Claude Fable 5.2 vs GPT-6.2 Sol
As of Nov 22, 2026, Claude Fable 5.2 leads GPT-6.2 Sol in 8 of 8 shared categories: General LLM, Reasoning, Science, Coding › Web dev, Long context, Factuality, Abstraction (ARC), and Legal.
Claude Fable 5.2
Yes. SOTA in Coding › Web dev (tied).
GPT-6.2 Sol
Too new. Too new to call. The crown still needs confirming evidence.
| Category | Claude Fable 5.2 | GPT-6.2 Sol |
|---|---|---|
| General LLM | #5 · Near-SOTA · General LLM Margin 3.5087719298245617 LMArena leaderboard dataset · Nov 19, 2026 | #54 · #54 in General LLM Margin 32.163742690058484 LMArena leaderboard dataset · Nov 19, 2026 |
| Reasoning | #10 · #10 in Reasoning Margin 6.470588235294116 LMArena leaderboard dataset · Nov 19, 2026 | #68 · #68 in Reasoning Margin 40.588235294117645 LMArena leaderboard dataset · Nov 19, 2026 |
| Science | #2 · #2 in Science Margin — Vals AI · Nov 21, 2026 | #9 · #9 in Science Margin — Vals AI · Nov 21, 2026 |
| Coding | #2 · Near-SOTA · Coding Margin 2.1235009607102597 Vals AI · Nov 21, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Nov 19, 2026 |
| Coding › Web dev | #1 · Co-SOTA · Coding › Web dev Margin 0 LMArena leaderboard dataset · Nov 20, 2026 | #7 · #7 in Coding › Web dev Margin 5.109489051094897 LMArena leaderboard dataset · Nov 20, 2026 |
| Long context | #5 · Near-SOTA · Long context Margin 3.5294117647058982 LMArena leaderboard dataset · Nov 19, 2026 | #55 · #55 in Long context Margin 32.94117647058823 LMArena leaderboard dataset · Nov 19, 2026 |
| Vision | #— · Not enough data Margin — LMArena leaderboard dataset · Nov 19, 2026 | #— · Not enough data Margin — Epoch AI benchmarking hub · Nov 17, 2026 |
| Factuality | #13 · #13 in Factuality Margin 7.647058823529406 LMArena leaderboard dataset · Nov 19, 2026 | #82 · #82 in Factuality Margin 48.23529411764706 LMArena leaderboard dataset · Nov 19, 2026 |
| Abstraction (ARC) | #1 · #1 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Nov 9, 2026 | #3 · Pending · Abstraction (ARC) Margin — Epoch AI benchmarking hub · Nov 17, 2026 |
| Finance | #1 · #1 in Finance Margin — Vals AI · Nov 21, 2026 | — |
| Legal | #13 · #13 in Legal Margin — Vals AI · Nov 21, 2026 | #26 · #26 in Legal Margin — Vals AI · Nov 21, 2026 |
Pricing
Claude Fable 5.2: $16 per 1M blended tokens.
GPT-6.2 Sol: $4 per 1M blended tokens.
Claude Fable 5.2: closed weights.
GPT-6.2 Sol: closed weights.
Benchmarks side by side
| Benchmark | Claude Fable 5.2 | GPT-6.2 Sol |
|---|---|---|
| ARC-AGI | 98.5% | 97.5% |
| Excel Modeling Benchmark (EMB) | 77.4 | 74.3 |
| Finance Agent | 69.5 | 58.9 |
| GDP.pdf | 51.8% | 48.8% |
| Legal Research Bench | 46.2 | 37.0 |
| LMArena Text (style-controlled, coding) | 1526 | 1506 |
| LMArena Text (style-controlled, hard prompts) | 1517 | 1475 |
| LMArena Text (style-controlled, longer query) | 1518 | 1471 |
| LMArena Text (style-controlled, overall) | 1503 | 1465 |
| LMArena Text factuality | 1483 | 1443 |
| LMArena WebDev | 1824 | 1754 |
| MysteryMechanism | 51.8 | 36.9 |
| Tax Agent Bench | 32.1 | 24.8 |
| Vals Index | 71.3 | 66.1 |
| Vibe Code Bench | 93.8 | 87.6 |
Latest validated result for each model. Benchmarks where only one model has a result are left out.
Verdict
As of Nov 22, 2026, Claude Fable 5.2 leads GPT-6.2 Sol in 8 of 8 shared categories: General LLM, Reasoning, Science, Coding › Web dev, Long context, Factuality, Abstraction (ARC), and Legal.
General LLM: As of Nov 22, 2026, Claude Fable 5.2 leads GPT-6.2 Sol in General LLM at #5 against #54.
Reasoning: As of Nov 22, 2026, Claude Fable 5.2 leads GPT-6.2 Sol in Reasoning at #10 against #68.
Science: As of Nov 22, 2026, Claude Fable 5.2 leads GPT-6.2 Sol in Science at #2 against #9.
Coding › Web dev: As of Nov 22, 2026, Claude Fable 5.2 leads GPT-6.2 Sol in Coding › Web dev at #1 against #7.
Long context: As of Nov 22, 2026, Claude Fable 5.2 leads GPT-6.2 Sol in Long context at #5 against #55.
Factuality: As of Nov 22, 2026, Claude Fable 5.2 leads GPT-6.2 Sol in Factuality at #13 against #82.
Abstraction (ARC): As of Nov 22, 2026, Claude Fable 5.2 leads GPT-6.2 Sol in Abstraction (ARC) at #1 against #3.
Legal: As of Nov 22, 2026, Claude Fable 5.2 leads GPT-6.2 Sol in Legal at #13 against #26.
Claude Fable 5.2 · GPT-6.2 Sol
Claude Fable 5.2 or GPT-6.2 Sol?
As of Nov 22, 2026, Claude Fable 5.2 leads GPT-6.2 Sol in 8 of 8 shared categories: General LLM, Reasoning, Science, Coding › Web dev, Long context, Factuality, Abstraction (ARC), and Legal.
Claude Fable 5.2 or GPT-6.2 Sol for General LLM?
As of Nov 22, 2026, Claude Fable 5.2 leads GPT-6.2 Sol in General LLM at #5 against #54.
Claude Fable 5.2 or GPT-6.2 Sol for Reasoning?
As of Nov 22, 2026, Claude Fable 5.2 leads GPT-6.2 Sol in Reasoning at #10 against #68.
Claude Fable 5.2 or GPT-6.2 Sol for Science?
As of Nov 22, 2026, Claude Fable 5.2 leads GPT-6.2 Sol in Science at #2 against #9.