Up to four models
Claude Fable 5.2 vs Gemini 4 Carbon
On the index (GPT-4 = 100), Claude Fable 5.2 scores 202 and Gemini 4 Carbon 198. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Claude Fable 5.2
202185–218
WeightsClosed
ReleasedNov 2026
Price in / out$8.0 / $40
Context1M
Core tests taken4 of 9
198182–215
WeightsClosed
ReleasedOct 2026
Price in / out$2.0 / $10
Context1.05M
Core tests taken4 of 9
Claude Fable 5.2 and Gemini 4 Carbon are too close to call (3 points apart, within the uncertainty), ahead on 2 of 4 shared core tests, at 4.0× the price.
Test by testthird-party results
Claude Fable 5.2
Gemini 4 Carbon
Every result as a table
| Test | Claude Fable 5.2 | Gemini 4 Carbon |
|---|---|---|
| Reasoning & knowledge | ||
| GPQA Diamond (Epoch AI) | 96.0% | 96.5% |
| EBR-bench | 90.5% | 87.6% |
| SimpleBench | 94.9% | 92.6% |
| SimpleQA Verified | 94.0% | 77.7% |
| Maths | ||
| FrontierMath (tiers 1-3) | 95.1% | 90.5% |
| AIME-style maths (OTIS mock) | 99.7% | 100.0% |
| Chess puzzles | 79.0% | 78.0% |
| FrontierMath (tier 4) | 100.0% | 95.1% |
| Coding | ||
| Terminal-Bench 4.0 | 65.1% | 63.1% |
| Vibe Code Bench v1.1 | 93.8% | 89.1% |
| FrontierSWE | 69.9% | 61.2% |
| Agents | ||
| APEX-Agents | 80.1% | 84.2% |
| Furniture assembly | 90.0% | 77.5% |
| Mystery game puzzles | 90.0% | 73.0% |
| Professional work | ||
| HLAB-Vals-1.1 | 5.0% | 17.5% |
| Legal Research Bench | 46.2% | 55.8% |
| Tax Agent Bench | 32.1% | 51.8% |
Tests at least two of these models have taken. Bold rows are the core tests.