Claude Fable 5.2 vs Gemini 3.8 Flash
As of Nov 22, 2026, Claude Fable 5.2 leads Gemini 3.8 Flash in 8 of 10 shared categories: General LLM, Science, Coding, Coding › Web dev, Long context, Factuality, Finance, and Legal.
Claude Fable 5.2
Yes. SOTA in Coding › Web dev (tied).
Gemini 3.8 Flash
Yes. Yes on General LLM (best per dollar); Reasoning (best per dollar). Not the overall leader.
| Category | Claude Fable 5.2 | Gemini 3.8 Flash |
|---|---|---|
| General LLM | #5 · Near-SOTA · General LLM Margin 3.5087719298245617 LMArena leaderboard dataset · Nov 19, 2026 | #10 · Was SOTA · General LLM Margin 6.432748538011694 LMArena leaderboard dataset · Nov 19, 2026 |
| Reasoning | #10 · #10 in Reasoning Margin 6.470588235294116 LMArena leaderboard dataset · Nov 19, 2026 | #9 · #9 in Reasoning Margin 5.882352941176464 LMArena leaderboard dataset · Nov 19, 2026 |
| Math | — | #5 · #5 in Math Margin 8.888888888888886 Epoch AI benchmarking hub · Sep 2, 2026 |
| Science | #2 · #2 in Science Margin — Vals AI · Nov 21, 2026 | #9 · #9 in Science Margin — Epoch AI benchmarking hub · Sep 2, 2026 |
| Coding | #2 · Near-SOTA · Coding Margin 2.1235009607102597 Vals AI · Nov 21, 2026 | #33 · #33 in Coding Margin 67.4517988471477 Terminal-Bench Harbor Hub · Nov 21, 2026 |
| Coding › Agentic | — | #24 · #24 in Coding › Agentic Margin 65.11627906976744 Terminal-Bench Harbor Hub · Nov 18, 2026 |
| Coding › Web dev | #1 · Co-SOTA · Coding › Web dev Margin 0 LMArena leaderboard dataset · Nov 20, 2026 | #41 · #41 in Coding › Web dev Margin 29.927007299270073 LMArena leaderboard dataset · Nov 20, 2026 |
| Long context | #5 · Near-SOTA · Long context Margin 3.5294117647058982 LMArena leaderboard dataset · Nov 19, 2026 | #8 · Was SOTA · Long context Margin 5.29411764705884 LMArena leaderboard dataset · Nov 19, 2026 |
| Vision | #— · Not enough data Margin — LMArena leaderboard dataset · Nov 19, 2026 | #— · Not enough data Margin — LMArena leaderboard dataset · Nov 19, 2026 |
| Factuality | #13 · #13 in Factuality Margin 7.647058823529406 LMArena leaderboard dataset · Nov 19, 2026 | #32 · #32 in Factuality Margin 18.82352941176471 LMArena leaderboard dataset · Nov 19, 2026 |
| Abstraction (ARC) | #1 · #1 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Nov 9, 2026 | #1 · #1 in Abstraction (ARC) Margin — Epoch AI benchmarking hub · Sep 2, 2026 |
| Cybersecurity | — | #11 · #11 in Cybersecurity Margin 32.352941176470594 Vals AI · Nov 21, 2026 |
| Finance | #1 · #1 in Finance Margin — Vals AI · Nov 21, 2026 | #30 · #30 in Finance Margin 32.407407407407405 Vals AI · Nov 13, 2026 |
| Legal | #13 · #13 in Legal Margin — Vals AI · Nov 21, 2026 | #22 · #22 in Legal Margin — Vals AI · Nov 21, 2026 |
| Healthcare | — | #31 · #31 in Healthcare Margin — Vals AI · Nov 21, 2026 |
Which is better for coding?
As of Nov 22, 2026, Claude Fable 5.2 leads Gemini 3.8 Flash in Coding at #2 against #33. See the full coding ranking.
Pricing
Claude Fable 5.2: $16 per 1M blended tokens.
Gemini 3.8 Flash: $1.65 per 1M blended tokens.
