Is Claude Fable 5.2 state of the art?Yes.SOTA in Coding › Web dev (tied).
As of Nov 22, 2026, Claude Fable 5.2 is tied for state of the art in Coding › Web dev (since Nov 11, 2026; sources LMArena WebDev; methodology v1.0). Claude Fable 5.2 is tied for SOTA in Coding › Web dev with Claude Opus 5.5, within the margin of error, since 2026-11-11.
Facts and scores
Claude Fable 5.2 is a closed-weights text, image and file model from Anthropic, listed on GPQA Diamond since Nov 9, 2026; no public parameter count, a 1,000K-token context window and $16.00 per 1M tokens blended.
How it scores
- On LMArena WebDev it scores 1824 (CI 1808–1839), #1 of 165 (top 1%); Claude Opus 5.5 is 5 below.
- On Vibe Code Bench it scores 93.8 (CI 91.5–96.0), #1 of 107 (top 1%); Claude Sonnet 5.5 is 1.4 below.
- On LMArena Vision (style-controlled) it scores 1305 (CI 1287–1323), #2 of 193 (top 2%); 4 behind Claude Fable 5; Claude Fable 5 is 4 above and Claude Opus 4.7 Thinking is 4 below.
History
First result on isitsota: Nov 9, 2026. Best overall rank so far: #1 in Coding › Web dev, first held Nov 11, 2026. Crown intervals: Coding › Web dev Nov 11, 2026–now.
The ruling, in plain English
Close in General LLM: rank #5, 3.5 percentile points behind the leader.
Evidence
| Source | Score | Date | Type | Receipt |
|---|---|---|---|---|
| LMArena Text (style-controlled, overall) Claude Fable 5.2 (Max) | 1503 1494–1512 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Text (style-controlled, hard prompts) Claude Fable 5.2 (Max) | 1517 1506–1528 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| MysteryMechanism anthropic/claude-fable-5-2 · Source: Vals AI | 51.8 45.2–58.4 | 2026-11-21 | INDEP. | snap_vals_54c41eb6660d |
| Code Migration anthropic/claude-fable-5-2 · Source: Vals AI | 83.3 77.2–89.4 | 2026-11-21 | INDEP. | snap_vals_f14fde123120 |
| LMArena WebDev Claude Fable 5.2 (xHigh) | 1824 1808–1839 | 2026-11-20 | INDEP. | snap_2f4a3ebc7e46 |
| LMArena Text (style-controlled, longer query) Claude Fable 5.2 (Max) | 1518 1504–1532 | 2026-11-19 | INDEP. | snap_280a9b5ca493 |
| LMArena Vision (style-controlled) Claude Fable 5.2 (Max) | 1305 1287–1323 | 2026-11-19 | INDEP. | snap_71563b13a9cc |
| LMArena Text factuality Claude Fable 5.2 (Max) | 1483 1476–1490 | 2026-11-19 | INDEP. | snap_275d95909246 |
| ARC-AGI claude-fable-5-2_xhigh · xhigh | 98.5% | 2026-11-09 | INDEP. | snap_b23439388aa3 |
| Finance Agent anthropic/claude-fable-5-2 · Source: Vals AI | 69.5 65.6–73.3 | 2026-11-21 | INDEP. | snap_vals_f9cfcd576758 |
| Legal Research Bench anthropic/claude-fable-5-2 · Source: Vals AI | 46.2 39.4–52.9 | 2026-11-21 | INDEP. | snap_vals_e4530282a8b5 |
Rows marked Vals AI come from Vals AI's proprietary benchmarks, republished with permission. Each receipt links to the benchmark on Vals.
Where it sits in the succession
Where it is not the crown
| Category | This model | Rank | Leader |
|---|---|---|---|
| General LLM | Near-SOTA | #5 | Gemini 4 Carbon |
| Reasoning | #10 in this category | #10 | Gemini 4 Carbon |
| Science | #2 in this category | #2 | GPT-6.2 Astra |
| Coding | Near-SOTA | #2 | Claude Sonnet 5.5 |
| Long context | Near-SOTA | #5 | Gemini 4 Argon |
| Vision | Not enough data | — | — |
| Factuality | #13 in this category | #13 | Gemini 4 Carbon |
| Abstraction (ARC) | #1 in this category | #1 | GPT-6.2 Astra |
Related pages
- General LLM
- Reasoning
- Science
- Coding
- Coding › Web dev
- Long context
- Vision
- Factuality
- Abstraction (ARC)
- Finance
- Legal
- Compare with the current leader in General LLM: Gemini 4 Carbon
- Compare with the current leader in General LLM: Gemini 4 Argon
- Compare with the current leader in General LLM: Muse Wonder
- Compare with the current leader in Reasoning: Gemini 4 Carbon
- Compare with the current leader in Reasoning: Gemini 4 Argon
- Compare with the current leader in Reasoning: Gemini 4 Neon
- Compare with the current leader in Coding: Claude Sonnet 5.5
- Compare with the current leader in Coding: Claude Opus 5.5
- Compare with the current leader in Coding: Kimi K3.1 Pro
- Compare with the current leader in Coding › Web dev: Claude Opus 5.5
- Compare with the current leader in Long context: Gemini 4 Argon
- Compare with the current leader in Long context: Gemini 4 Carbon
- Compare with the current leader in Long context: Gemini 4 Neon
- Compare with the current leader in Factuality: Gemini 4 Carbon
- Compare with the current leader in Factuality: Gemini 4 Neon
- Claude Fable 5.2 vs Claude Fable 5
- Claude Fable 5.2 vs Claude Opus 5
- Claude Fable 5.2 vs Gemini 3.8 Flash
- ARC-AGI
- Code Migration
- MysteryMechanism
- Finance Agent
- Legal Research Bench
- LMArena WebDev
- LMArena Text (style-controlled, overall)
- LMArena Text (style-controlled, hard prompts)
- LMArena Text (style-controlled, longer query)
- LMArena Vision (style-controlled)
- LMArena Text factuality
- Lab: Anthropic
- Crown change in November 2026 recap
Is Claude Fable 5.2 SOTA?
As of Nov 22, 2026, Claude Fable 5.2 is tied for state of the art in Coding › Web dev (since Nov 11, 2026; sources LMArena WebDev; methodology v1.0).
What is Claude Fable 5.2 best at?
As of Nov 22, 2026, Claude Fable 5.2 is tied for state of the art in Coding › Web dev (since Nov 11, 2026; sources LMArena WebDev).
How does Claude Fable 5.2 rank in Coding?
Best current rank: #2 in Coding, as of Nov 22, 2026.