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 Gemini 3.6 Flash: benchmark scores, pricing & comparison.
Side-by-side Hy3 vs Gemini 3.6 Flash 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 #18 vs #22AskClash overall scores 59.1 vs 55.3.
Pricing $0.12/$0.43 vs $1.50/$7.50Input and output token prices per 1M tokens when published.
Open Weight vs ProprietaryTencent vs Google.
Hy3 vs Gemini 3.6 Flash benchmark comparison
Green cells highlight the winning model for each metric. Scores are cached from the AskClash LLM leaderboard snapshot.
| Metric | Hy3 | Gemini 3.6 Flash |
|---|---|---|
| Overall Score | 59.1 | 55.3 |
| Leaderboard Rank | #18 | #22 |
| RWT | 8.0 | — |
| HLE | 53.2 | 38.0 |
| GPQA | 90.4 | 92.8 |
| SWE-bench | 78.0 | — |
| SWE-Pro | 57.9 | 58.7 |
| Terminal-Bench | 71.7 | 78.0 |
| DeepSWE | — | 49.0 |
| OSWorld | — | 83.0 |
| MCP Atlas | 79.1 | — |
| Finance Agent | — | 56.3 |
| CharXiv | — | 85.2 |
| MMMU-Pro | — | 83.2 |
| Tau2 | 92.7 | — |
| MRCR | 75.1 | 91.8 |
| Input Price (per 1M tokens) | $0.12 | $1.50 |
| Output Price (per 1M tokens) | $0.43 | $7.50 |
| Context Window | 256K | 1M |
| Benchmarks Published | 9 | 13 |
Hy3 vs Gemini 3.6 Flash head-to-head charts
Hy3 leads 2 and Gemini 3.6 Flash leads 4 of 6 shared benchmarks. Hy3 is cheaper on a defined 1M-input / 200K-output workload. Charts show only benchmarks both models publish.
Hy3Gemini 3.6 Flash
Overall
HLE
GPQA
SWE-Pro
Terminal-Bench
MRCR
Hy3
Input$0.12
Output$0.43
Workload$0.21
Context256K
Gemini 3.6 Flash
Input$1.50
Output$7.50
Workload$3.00
Context1M
Workload = published cost of 1M input + 200K output tokens. Open the live leaderboard for interactive compare charts.
More Hy3 and Gemini 3.6 Flash comparisons
Explore how Hy3 and Gemini 3.6 Flash 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.