Claude Fable 5.2 vs Gemini 4 Carbon
| Spec | Claude Fable 5.2 | Gemini 4 Carbon |
|---|---|---|
| Respan Index | 80.8 (#1) | 76.1 (#3) |
| Blended price per 1M | $16 | $4 |
| Context window | - | 1M |
| Input / output per 1M | $8 / $40 | $2 / $10 |
| Max output | - | - |
| Input | text | text, image, audio, video |
| Released | 2026-11-09 | 2026-11-10 |
Respan Index by category
Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.
| Category | Claude Fable 5.2 | Gemini 4 Carbon |
|---|---|---|
| Coding | 73.0 Claude Fable 5.2 | 69.3 Gemini 4 Carbon |
| Agents | 85.3 Claude Fable 5.2 | 83.5 Gemini 4 Carbon |
| Reasoning | 90.2 Claude Fable 5.2 | 84.1 Gemini 4 Carbon |
| Knowledge & language | 94.0 Claude Fable 5.2 | 77.8 Gemini 4 Carbon |
| Human preference | 61.7 Claude Fable 5.2 | 60.6 Gemini 4 Carbon |
Benchmarks both report
Claude Fable 5.2 leads on 12 of the 17 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Fable 5.2 | Gemini 4 Carbon |
|---|---|---|
| LMArena Elo | 1503 | 1527 |
| LMArena WebDev (LMArena) | 1823 | 1769 |
| LMArena Agent (LMArena) | 0.2742 | 0.161 |
| Vending-Bench 2 (Andon Labs) | 9628.48 | 16484.21 |
| APEX-Agents (Mercor) | 80.1% | 84.2% |
| Chess Puzzles (Epoch AI) | 79% | 78% |
| EBR-bench (Epoch AI) | 90.5% | 87.6% |
| FrontierMath Tier 4 v2 (Epoch AI) | 100% | 95.1% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 95.1% | 90.5% |
| FrontierSWE V2 (Proximal Labs) | 69.9% | 61.2% |
| Furniture Assembly (Epoch AI) | 90% | 77.5% |
| GPQA Diamond | 93.9% | 96.5% |
| Mystery Game Puzzles (Epoch AI) | 90% | 73% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 99.7% | 100% |
| SimpleBench (SimpleBench) | 94.9% | 92.6% |
| SimpleQA Verified | 94% | 77.7% |
| Terminal-Bench 4.0 (Vals AI) | 65.2% | 63.1% |
FAQ
Is Claude Fable 5.2 better than Gemini 4 Carbon?
Claude Fable 5.2 scores 80.8 on the Respan Index (#1), ahead of Gemini 4 Carbon at 76.1 (#3). Claude Fable 5.2 leads on 12 of the 17 benchmarks both report.
Which is cheaper, Claude Fable 5.2 or Gemini 4 Carbon?
Claude Fable 5.2 lists at $8 input and $40 output per 1M tokens; Gemini 4 Carbon at $2 and $10. Gemini 4 Carbon is 4.0x cheaper per token at list price.