Claude Fable 5.2 vs Claude Opus 4.5
Full profiles: Claude Fable 5.2 (Anthropic) and Claude Opus 4.5 (Anthropic): every benchmark, price and rank.
Updated · Data from 9 sources
As of 9 Nov 2026, Claude Fable 5.2 is ahead of Claude Opus 4.5 on quality (69.4 vs 59.7 on the BenchLeader Index), but Claude Opus 4.5 is 1.6× cheaper at $10.00 vs $16.00 per 1M tokens blended. Claude Fable 5.2 leads in every category we measure both in.
Key facts (as of 9 Nov 2026)
- Claude Fable 5.2 scores 69.4 on the BenchLeader Index and Claude Opus 4.5 scores 59.7 (BenchLeader, 9 Nov 2026).
- Claude Fable 5.2 costs $16.00 per 1M tokens blended (list price, 9 Nov 2026).
- Claude Opus 4.5 costs $10.00 per 1M tokens blended (list price, 9 Nov 2026).
- Of the 5 benchmarks both models have, Claude Fable 5.2 leads 5 (BenchLeader, 9 Nov 2026).
Claude Fable 5.2 benchmarks max Anthropic Claude Opus 4.5 benchmarks thinking 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 61 category score | High |
| Reasoning | Claude Fable 5.2 | 78 vs 57 category score; ARC-AGI-2 92.5% vs 37.6% | High |
| Knowledge | Claude Fable 5.2 | 82 vs 58 category score | High |
| Long documents | Claude Fable 5.2 | 66 vs 63 category score; AA-LCR v1.1 83.3% vs 77.3% | Medium |
| Lowest cost | Claude Opus 4.5 | $10.00 vs $16.00 per 1M blended; agentic coding session $0.400 vs $0.640 | – |
| Fastest first answer | Claude Fable 5.2 | 3.0 s (Claude Fable 5.2 (max)) vs 12.6 s (Claude Opus 4.5 (thinking)) 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) leads on quality: 69.4 vs 59.7.
- Claude Fable 5.2 (max) is stronger in coding, knowledge, long context, reasoning.
- Claude Opus 4.5 (thinking) is stronger in agents & tools, instruction following, maths, multimodal.
- Claude Opus 4.5 (thinking) is 1.6× cheaper ($10.00 vs $16.00 per 1M blended).
At a glance
| Spec | Claude Fable 5.2 | Claude Opus 4.5 |
|---|---|---|
| Developer | Anthropic | Anthropic |
| Released | 9 Nov 2026 | 24 Nov 2025 |
| Context window (tokens) | 1,000,000 | 200,000 |
| Compared at | Claude Fable 5.2 (max) | Claude Opus 4.5 (thinking) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $8.00 / $40.00 / $0.200 | $5.00 / $25.00 / $0.500 |
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 Opus 4.5 (thinking) | Leader |
|---|---|---|---|
| Reasoning | 78.4 | 57.1 | Claude Fable 5.2 |
| Coding | 80.2 | 60.6 | Claude Fable 5.2 |
| Agents & tools | – | 74.8 | not comparable |
| Maths | – | 64.2 | not comparable |
| Knowledge | 81.7 | 58.3 | Claude Fable 5.2 |
| Instruction following | – | 53.2 | not comparable |
| Multimodal | – | 57.0 | not comparable |
| Long context | 66.4 | 63.3 | Claude Fable 5.2 |
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 5 benchmarks both have, Claude Fable 5.2 leads 5, Claude Opus 4.5 leads 0. Every overall index that rates both puts Claude Fable 5.2 ahead.
