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
Hy3 vs Composer 2.5: benchmark scores, pricing & comparison.
Side-by-side Hy3 vs Composer 2.5 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 #33 vs #64AskClash overall scores 55.7 vs 36.2.
Pricing $0.12/$0.43 vs $0.50/$2.50Input and output token prices per 1M tokens when published.
Open Weight vs ProprietaryTencent vs Cursor.
Hy3 vs Composer 2.5 benchmark comparison
Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.
| Metric | Hy3 | Composer 2.5 |
|---|---|---|
| Overall Score | 55.7 | 36.2 |
| Leaderboard Rank | #33 | #64 |
| ACB | — | 53.2 |
| RWT | 8.0 | 8.5 |
| Coding Agent Index | — | 38.3 |
| HLE | 53.2 | — |
| GPQA | 90.4 | — |
| SWE-bench | 78.0 | — |
| SWE-Pro | 57.9 | 47.0 |
| SWE-Atlas | — | 31.2 |
| Terminal-Bench | 71.7 | 67.8 |
| GDPval-AA | 1136.0 | — |
| MCP Atlas | 79.1 | — |
| Tau2 | 92.7 | — |
| MRCR | 75.1 | — |
| Input Price (per 1M tokens) | $0.12 | $0.50 |
| Output Price (per 1M tokens) | $0.43 | $2.50 |
| Context Window | 256K | 200K |
| Benchmarks Published | 10 | 5 |
Hy3 vs Composer 2.5 head-to-head charts
Hy3 leads 3 and Composer 2.5 leads 1 of 4 shared benchmarks. Hy3 is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.
Hy3Composer 2.5
Overall
RWT
SWE-Pro
Terminal-Bench
Hy3
Input$0.12
Output$0.43
Workload$0.21
Context256K
Composer 2.5
Input$0.50
Output$2.50
Workload$1.00
Context200K
Workload = published cost of 1M input + 200K output tokens. Open the live leaderboard for interactive compare charts.
More Hy3 and Composer 2.5 comparisons
Explore how Hy3 and Composer 2.5 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.