Compare / head-to-head
Claude Fable 5vs
Kimi K3
Claude Fable 5 leads 22 of 31 shared benchmarks. Kimi K3 is 3.3x cheaper per token. Kimi K3 has the larger context window (1.0M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
22 – 7
Claude Fable 5 leads · 2 tied
Cheaper per token
Kimi K3
3.3x cheaper, input + output
Larger context
Kimi K3
1.0M tokens
Providers
2 providers
Anthropic · Moonshot AI
Claude Fable 5
Anthropic · released 2026-06-09
textvision
Quality
Benchmark matrix
31 shared · 13 only Claude Fable 5 · 49 only Kimi K3| Benchmark | Claude Fable 5 | Kimi K3 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 31 | ||||
| GPQA Diamond | 85.9% ↗epoch run | 93.5% ↗ | -7.6 pt | Kimi K3 |
| LMArena Elo | 1504.3 ↗ | 1488.4 ↗ | +15.9 | Claude Fable 5 |
| APEX-Agents (Mercor) | 63.6% ↗ | 50.6% ↗ | +13 pt | Claude Fable 5 |
| AutomationBench | 17.4% ↗ | 30.8% ↗ | -13.4 pt | Kimi K3 |
| Chess Puzzles (Epoch AI run) | 41% ↗epoch run | 39% ↗epoch run | +2 pt | Claude Fable 5 |
| DeepSWE v1.1 (Datacurve) | 69.9% ↗ | 68.5% ↗ | +1.4 pt | Claude Fable 5 |
| FrontierMath Tier 4 v2 (Epoch AI run) | 90.2% ↗epoch run | 39% ↗epoch run | +51.2 pt | Claude Fable 5 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 87% ↗epoch run | 72.2% ↗epoch run | +14.8 pt | Claude Fable 5 |
| FrontierSWE V2 (Proximal Labs) | 47% ↗ | 25.9% ↗ | +21.1 pt | Claude Fable 5 |
| Furniture Assembly (Epoch AI run) | 35.8% ↗epoch run | 34.2% ↗epoch run | +1.6 pt | Claude Fable 5 |
| LiveBench Agentic Coding (LiveBench) | 62.2% ↗ | 62.2% ↗ | 0 | Tie |
| LiveBench Coding (LiveBench) | 86% ↗ | 81.4% ↗ | +4.6 pt | Claude Fable 5 |
| LiveBench Data Analysis (LiveBench) | 80.5% ↗ | 78.7% ↗ | +1.8 pt | Claude Fable 5 |
| LiveBench Instruction Following (LiveBench) | 75.8% ↗ | 71.4% ↗ | +4.4 pt | Claude Fable 5 |
| LiveBench Language (LiveBench) | 90.7% ↗ | 85.5% ↗ | +5.2 pt | Claude Fable 5 |
| LiveBench Mathematics (LiveBench) | 96% ↗ | 84.4% ↗ | +11.6 pt | Claude Fable 5 |
| LiveBench Reasoning (LiveBench) | 89.7% ↗ | 90.7% ↗ | -1 pt | Kimi K3 |
| LMArena Agent (LMArena) | 0.0821 ↗ | 0.0418 ↗ | 0 | Tie |
| LMArena WebDev (LMArena) | 1625.3 ↗ | 1657.8 ↗ | -32.5 | Kimi K3 |
| Mystery Game Puzzles (Epoch AI run) | 52% ↗epoch run | 26% ↗epoch run | +26 pt | Claude Fable 5 |
| OfficeQA Pro | 57.9% ↗ | 63.3% ↗ | -5.4 pt | Kimi K3 |
| OSWorld-Verified | 85% ↗ | 84.8% ↗ | +0.2 pt | Claude Fable 5 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 100% ↗epoch run | 97.2% ↗epoch run | +2.8 pt | Claude Fable 5 |
| SAGE (Vals AI) | 51.9% ↗ | 52.8% ↗ | -0.9 pt | Kimi K3 |
| SimpleBench (SimpleBench) | 81.9% ↗ | 60.7% ↗ | +21.2 pt | Claude Fable 5 |
| SimpleQA Verified | 70.7% ↗epoch run | 50.6% ↗epoch run | +20.1 pt | Claude Fable 5 |
| tau2-bench Banking Knowledge (Sierra) | 39.7% ↗ | 37.1% ↗ | +2.6 pt | Claude Fable 5 |
| Terminal-Bench 2.1 | 84.3% ↗ | 88.3% ↗ | -4 pt | Kimi K3 |
| Terminal-Bench 4.0 (Vals AI) | 41.4% ↗ | 17.2% ↗ | +24.2 pt | Claude Fable 5 |
| Vending-Bench 2 (Andon Labs) | 5680.26 ↗ | 5165.04 ↗ | +515.2 | Claude Fable 5 |
| WeirdML (Håvard Tveit Ihle) | 91.9% ↗ | 82.6% ↗ | +9.3 pt | Claude Fable 5 |
| Only Claude Fable 5 reports · 13 | ||||
| SWE-bench Verified | 95% ↗ | not reported | — | — |
| Blueprint-Bench 2 | 38.6% ↗ | not reported | — | — |
| CursorBench | 72.9% ↗ | not reported | — | — |
| EBR-bench (Epoch AI run) | 39.5% ↗epoch run | not reported | — | — |
| FrontierCode (Diamond) | 29.3% ↗ | not reported | — | — |
| GDP.pdf | 29.8% ↗ | not reported | — | — |
| GSO Opt@1 (GSO) | 76.5% ↗ | not reported | — | — |
| Legal Agent Benchmark (Harvey's Held-Out Set) | 13.3% ↗ | not reported | — | — |
| LMArena Vision (LMArena) | 1308.8 ↗ | not reported | — | — |
| MirrorCode (Epoch AI run) | 63.9% ↗epoch run | not reported | — | — |
| OSWorld-Verified (XLANG) | 86% ↗ | not reported | — | — |