| Overall index | Claude Fable 5.2 (max) | Claude Opus 4.5 (thinking) | Leader |
|---|---|---|---|
| BenchLeader Index | 69.4 | 59.7 | 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 Opus 4.5 (thinking) |
|---|---|---|
| Blended price per 1M tokens | $16.00 | $10.00 |
| Input / output per 1M | $8.00 / $40.00 | $5.00 / $25.00 |
| Cached input per 1M | $0.200 | $0.500 |
| Price per task: chat reply | $0.015 | $0.0095 |
| Price per task: summarize a 30-page report | $0.120 | $0.075 |
| Price per task: code edit | $0.108 | $0.068 |
| Price per task: agentic coding session | $0.640 | $0.400 |
| Price per task: structured extraction | $0.024 | $0.015 |
| Agentic coding session, input mostly cached | $0.289 | $0.198 |
| Cost per benchmark task (AA Index) | $26.54 | – |
| Output tokens per task (AA Index) | 274k | – |
| Of which reasoning | 193k | – |
| Output speed | 72 tok/s | 67 tok/s |
| Time to first answer | 3.0 s | 12.6 s |
| Time to a complete answer | – | 65.0 s |
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 Opus 4.5 (thinking) scores 59.7 and takes 13 s to its first answer token; Claude Opus 4.5 (high) scores 59.0 in 1 s, Claude Opus 4.5 scores 57.9 in 1 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
150 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 Opus 4.5 (thinking) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 69.4 | 59.7 |
| Coding score | BenchLeader | 80.2 | 60.6 |
| Knowledge score | BenchLeader | 81.7 | 58.3 |
| Long context score | BenchLeader | 66.4 | 63.3 |
| Reasoning score | BenchLeader | 78.4 | 57.1 |
| Agents & tools score | BenchLeader | – | 74.8 |
| Instruction following score | BenchLeader | – | 53.2 |
| Maths score | BenchLeader | – | 64.2 |
| Multimodal score | BenchLeader | – | 57.0 |
| Blended price $/M | BenchLeader | $16.00 | $10.00 |
| Output speed | BenchLeader | 72 tok/s | 67 tok/s |
| Time to first answer | BenchLeader | 3.0 s | 12.6 s |
| Context window | BenchLeader | 1,000,000 tokens | 200,000 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | – | 86.0%† |
| Humanity's Last Exam | Scale AI / CAIS | – | 25.2%† |
| SimpleBench | SimpleBench | – | 62.0%† |
| Arena Hard Prompts | Arena (LMArena) | – | 1498† |
| LiveBench 2.0 Reasoning | LiveBench | 88.8%† | – |
| LiveBench 1.0 Reasoning | LiveBench | – | 80.1%† |
| GPQA Diamond (AA) | Artificial Analysis | – | 86.6% |
| Humanity's Last Exam (AA) | Artificial Analysis | 74.3% | 30.1% |
| HLE-Diamond (AA) | Artificial Analysis | 80.2% | – |
| GPQA Diamond (Vals) | Vals AI | – | 85.9% |
| Kagi LLM Benchmark | Kagi LLM Benchmark | – | 80.2% |
| ARC-AGI-1 | ARC Prize | 97.5% | 80.0% |
| ARC-AGI-2 | ARC Prize | 92.5% | 37.6% |
| ARC-AGI-3 | ARC Prize | 94.9% | – |
| CritPt | Artificial Analysis | 35.4% | 4.6% |
| CritPt v2 hard subset (AA) | Artificial Analysis | 76.5% | – |
| MysteryMechanism | Vals AI | 51.8%† | – |
| SciPredict | Scale AI SEAL | – | 23.1%† |
| Chess Puzzles | Epoch AI Benchmarking Hub | – | 14.0%† |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | – | 22.0%† |
| CL-bench | Epoch AI Benchmarking Hub | – | 21.1%† |
| LMCA | Epoch AI Benchmarking Hub | – | 44.5%† |
| DTBench | Epoch AI Benchmarking Hub | – | 89.9%† |
| ForecastBench | ForecastBench | – | 64.9%† |
| Coding | |||
| SWE-bench Verified (Epoch) | Epoch AI Benchmarking Hub | – | 76.7%† |
Show all 150 benchmarks
| Metric | Publisher | Claude Fable 5.2 (max) | Claude Opus 4.5 (thinking) |
|---|---|---|---|
| Coding | |||
| WeirdML | WeirdML | – | 63.7%† |
| GSO-Bench | GSO-Bench | – | 26.5%† |
| Arena Coding | Arena (LMArena) | – | 1523† |
| Arena WebDev | Arena (LMArena) | – | 1469† |
| LiveBench 2.0 Coding | LiveBench | 79.2%† | – |
| LiveBench 1.0 Coding | LiveBench | – | 79.7%† |
| SciCode (AA) | Artificial Analysis | 67.7% | – |
| LiveCodeBench | Vals AI | – | 83.7% |
| SWE-bench (Vals) | Vals AI | – | 76.4% |
