Tencent·LLM — weighted competency·Tue 25 Aug 2026
THy3
Hy3 scores 65/100 competency for LLM at $0.24.
High confidence
Competency
65/100
category rank #49
Cost
$0.24/1M tok
blended
Speed
42/100
Slow
Accuracy
—
no data yet
Score history.
Weighted LLM competency · last 12 weeks · weekly snapshot.
65/100
+0 pts vs prior
17 Jul20 Jul23 Jul26 Jul30 Jul2 Aug5 Aug9 Aug12 Aug16 Aug19 Aug22 Aug25 Aug
What it's actually good at.
Score on each business-task subset that goes into the weighted competency.
Customer Service20% of category weight
54
Content Writing15% of category weight
58
Research & Analysis16% of category weight
62
Summarization12% of category weight
66
Translation7% of category weight
70
Reasoning16% of category weight
80
Knowledge14% of category weight
51
Pricing.
Published usage pricing. Figures refresh daily from our pricing sources.
$0.24
Usage pricing
$0.24/1M tok
- Input
- $0.14 / 1M tokens
- Output
- $0.55 / 1M tokens
Where it sits.
Position against the rest of the category. Ranked by weighted competency.
| Rank | Model | Score | Cost | Speed | Δ vs Hy3 |
|---|---|---|---|---|---|
| 19 | MMiniMax-M3 | 72 | $0.53 | 82 / 100 | +7 |
| 20 | KKimi K2.7 Code | 71 | $1.71 | 39 / 100 | +6 |
| 21 | MMotif 3 | 70 | — | 40 / 100 | +5 |
| 22 | NNex-N2-Pro | 69 | $1.00 | 82 / 100 | +4 |
| 23 | SGrok Build 0.1 0616 | 67 | $1.25 | 40 / 100 | +2 |
| 24 | USolar Pro 4 | 66 | $0.53 | 40 / 100 | +1 |
| 25 | KKimi K2 Thinking | 66 | $1.08 | 40 / 100 | +1 |
| 26 | THy3 | 65 | $0.24 | 42 / 100 | — |
| 27 | XMiMo-V2.5-Pro | 63 | $0.54 | 22 / 100 | -2 |
| 28 | DDeepSeek V3.2 | 63 | $0.32 | 0 / 100 | -2 |
| 29 | XGrok 4.20 0309 v2 | 62 | $1.56 | 40 / 100 | -3 |
| 30 | AQwen3.6 Plus | 62 | $1.13 | 40 / 100 | -3 |
| 31 | OGPT-5.4 mini | 62 | $1.69 | 0 / 100 | -3 |
| 32 | TInkling | 61 | $1.76 | 23 / 100 | -4 |
| 33 | XMiMo-V2.5 | 60 | $0.18 | 29 / 100 | -5 |