Claude Fable 5.2: closed weights.
Gemini 3.8 Flash: closed weights.
Benchmarks side by side
| Benchmark | Claude Fable 5.2 | Gemini 3.8 Flash |
|---|---|---|
| ARC-AGI | 98.5% | 98.5% |
| Code Migration | 83.3 | 38.6 |
| Excel Modeling Benchmark (EMB) | 77.4 | 72.9 |
| Finance Agent | 69.5 | 65.8 |
| GDP.pdf | 51.8% | 23.4% |
| GPQA Diamond | 93.9% | 95.4% |
| Legal Research Bench | 46.2 | 38.9 |
| LMArena Text (style-controlled, coding) | 1526 | 1530 |
| LMArena Text (style-controlled, hard prompts) | 1517 | 1518 |
| LMArena Text (style-controlled, longer query) | 1518 | 1510 |
| LMArena Text (style-controlled, overall) | 1503 | 1497 |
| LMArena Text factuality | 1483 | 1469 |
| LMArena Vision (style-controlled) | 1305 | 1293 |
| LMArena WebDev | 1824 | 1584 |
| MysteryMechanism | 51.8 | 36.5 |
| ProofBench | 100 | 48.0 |
| SimpleQA Verified | 94.0% | 69.7% |
| Tax Agent Bench | 32.1 | 32.1 |
| Vals Index | 71.3 | 56.0 |
| Vibe Code Bench | 93.8 | 78.7 |
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 Gemini 3.8 Flash in 8 of 10 shared categories: General LLM, Science, Coding, Coding › Web dev, Long context, Factuality, Finance, and Legal.
General LLM: As of Nov 22, 2026, Claude Fable 5.2 leads Gemini 3.8 Flash in General LLM at #5 against #10.
Reasoning: As of Nov 22, 2026, Gemini 3.8 Flash leads Claude Fable 5.2 in Reasoning at #9 against #10.
Science: As of Nov 22, 2026, Claude Fable 5.2 leads Gemini 3.8 Flash in Science at #2 against #9.
Coding: As of Nov 22, 2026, Claude Fable 5.2 leads Gemini 3.8 Flash in Coding at #2 against #33.
Coding › Web dev: As of Nov 22, 2026, Claude Fable 5.2 leads Gemini 3.8 Flash in Coding › Web dev at #1 against #41.
Long context: As of Nov 22, 2026, Claude Fable 5.2 leads Gemini 3.8 Flash in Long context at #5 against #8.
Factuality: As of Nov 22, 2026, Claude Fable 5.2 leads Gemini 3.8 Flash in Factuality at #13 against #32.
Abstraction (ARC): As of Nov 22, 2026, Claude Fable 5.2 and Gemini 3.8 Flash share #1 in Abstraction (ARC).
Finance: As of Nov 22, 2026, Claude Fable 5.2 leads Gemini 3.8 Flash in Finance at #1 against #30.
Legal: As of Nov 22, 2026, Claude Fable 5.2 leads Gemini 3.8 Flash in Legal at #13 against #22.
Claude Fable 5.2 · Gemini 3.8 Flash
Claude Fable 5.2 or Gemini 3.8 Flash?
As of Nov 22, 2026, Claude Fable 5.2 leads Gemini 3.8 Flash in 8 of 10 shared categories: General LLM, Science, Coding, Coding › Web dev, Long context, Factuality, Finance, and Legal.
Claude Fable 5.2 or Gemini 3.8 Flash for General LLM?
As of Nov 22, 2026, Claude Fable 5.2 leads Gemini 3.8 Flash in General LLM at #5 against #10.
Claude Fable 5.2 or Gemini 3.8 Flash for Reasoning?
As of Nov 22, 2026, Gemini 3.8 Flash leads Claude Fable 5.2 in Reasoning at #9 against #10.
Claude Fable 5.2 or Gemini 3.8 Flash for Science?
As of Nov 22, 2026, Claude Fable 5.2 leads Gemini 3.8 Flash in Science at #2 against #9.