| SWE-Bench Pro | Scale AI SEAL | – | 45.9%† |
| SWE-bench Verified (bash only) | SWE-bench | – | 76.8%† |
| SWE-bench Verified (any scaffold) | SWE-bench | – | 79.2%† |
| Code Migration v1.1 | Vals AI | 83.3%† | – |
| ProgramBench | Vals AI | 19.0%† | – |
| SWE-bench Multimodal | Vals AI | 62.3%† | – |
| Vibe Code Bench v1.1 | Vals AI | 93.8%† | 20.6% |
| SWE-Bench Pro (private) | Scale AI SEAL | – | 45.9%† |
| ALE-Bench | Epoch AI Benchmarking Hub | – | 1025.4† |
| AlgoTune | AlgoTune | – | 1.8† |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 59.6% | – |
| GameBench 2 Overall | DuelLab GameBench 2 | – | 47.0† |
| Design Arena Website | Design Arena | – | 1244† |
| FrontierCode 1.1 (AA) | Artificial Analysis | 56.2% | – |
| FrontierCode 2.0 (AA) | Artificial Analysis | 48.8% | – |
| LiveCodeBench (AA) | Artificial Analysis | – | 87.1% |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | – | 63.1%† |
| GDPval | OpenAI | – | 45.5%† |
| Cybench | Cybench | – | 82.0%† |
| Remote Labor Index | Scale AI / CAIS | – | 3.8%† |
| LiveBench Long Agentic | LiveBench | 82.9%† | – |
| LiveBench Browser | LiveBench | 86.9%† | – |
| LiveBench Agentic Coding | LiveBench | – | 39.7%† |
| Terminal-Bench Hard | Artificial Analysis | – | 47.0% |
| τ²-Bench Telecom (AA) | Artificial Analysis | – | 89.5% |
| MCP Atlas | Scale AI SEAL | – | 69.8%† |
| BFCL Overall | Berkeley Function Calling Leaderboard | – | 77.5%† |
| τ²-bench | τ²-bench | – | 85.3%† |
| τ³-bench Banking | τ²-bench | – | 24.7%† |
| GDPval-AA v2.1 | Artificial Analysis | 1831 | – |
| Finance Agent v2.1 | Vals AI | 69.5%† | – |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 5.0%† | – |
| Legal Research Bench | Vals AI | 46.1%† | – |
| Poker Agent | Vals AI | – | 1033.4%† |
| Tax Agent Bench | Vals AI | 32.1%† | – |
| Terminal-Bench 2.0 (Vals) | Vals AI | – | 53.9% |
| Terminal-Bench 4.0 (Vals) | Vals AI | 65.2%† | – |
| Terminal-Bench Science | Vals AI | 55.7%† | – |
| Arena Search | Arena (LMArena) | – | 1186† |
| BALROG | BALROG | – | 43.0%† |
| DeepResearch Bench | DeepResearch Bench | – | 54.8%† |
| METR Time Horizons | METR | – | 75.0%† |
| Vending-Bench 2 | Andon Labs | – | 4967.1† |
| AutomationBench | Artificial Analysis | 76.4% | – |
| GDP.pdf (AA) | Artificial Analysis | 24.2% | – |
| Harvey LAB-AA v1.1 | Harvey | 7.2% | – |
| AA-Briefcase v1.1 | Artificial Analysis | 1785 | – |
| Design Arena Agentic | Design Arena | – | 1151† |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 73.3% | – |
| DeepSearchQA | – | 24.0% | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | – | 34.4%† |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | – | 4.9%† |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | – | 86.1%† |
| ProofBench | Vals AI | – | 36.0%† |
| LiveBench Mathematics | LiveBench | – | 90.4%† |
| AIME (Vals) | Vals AI | – | 95.4% |
| MGSM | Vals AI | – | 95.2% |
| Arena Maths | Arena (LMArena) | – | 1463† |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | – | 45.7%† |
| LiveBench 2.0 Data Analysis | LiveBench | 81.5%† | – |
| LiveBench Research | LiveBench | 94.5%† | – |
| LiveBench 1.0 Data Analysis | LiveBench | – | 74.4%† |
| AA-Omniscience v1.1 | Artificial Analysis | 66.8 | – |
| MMLU-Pro | Vals AI | – | 87.3% |
| LegalBench | Vals AI | – | 84.6% |
| CorpFin | Vals AI | – | 65.1% |
| TaxEval | Vals AI | – | 74.9% |
| MedQA | Vals AI | – | 95.9% |
| PRBench Finance | Scale AI SEAL | – | 46.2% |
| PRBench Legal | Scale AI SEAL | – | 44.2% |
| MultiNRC | Scale AI SEAL | – | 48.6% |
| BioMysteryBench | Vals AI | 83.7%† | – |
| CaseLaw v2 | Vals AI | – | 62.6% |
| Excel Modeling Benchmark v1.1 | Vals AI | 77.4%† | – |
| MedCode | Vals AI | – | 49.2% |
| MedScribe | Vals AI | – | 85.3% |
| EBR-bench | Epoch AI Benchmarking Hub | – | 14.3%† |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 79.1% | – |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 40.7% | – |
