources
As of 9 Nov 2026, Claude Fable 5.2 and Claude Sonnet 5.5 are neck and neck on quality (69.4 vs 65.0 on the BenchLeader Index, inside the ±6.5 margin), and Claude Sonnet 5.5 is 4.0× cheaper at $4.00 vs $16.00 per 1M tokens blended. Claude Fable 5.2 leads in every category we measure both in. Claude Sonnet 5.5 streams ~2× faster.
Key facts (as of 9 Nov 2026)
- Claude Fable 5.2 scores 69.4 on the BenchLeader Index and Claude Sonnet 5.5 scores 65.0 (BenchLeader, 9 Nov 2026).
- Claude Fable 5.2 costs $16.00 per 1M tokens blended (list price, 9 Nov 2026).
- Claude Sonnet 5.5 costs $4.00 per 1M tokens blended (list price, 9 Nov 2026).
- Claude Sonnet 5.5 streams ~2× faster than Claude Fable 5.2 (Artificial Analysis, 7-day median, 9 Nov 2026).
- Of the 21 benchmarks both models have, Claude Fable 5.2 leads 16 (BenchLeader, 9 Nov 2026).
Claude Fable 5.2 benchmarks max Anthropic Claude Sonnet 5.5 benchmarks max AnthropicAdd a third modelWhich to pick for…
The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.
| Use case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | Claude Fable 5.2 | 80 vs 72 category score; FrontierCode 2.0 (AA) 48.8% vs 41.7% | High |
| Reasoning | Claude Fable 5.2 | 78 vs 68 category score; HLE-Diamond (AA) 80.2% vs 53.3% | High |
| Knowledge | Claude Fable 5.2 | 82 vs 58 category score; AA-Omniscience v1.1 66.8 vs 30.5 | High |
| Long documents | Either | 66 vs 66 category score; AA-LCR v1.1 83.3% vs 82.7% | Either |
| Lowest cost | Claude Sonnet 5.5 | $4.00 vs $16.00 per 1M blended; agentic coding session $0.160 vs $0.640 | – |
| Fastest first answer | Claude Fable 5.2 | 3.0 s (Claude Fable 5.2 (max)) vs 288.8 s (Claude Sonnet 5.5 (max)) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Claude Fable 5.2 (max) and Claude Sonnet 5.5 (max) are neck and neck on quality (69.4 vs 65.0, within the ±6.5 margin).
- Claude Fable 5.2 (max) is stronger in coding, knowledge, long context, reasoning.
- Claude Sonnet 5.5 (max) is stronger in agents & tools, maths.
- Claude Sonnet 5.5 (max) is 4.0× cheaper ($4.00 vs $16.00 per 1M blended).
- Claude Sonnet 5.5 (max) streams 2.1× faster (152 vs 72 tokens per second).
At a glance
| Spec | Claude Fable 5.2 | Claude Sonnet 5.5 |
|---|---|---|
| Developer | Anthropic | Anthropic |
| Released | 9 Nov 2026 | 28 Sep 2026 |
| Context window (tokens) | 1,000,000 | 1,000,000 |
| Compared at | Claude Fable 5.2 (max) | Claude Sonnet 5.5 (max) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $8.00 / $40.00 / $0.200 | $2.00 / $10.00 / $0.100 |
Category by category
Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.
| Category | Claude Fable 5.2 (max) | Claude Sonnet 5.5 (max) | Leader |
|---|---|---|---|
| Reasoning | 78.4 | 68.0 | Claude Fable 5.2 |
| Coding | 80.2 | 71.5 | Claude Fable 5.2 |
| Agents & tools | – | 71.3 | not comparable |
| Maths | – | 72.0 | not comparable |
| Knowledge | 81.7 | 58.0 | Claude Fable 5.2 |
| Long context | 66.4 | 66.1 | level |
On one chart
Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.
Not drawn, measured for fewer than two of these models: Agents & tools, Maths, Instruction following, Multimodal, Human preference.
Where sources disagree
Across the 21 benchmarks both have, Claude Fable 5.2 leads 16, Claude Sonnet 5.5 leads 5. Every overall index that rates both puts Claude Fable 5.2 ahead.
| Overall index | Claude Fable 5.2 (max) | Claude Sonnet 5.5 (max) | Leader |
|---|---|---|---|
| BenchLeader Index | 69.4 | 65.0 | neck and neck |
| AA Intelligence Index v5.0 | 64.6 | 54.5 | Claude Fable 5.2 |
| Vals Index | 71.3† | 70.8 | Claude Fable 5.2 |
Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).