| SWE-Bench Pro | 80% ↗ | not reported | — | — |
| SWE-rebench 2026-05-15 to 2026-07-01 (Nebius) | 64.5% ↗ | not reported | — | — |
| Only Kimi K3 reports · 49 | ||||
| AIME 2026 | not reported | 96.7% ↗matharena ⚠ | — | — |
| Humanity's Last Exam (no tools) | not reported | 43.5% ↗ | — | — |
| AA-Briefcase | not reported | 1548 ↗ | — | — |
| AA-LCR | not reported | 74.7% ↗ | — | — |
| Agents' Last Exam | not reported | 28.3% ↗ | — | — |
| APEX-Agents | not reported | 41% ↗ | — | — |
| BabyVision (with Python) | not reported | 85.7% ↗ | — | — |
| BrowseComp (1M context, no compaction) | not reported | 90.4% ↗ | — | — |
| BrowseComp (context compaction) | not reported | 91.2% ↗ | — | — |
| CharXiv Reasoning (no tools) | not reported | 84.8% ↗ | — | — |
| CharXiv Reasoning (with Python) | not reported | 91.3% ↗ | — | — |
| CorpFin v2 | not reported | 71.6% ↗ | — | — |
| CritPt | not reported | 23.4% ↗ | — | — |
| DeepSearchQA (F1) | not reported | 95% ↗ | — | — |
| DeepSWE v1.1 | not reported | 67.3% ↗ | — | — |
| DeepSWE v1.1 (Kimi Code) | not reported | 67.5% ↗ | — | — |
| Finance Agent v2 | not reported | 54.4% ↗ | — | — |
| FrontierSWE | not reported | 81.2% ↗ | — | — |
| GDPval-AA v2 | not reported | 1686 ↗ | — | — |
| Harvey Lab-AA | not reported | 94.6% ↗ | — | — |
| Humanity's Last Exam (with tools) | not reported | 56% ↗ | — | — |
| JobBench | not reported | 54.3% ↗ | — | — |
| Kimi Code Bench 2.0 | not reported | 72.9% ↗ | — | — |
| Legal Research Bench | not reported | 44.2% ↗ | — | — |
| MathVision (no tools) | not reported | 94.3% ↗ | — | — |
| MathVision (with Python) | not reported | 97.8% ↗ | — | — |
| MCP-Atlas | not reported | 84.2% ↗ | — | — |
| MCPMark-Verified | not reported | 94.5% ↗ | — | — |
| MLS-Bench-Lite | not reported | 48.3% ↗ | — | — |
| MMMU-Pro (no tools) | not reported | 81.6% ↗ | — | — |
| MMMU-Pro (with Python) | not reported | 83.4% ↗ | — | — |
| MMVU | not reported | 82.1% ↗ | — | — |
| OmniDocBench | not reported | 91.1% ↗ | — | — |
| OSWorld 2.0 | not reported | 58.3% ↗ | — | — |
| PerceptionBench | not reported | 58.5% ↗ | — | — |
| PostTrainBench | not reported | 36.6% ↗ | — | — |
| ProgramBench | not reported | 77.8% ↗ | — | — |
| ResearchRubrics | not reported | 76.2% ↗ | — | — |
| SaaS-Bench | not reported | 60.1% ↗ | — | — |
| SciCode | not reported | 58.7% ↗ | — | — |
| SpreadsheetBench 2 | not reported | 34.8% ↗ | — | — |
| SWE-Marathon | not reported | 42% ↗ | — | — |
| tau3-Banking | not reported | 33.4% ↗ | — | — |
| Toolathlon-Verified | not reported | 76.5% ↗ | — | — |
| Toolathlon-Verified (HKUST) | not reported | 76.5% ↗ | — | — |
| Video-MME (with subtitles) | not reported | 90% ↗ | — | — |
| WorldVQA ForceAnswer | not reported | 51% ↗ | — | — |
| ZeroBench pass@5 (no tools) | not reported | 23% ↗ | — | — |
| ZeroBench pass@5 (with Python) | not reported | 41% ↗ | — | — |
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is Claude Fable 5 minus Kimi K3 in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing
Side by side
Official pricing pages and model cards| Spec | Claude Fable 5 | Kimi K3 | Edge |
|---|---|---|---|
| Context window | 1M tokens | 1.0M tokens | Kimi K3 |
| Max output | 128K tokens | 1.0M tokens | Kimi K3 |
| Input price / 1M | $10 ↗ | $3 ↗ | Kimi K3 |
| Output price / 1M | $50 ↗ | $15 ↗ | Kimi K3 |
| Cached input / 1M | $1 ↗ | $0.3 ↗ | Kimi K3 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $60 | $18 | Kimi K3 |
| Modalities | text · vision | text · vision | Tie |
| Released | 2026-06-09 | 2026-07-16 | — |
| Cited benchmark scores | 44 | 87 | — |
Reliability
Provider status
Live from /statusMore matchups
Claude Fable 5 vs …
Models sharing the most benchmarksMore matchups
Kimi K3 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Fable 5 and Kimi K3 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.