| Global-MMLU-Lite (AA) | Artificial Analysis | – | 91.3% |
| HealthBench Professional (AA) | OpenAI | 67.7% | – |
| Instruction following | |||
| LiveBench Language | LiveBench | – | 81.3%† |
| LiveBench Instruction Following | LiveBench | – | 62.5%† |
| IFBench | Artificial Analysis | – | 58.0% |
| MultiChallenge | Scale AI SEAL | – | 59.0% |
| TutorBench | Scale AI SEAL | – | 51.2% |
| Arena Instruction Following | Arena (LMArena) | – | 1474† |
| Human preference | |||
| Arena Text | Arena (LMArena) | – | 1470† |
| Arena Creative Writing | Arena (LMArena) | – | 1461† |
| Arena Multi-turn | Arena (LMArena) | – | 1484† |
| Arena Longer Queries | Arena (LMArena) | – | 1492† |
| Multimodal | |||
| LiveBench Design | LiveBench | 85.1%† | – |
| MMMU-Pro | Artificial Analysis | – | 74.0% |
| VISTA | Scale AI SEAL | – | 46.4% |
| MMMU (validation) | MMMU | – | 80.7%† |
| MMMU-Pro (official) | MMMU | – | 73.9%† |
| MMMU-Pro (Vals) | Vals AI | – | 83.0% |
| MortgageTax | Vals AI | – | 67.7% |
| GeoBench | GeoBench | – | 75.0%† |
| VPCT | Epoch AI Benchmarking Hub | – | 40.0%† |
| AA-3D | Artificial Analysis | 1271 | – |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 83.3% | 77.3% |
| Arena Document | Arena (LMArena) | – | 1468† |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | – | 151.8† |
| LiveBench 2.0 | LiveBench | 84.9%† | – |
| LiveBench 1.0 | LiveBench | – | 72.6%† |
| AA Intelligence Index v5.0 | Artificial Analysis | 64.6 | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | – | 29.1 |
| AA Progress Index v1 | Artificial Analysis | – | 284.4 |
| Vals Index | Vals AI | 71.3† | – |
| Vals Finance Index | Vals AI | 63.6%† | – |
| Vals RSI Index | Vals AI | – | 14.8%† |
| Vals Science Index | Vals AI | 63.7%† | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | – | 9.6% |
| MASK | Scale AI SEAL | – | 92.5% |
| Metadata | |||
| AA Openness Index | Artificial Analysis | – | 11.1 |
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 Opus 4.5 (thinking): BenchLeader Index 60.1 → 59.6.
- Claude Opus 4.5 (thinking): 1 new result (AA Progress Index v1).
- Claude Opus 4.5 (thinking): 1 new result (Global-MMLU-Lite (AA)).
- Claude Opus 4.5 (thinking): 1 new result (PRBench Legal).
- Claude Opus 4.5 (thinking): 2 new results (PRBench Legal, MultiNRC).
- Claude Opus 4.5 (thinking): 1 new result (PRBench Finance).
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 Opus 4.5 vs Claude Opus 5.5
- Claude Opus 4.5 vs Gemini 4 Carbon
- Claude Opus 4.5 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 agents · Best cheap LLMs
Claude Fable 5.2 vs Claude Opus 4.5: questions
- Is Claude Fable 5.2 better than Claude Opus 4.5?
- Claude Fable 5.2 (max) leads on quality: 69.4 vs 59.7. The BenchLeader Index combines every independent quality benchmark; Claude Fable 5.2 (max) is ahead overall as of 9 Nov 2026, but check the category scores for your use.
- Claude Fable 5.2 vs Claude Opus 4.5: which is cheaper, and will that change?
- Claude Opus 4.5 is cheaper today: $10.00 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 Opus 4.5 better for coding?
- Claude Fable 5.2 scores higher in coding (80 vs 61 on the category index, where 50 is average).
- Which is faster, Claude Fable 5.2 or Claude Opus 4.5?
- Claude Fable 5.2 streams faster (72 vs 67 output tokens per second, Artificial Analysis 7-day median).
- Which is better for long documents?
- Claude Fable 5.2 scores higher on long-context benchmarks (66 vs 63). Claude Fable 5.2 accepts more context: 1,000,000 against 200,000 tokens for Claude Opus 4.5.
More questions (3)
- Which has lower latency?
- Claude Fable 5.2 answers first: 3.0 s against 12.6 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 Opus 4.5?
- Across the 5 benchmarks both have, Claude Fable 5.2 leads 5, Claude Opus 4.5 leads 0. 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.