Comparing 2 models
Claude Fable 5.1 vs Gemini 3.1 Pro Preview
Benchmarks through
Verdict
Gemini 3.1 Pro Preview places higher on 6 of the 9 tasks where both are ranked. Gemini 3.1 Pro Preview costs 5.0x less per input token. Gemini 3.1 Pro Preview accepts 1.0x more context.
- Choose Claude Fable 5.1 for Translation (#3), Literary Translation (#3), Everyday Translation (#3).
- Choose Gemini 3.1 Pro Preview for Creative Writing (#3), Marketing Copy (#3), Business Writing (#3).
Built from the published task rankings below; ranks come from each task's own weighted benchmarks, so a win on one task says nothing about another.
Measured head to head
Benchmarks both models were run on
| Evaluation | Claude Fable 5.1 | Gemini 3.1 Pro Preview | Source |
|---|---|---|---|
| Design Arena Coding | 1338 Elo | 1233 Elo | source · 2026-10-16 |
| Design Arena Full-stack Agent | 1326 Elo | 1068 Elo | source · 2026-10-14 |
| Design Arena UI | 1338 Elo | 1226 Elo | source · 2026-10-16 |
| Design Arena Web-app Agent | 1311 Elo | 1119 Elo | source · 2026-10-14 |
| Design Arena Website | 1314 Elo | 1235 Elo | source · 2026-10-16 |
| FrontierMath Tiers 1-3 (Epoch AI) | 90.2% ± 1.8 | 59.6% ± 2.9 | source · 2026-09-01 |
| LiveBench Agentic Coding | 66.1% | 44.1% | source · 2026-10-16 |
| LiveBench Coding | 86.4% | 76.5% | source · 2026-10-16 |
| LiveBench Data Analysis | 80.3% | 78.5% | source · 2026-10-16 |
| LiveBench Instruction Following | 73.0% | 79.1% | source · 2026-10-16 |
| LiveBench Language | 89.5% | 85.4% | source · 2026-10-16 |
| LiveBench Math | 97.0% | 91.0% | source · 2026-10-16 |
| LiveBench Reasoning | 91.7% | 84% | source · 2026-10-16 |
| LMArena Agent | 14.1 | -3.5 | source · 2026-10-14 |
| LMArena Agent Bash Recovery | 11.6 | -23.3 | source · 2026-10-08 |
| LMArena Agent Steerability | 14.7 | -6.2 | source · 2026-10-14 |
| LMArena Agent Task Outcome | 15.7 | -10.1 | source · 2026-10-14 |
| LMArena Agent Tool Hallucination | 0.6 | -0.2 | source · 2026-10-14 |
| LMArena Creative Writing | 1508 Elo | 1482 Elo | source · 2026-10-15 |
| LMArena Instruction Following | 1517 Elo | 1466 Elo | source · 2026-10-15 |
| LMArena Long Query | 1523 Elo | 1483 Elo | source · 2026-10-15 |
| LMArena Math | 1528 Elo | 1485 Elo | source · 2026-10-15 |
| LMArena Text | 1502 Elo | 1487 Elo | source · 2026-10-15 |
| LMArena Text Factuality | 1498 Elo | 1472 Elo | source · 2026-10-15 |
| LMArena Vision | 1286 Elo | 1280 Elo | source · 2026-10-09 |
| LMArena Vision Diagrams | 1326 Elo | 1309 Elo | source · 2026-10-09 |
| LMArena Vision OCR | 1302 Elo | 1294 Elo | source · 2026-10-09 |
| LMArena WebDev | 1743 Elo | 1447 Elo | source · 2026-10-13 |
| LMArena WebDev Image-to-Web | 1720 Elo | 1481 Elo | source · 2026-10-09 |
| OTIS Mock AIME (Epoch AI) | 100% ± 0 | 95.6% ± 3.1 | source · 2026-09-01 |
| SimpleQA Verified (Epoch AI) | 70.8% ± 1.4 | 73.5% ± 1.4 | source · 2026-09-01 |
Values are as published by each evaluator, in its own units; rows from different evaluators are not on a common scale.
task evidence
How they place when the question changes
Lower ranks are better. “Best” marks the strongest option in this shortlist for that task.