Price, speed and latency
List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.
| Measure | Claude Fable 5.2 (max) | Claude Sonnet 5.5 (max) |
|---|---|---|
| Blended price per 1M tokens | $16.00 | $4.00 |
| Input / output per 1M | $8.00 / $40.00 | $2.00 / $10.00 |
| Cached input per 1M | $0.200 | $0.100 |
| Price per task: chat reply | $0.015 | $0.0038 |
| Price per task: summarize a 30-page report | $0.120 | $0.030 |
| Price per task: code edit | $0.108 | $0.027 |
| Price per task: agentic coding session | $0.640 | $0.160 |
| Price per task: structured extraction | $0.024 | $0.0060 |
| Agentic coding session, input mostly cached | $0.289 | $0.074 |
| Cost per benchmark task (AA Index) | $26.54 | $10.02 |
| Output tokens per task (AA Index) | 274k | 285k |
| Of which reasoning | 193k | 206k |
| Time per task (AA Index) | – | 31 min |
| Output speed | 72 tok/s | 152 tok/s |
| Time to first answer | 3.0 s | 288.8 s |
| Time to a complete answer | – | 569.9 s |
Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $26.54 on Claude Fable 5.2 (max) and $10.02 on Claude Sonnet 5.5 (max), and Claude Sonnet 5.5 (max) wrote 1.0× as many output tokens for the same work.
Each model is compared at its best-ranked reasoning-effort setting. Claude Fable 5.2 (max) scores 69.4 and takes 3 s to its first answer token; Claude Fable 5.2 (high) scores 68.9 in 3 s, Claude Fable 5.2 (xhigh) scores 68.7 in 3 s. Claude Sonnet 5.5 (max) scores 65.0 and takes 289 s to its first answer token; Claude Sonnet 5.5 (xhigh) scores 62.7 in 27 s, Claude Sonnet 5.5 (high) scores 58.0 in 9 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.
Every benchmark
116 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.
| Metric | Publisher | Claude Fable 5.2 (max) | Claude Sonnet 5.5 (max) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 69.4 | 65.0 |
| Coding score | BenchLeader | 80.2 | 71.5 |
| Knowledge score | BenchLeader | 81.7 | 58.0 |
| Long context score | BenchLeader | 66.4 | 66.1 |
| Reasoning score | BenchLeader | 78.4 | 68.0 |
| Agents & tools score | BenchLeader | – | 71.3 |
| Maths score | BenchLeader | – | 72.0 |
| Blended price $/M | BenchLeader | $16.00 | $4.00 |
| Output speed | BenchLeader | 72 tok/s | 152 tok/s |
| Time to first answer | BenchLeader | 3.0 s | 288.8 s |
| Context window | BenchLeader | 1,000,000 tokens | 1,000,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | – | 95.6% |
| Humanity's Last Exam | Scale AI / CAIS | – | 46.1%† |
| Arena Hard Prompts | Arena (LMArena) | – | 1498† |
| LiveBench 2.0 Reasoning | LiveBench | 88.8%† | 91.6%† |
| LiveBench 1.0 Reasoning | LiveBench | – | 91.6% |
| Humanity's Last Exam (AA) | Artificial Analysis | 74.3% | 55.0% |
| HLE-Diamond (AA) | Artificial Analysis | 80.2% | 53.3% |
| ARC-AGI-1 | ARC Prize | 97.5% | 96.5% |
| ARC-AGI-2 | ARC Prize | 92.5% | 83.9%† |
| ARC-AGI-3 | ARC Prize | 94.9% | 72.4%† |
| CritPt | Artificial Analysis | 35.4% | 31.4% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 76.5% | 59.0% |
| MysteryMechanism | Vals AI | 51.8%† | 49.1%† |
| Chess Puzzles | Epoch AI Benchmarking Hub | – | 59.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 65.0% |
| LMCA | Epoch AI Benchmarking Hub | – | 68.3% |
| DTBench | Epoch AI Benchmarking Hub | – | 97.3% |
| Coding | |||
| SciCode | SciCode | – | 61.0% |
| FrontierCode | Cognition | – | 52.1%† |
| Arena Coding | Arena (LMArena) | – | 1517† |
| Arena WebDev | Arena (LMArena) | – | 1774† |
| LiveBench 2.0 Coding | LiveBench | 79.2%† | 77.2%† |
| LiveBench 1.0 Coding | LiveBench | – | 91.4% |
| SciCode (AA) | Artificial Analysis | 67.7% | 61.0% |
| IOI | Vals AI | – | 83.1%† |
Show all 116 benchmarks
| Metric | Publisher | Claude Fable 5.2 (max) | Claude Sonnet 5.5 (max) |
|---|---|---|---|
| Coding | |||
