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
Kimi K2.7 Code vs Hy3 Preview: benchmark scores, pricing & comparison.
Side-by-side Kimi K2.7 Code vs Hy3 Preview 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 #8 vs #30AskClash overall scores 68.3 vs 40.3.
Pricing $0.95/$4.00 vs $0/$0Input and output token prices per 1M tokens when published.
Open Weight vs Open WeightMoonshot AI vs Tencent.
Kimi K2.7 Code vs Hy3 Preview benchmark comparison
Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.
| Metric | Kimi K2.7 Code | Hy3 Preview |
|---|---|---|
| Overall Score | 68.3 | 40.3 |
| Leaderboard Rank | #8 | #30 |
| RWT | 7.5 | — |
| HLE | 54.0 | 25.5 |
| GPQA | 90.5 | 87.2 |
| IFEval | — | 63.1 |
| SWE-bench | 80.2 | 74.4 |
| SWE-Pro | 58.6 | — |
| Terminal-Bench | 66.7 | 54.4 |
| LiveCodeBench | 89.6 | — |
| OSWorld | 73.1 | — |
| MCP Atlas | 76.0 | — |
| Finance Agent | 44.9 | — |
| CharXiv | 80.4 | — |
| MMMU-Pro | 79.4 | — |
| Tau2 | 90.1 | 92.7 |
| Input Price (per 1M tokens) | $0.95 | $0 |
| Output Price (per 1M tokens) | $4.00 | $0 |
| Context Window | 256K | 256K |
| Benchmark Cells | 13 | 6 |
More Kimi K2.7 Code and Hy3 Preview comparisons
Explore how Kimi K2.7 Code and Hy3 Preview stack up against other top-ranked LLMs.
Claude Mythos/Fable 5 vs Kimi K2.7 CodeClaude Mythos/Fable 5 vs Hy3 PreviewClaude Opus 4.8 (Adaptive) vs Kimi K2.7 CodeClaude Opus 4.8 (Adaptive) vs Hy3 PreviewGPT-5.5 xHigh vs Kimi K2.7 CodeGPT-5.5 xHigh vs Hy3 PreviewGLM-5.2 vs Kimi K2.7 CodeGLM-5.2 vs Hy3 PreviewClaude Opus 4.7 (Adaptive) vs Kimi K2.7 CodeClaude Opus 4.7 (Adaptive) vs Hy3 Preview
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.