Claude Fable 5.2 vs Kimi K3
| Spec | Claude Fable 5.2 | Kimi K3 |
|---|---|---|
| Respan Index | 80.8 (#1) | 52.8 (#35) |
| Blended price per 1M | $16 | $2.52 |
| Context window | - | 1.0M |
| Input / output per 1M | $8 / $40 | $0.192 / $9.5 |
| Max output | - | 1.0M |
| Input | text | text, vision |
| Released | 2026-11-09 | 2026-07-16 |
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 | Kimi K3 |
|---|---|---|
| Coding | 73.0 Claude Fable 5.2 | 38.8 Kimi K3 |
| Agents | 85.3 Claude Fable 5.2 | 61.8 Kimi K3 |
| Reasoning | 90.2 Claude Fable 5.2 | 54.8 Kimi K3 |
| Knowledge & language | 94.0 Claude Fable 5.2 | 52.9 Kimi K3 |
| Human preference | 61.7 Claude Fable 5.2 | 57.7 Kimi K3 |
Benchmarks both report
Claude Fable 5.2 leads on 17 of the 17 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Fable 5.2 | Kimi K3 |
|---|---|---|
| LMArena WebDev (LMArena) | 1824 | 1659 |
| LMArena Elo | 1503 | 1488 |
| LMArena Agent (LMArena) | 0.2742 | -0.0015 |
| Vending-Bench 2 (Andon Labs) | 9628.48 | 5165.04 |
| APEX-Agents (Mercor) | 80.1% | 47.8% |
| Chess Puzzles (Epoch AI) | 79% | 37% |
| FrontierMath Tier 4 v2 (Epoch AI) | 100% | 39% |
| FrontierMath Tiers 1-3 v2 (Epoch AI) | 95.1% | 72.2% |
| FrontierSWE V2 (Proximal Labs) | 69.9% | 25.9% |
| Furniture Assembly (Epoch AI) | 90% | 34.2% |
| GPQA Diamond | 93.9% | 93.5% |
| Mystery Game Puzzles (Epoch AI) | 90% | 26% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 99.7% | 97.2% |
| SimpleBench (SimpleBench) | 94.9% | 60.7% |
| SimpleQA Verified | 94% | 50.6% |
| Terminal-Bench 4.0 (Vals AI) | 65.2% | 17.2% |
| Humanity's Last Exam (with tools) | 74.2% | 56% |
FAQ
Is Claude Fable 5.2 better than Kimi K3?
Claude Fable 5.2 scores 80.8 on the Respan Index (#1), ahead of Kimi K3 at 52.8 (#35). Claude Fable 5.2 leads on 17 of the 17 benchmarks both report.
Which is cheaper, Claude Fable 5.2 or Kimi K3?
Claude Fable 5.2 lists at $8 input and $40 output per 1M tokens; Kimi K3 at $0.192 and $9.5. Kimi K3 is 6.4x cheaper per token at list price.