| Code Migration | Vals AI | – | 69.8%† |
| Code Migration v1.1 | Vals AI | 83.3%† | 86.9%† |
| ProgramBench | Vals AI | 19.0%† | 6.5%† |
| SWE-bench Multimodal | Vals AI | 62.3%† | 58.3%† |
| Vibe Code Bench v1.1 | Vals AI | 93.8%† | 92.4%† |
| CursorBench | Cursor | – | 55.5% |
| ALE-Bench | Epoch AI Benchmarking Hub | – | 1819.1† |
| FrontierSWE | Epoch AI Benchmarking Hub | – | 61.9% |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 59.6% | 63.6% |
| Startrise Frontend | Startrise | – | 75.9%† |
| GameBench 2 Overall | DuelLab GameBench 2 | – | 60.4† |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | – | 91.3† |
| Design Arena Website | Design Arena | – | 1315† |
| FrontierCode 1.1 (AA) | Artificial Analysis | 56.2% | 45.8% |
| FrontierCode 2.0 (AA) | Artificial Analysis | 48.8% | 41.7% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | – | 63.9% |
| APEX-Agents | Mercor | – | 75.5% |
| Arena Agent | Arena (LMArena) | – | 16 |
| LiveBench Long Agentic | LiveBench | 82.9%† | 63.4%† |
| LiveBench Browser | LiveBench | 86.9%† | 89.3%† |
| LiveBench Agentic Coding | LiveBench | – | 56.3% |
| Terminal-Bench 2.1 (Vals) | Vals AI | – | 83.2%† |
| GDPval-AA v2.1, normalised score | Artificial Analysis | – | 66.9% |
| GDPval-AA v2.1 | Artificial Analysis | 1831 | 1838 |
| Analyst Agent (AA) | Artificial Analysis | – | 57.5% |
| CyberBench | Vals AI | – | 59.6%† |
| Finance Agent v2 | Vals AI | – | 58.1%† |
| Finance Agent v2.1 | Vals AI | 69.5%† | 67.3%† |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 5.0%† | 10.4%† |
| Harvey's Legal Agent Benchmark v1 | Vals AI | – | 2.9%† |
| Legal Research Bench | Vals AI | 46.1%† | 48.1%† |
| SREBench | Vals AI | – | 30.1%† |
| Tax Agent Bench | Vals AI | 32.1%† | 42.0%† |
| Terminal-Bench 4.0 (Vals) | Vals AI | 65.2%† | 64.1%† |
| Terminal-Bench Science | Vals AI | 55.7%† | 47.1%† |
| Vending-Bench 2 | Andon Labs | – | 11165.3† |
| AutomationBench | Artificial Analysis | 76.4% | 71.8% |
| GDP.pdf (AA) | Artificial Analysis | 24.2% | 25.8% |
| Harvey LAB-AA v1.1 | Harvey | 7.2% | 2.8% |
| AA-Briefcase v1.1 | Artificial Analysis | 1785 | 1813 |
| GDPx | GDPx by SemiAnalysis | – | 8.2% |
| Design Arena Agentic | Design Arena | – | 1283† |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 73.3% | 53.3% |
| FACTS Search | – | 86.8%† | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | – | 88.8% |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | – | 80.5% |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | – | 100.0% |
| ProofBench | Vals AI | – | 100.0% |
| LiveBench Mathematics | LiveBench | – | 96.1% |
| Arena Maths | Arena (LMArena) | – | 1489† |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | – | 46.5% |
| LiveBench 2.0 Data Analysis | LiveBench | 81.5%† | 59.5%† |
| LiveBench Research | LiveBench | 94.5%† | 88.0%† |
| LiveBench 1.0 Data Analysis | LiveBench | – | 59.5% |
| AA-Omniscience v1.1 | Artificial Analysis | 66.8 | 30.5 |
| BioMysteryBench | Vals AI | 83.7%† | 81.1%† |
| ClaimBench | Vals AI | – | 100.0%† |
| Excel Modeling Benchmark | Vals AI | – | 75.7%† |
| Excel Modeling Benchmark v1.1 | Vals AI | 77.4%† | 75.9%† |
| MedCode | Vals AI | – | 52.9%† |
| MedScribe | Vals AI | – | 91.1%† |
| Public Benefits Bench v1.1 | Vals AI | – | 67.2%† |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 31.4% |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 79.1% | 51.5% |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 40.7% | 56.7% |
| HealthBench Professional (AA) | OpenAI | 67.7% | 63.0% |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 78.0% |
| LiveBench Instruction Following | LiveBench | – | 56.8% |
| Arena Instruction Following | Arena (LMArena) | – | 1479† |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1472† |
