Benchmark scores
Higher is better for all benchmark scores (SWE-bench, GPQA, HLE, Terminal-Bench, etc.). Green marks the model with the higher score.
LLM Comparison
Claude Fable 5 vs Hy3: benchmark scores, pricing & comparison.
Side-by-side Claude Fable 5 vs Hy3 comparison across SWE-bench, GPQA, HLE, Terminal-Bench, coding agent scores, token pricing, context window, and AskClash RWT. Green marks the winner on each benchmark.
Rank #1 vs #18AskClash overall scores 91.9 vs 58.7.
Pricing $10.0/$50.0 vs $0.12/$0.43Input and output token prices per 1M tokens when published.
Proprietary vs Open WeightAnthropic vs Tencent.
Claude Fable 5 vs Hy3 benchmark comparison
Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.
| Metric | Claude Fable 5 | Hy3 |
|---|---|---|
| Overall Score | 91.9 | 58.7 |
| Leaderboard Rank | #1 | #18 |
| RWT | 9.0 | 8.0 |
| Coding Agent Index | 77.2 | — |
| HLE | 64.5 | 53.2 |
| GPQA | 94.5 | 90.4 |
| IFEval | 80.3 | — |
| SWE-bench | 95.5 | 78.0 |
| SWE-Pro | 80.3 | 57.9 |
| SWE-Atlas | 83.3 | — |
| Terminal-Bench | 88.0 | 71.7 |
| DeepSWE | 69.7 | — |
| OSWorld | 85.0 | — |
| MCP Atlas | — | 79.1 |
| Finance Agent | 56.3 | — |
| CharXiv | 93.5 | — |
| MMMU-Pro | 92.7 | — |
| Tau2 | 89.2 | 92.7 |
| MRCR | — | 75.1 |
| Input Price (per 1M tokens) | $10.0 | $0.12 |
| Output Price (per 1M tokens) | $50.0 | $0.43 |
| Context Window | 1M+ | 256K |
| Benchmarks Published | 16 | 9 |
Claude Fable 5 vs Hy3 head-to-head charts
Claude Fable 5 leads 7 and Hy3 leads 1 of 8 shared benchmarks. Hy3 is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.
Claude Fable 5Hy3
Overall
RWT
HLE
GPQA
SWE-bench
SWE-Pro
Terminal-Bench
Tau2
Claude Fable 5
Input$10.0
Output$50.0
Workload$20
Context1M+
Hy3
Input$0.12
Output$0.43
Workload$0.21
Context256K
Workload = published cost of 1M input + 200K output tokens. Open the live leaderboard for interactive compare charts.
More Claude Fable 5 and Hy3 comparisons
Explore how Claude Fable 5 and Hy3 stack up against other top-ranked LLMs.
How to read this comparison
Token pricing
Lower is better for input and output prices. Green marks the cheaper model per 1M tokens.
Coverage matters
Models with fewer disclosed benchmark cells may have inflated percentile scores. Check the benchmark cell count for context.
This comparison page is generated from the AskClash LLM leaderboard cache. Open the live leaderboard for real-time scores and interactive filtering.