| Arena Creative Writing | Arena (LMArena) | – | 1465† |
| Arena Multi-turn | Arena (LMArena) | – | 1469† |
| Arena Longer Queries | Arena (LMArena) | – | 1489† |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | – | 1284† |
| LiveBench Design | LiveBench | 85.1%† | 81.3%† |
| SAGE | Vals AI | – | 88.0%† |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | – | 39.3%† |
| Code2Video-AA | Artificial Analysis | – | 1443 |
| AA-3D | Artificial Analysis | 1271 | 1204 |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 83.3% | 82.7% |
| MLCR | Artificial Analysis | – | 41.7% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | – | 166.2† |
| LiveBench 2.0 | LiveBench | 84.9%† | 77.0%† |
| LiveBench 1.0 | LiveBench | – | 75.7% |
| AA Intelligence Index v5.0 | Artificial Analysis | 64.6 | 54.5 |
| AA Intelligence Index v4.3.2 | Artificial Analysis | – | 56 |
| AA Progress Index v1 | Artificial Analysis | – | 350.5 |
| Vals Index | Vals AI | 71.3† | 70.8† |
| Vals Finance Index | Vals AI | 63.6%† | 64.5%† |
| Vals Science Index | Vals AI | 63.7%† | 59.1%† |
| Vals Router Index | Vals AI | – | 69.0%† |
Data as of 2026-11-09. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- Claude Sonnet 5.5 (max): 2 score revisions.
- Claude Sonnet 5.5 (max): 1 score revision.
- Claude Sonnet 5.5 (max): 1 score revision.
- Claude Sonnet 5.5 (max): 1 score revision.
- Claude Sonnet 5.5 (max): 1 new result (MirrorCode).
- Claude Sonnet 5.5 (max): 5 new results (AA Intelligence Index v5.0, AA Progress Index v1, HLE-Diamond (AA)…); 3 score revisions; cost per task moved from $5.46/M to $10.02/M (83% up).
- Claude Sonnet 5.5 (max): 1 score revision.
- Claude Sonnet 5.5 (max): 1 new result (ARC-AGI-1); 1 score revision.
- Claude Sonnet 5.5 (max): 2 new results (LMCA, DTBench).
- Claude Sonnet 5.5 (max): 1 score revision.
Related comparisons
- Claude Fable 5.2 vs Claude Opus 5.5
- Claude Fable 5.2 vs Gemini 4 Carbon
- Claude Fable 5.2 vs GPT-6 Astra
- Claude Sonnet 5.5 vs Claude Opus 5.5
- Claude Sonnet 5.5 vs Gemini 4 Carbon
- Claude Sonnet 5.5 vs GPT-6 Astra
- Claude Fable 5.2 vs Claude Fable 5.1
- Claude Fable 5.2 vs Claude Fable 5
Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs
Claude Fable 5.2 vs Claude Sonnet 5.5: questions
- Is Claude Fable 5.2 better than Claude Sonnet 5.5?
- Claude Fable 5.2 (max) and Claude Sonnet 5.5 (max) are neck and neck on quality (69.4 vs 65.0, within the ±6.5 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 9 Nov 2026, so check the category scores for your use.
- Claude Fable 5.2 vs Claude Sonnet 5.5: which is cheaper, and will that change?
- Claude Sonnet 5.5 is cheaper today: $4.00 against $16.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Is Claude Fable 5.2 or Claude Sonnet 5.5 better for coding?
- Claude Fable 5.2 scores higher in coding (80 vs 72 on the category index, where 50 is average). On FrontierCode 2.0 (AA), the top shared coding benchmark, it is 48.8% for Claude Fable 5.2 against 41.7% for Claude Sonnet 5.5.
- Which is faster, Claude Fable 5.2 or Claude Sonnet 5.5?
- Claude Sonnet 5.5 streams ~2× faster (152 vs 72 output tokens per second, Artificial Analysis 7-day median).
- Which is better for long documents?
- They are level on long-context benchmarks (66 vs 66). Both accept 1,000,000 tokens of context.
More questions (3)
- Which has lower latency?
- Claude Fable 5.2 answers first: 3.0 s against 288.8 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
- Do independent benchmarks agree on Claude Fable 5.2 vs Claude Sonnet 5.5?
- Across the 21 benchmarks both have, Claude Fable 5.2 leads 16, Claude Sonnet 5.5 leads 5. Every overall index that rates both puts Claude Fable 5.2 ahead.
- When was Claude Fable 5.2 released?
- Claude Fable 5.2 was released on 9 Nov 2026.