Compare / Hy3 vs Hy3 Preview
Hy3 vs Hy3 Preview
Which is cheaper, which is more capable, and which does better at each kind of work, from 11 results on 2 sources that measured both models.
Results as of 8 October 2026 (catalogue release 2026-10-08-4199ce0620fe).
Hy3 or Hy3 Preview? The short answer
Hy3 is the newer version at about the same price, and it scores higher (Intelligence Index 25.3 against 22.7): upgrade.
- They cost about the same: $0.25 and $0.29 per million tokens (three input to one output).
- Hy3 scores higher on the Artificial Analysis Intelligence Index: 25.3 against 22.7.
- Hy3 is newer: released 6 Jul 2026, against 23 Apr 2026 for Hy3 Preview.
- On third-party benchmarks, on the results both models have: Hy3 does better for reasoning and knowledge, writing and sticking to the facts.
At a glance
| Hy3 | Hy3 Preview | |
|---|---|---|
| Price per million tokens | $0.14 in · $0.58 out | $0.18 in · $0.60 out |
| Blended (3 in : 1 out) | $0.25 | $0.29 |
| Cheapest host, blended | $0.23 (DeepInfra, FP4) | – |
| Intelligence Index | 25.3 | 22.7 |
| Spring Prompt overall | – | – |
| Output speed, tokens a second | 87 | – |
| Context window | 262,144 tokens | 262,144 tokens |
| Released | 6 Jul 2026 (newer) | 23 Apr 2026 |
| Weights | Open | Open |
| Developer based in | China | China |
Prices are the developer's list price where we have read it, otherwise the typical host on OpenRouter; see every model's price. Intelligence and speed from Artificial Analysis.
Which is better for what
Each model's rank among models available today, for each kind of work, from our own benchmarks and licensed sources. The better rank is in green.
| Use case | Hy3 | Hy3 Preview |
|---|---|---|
| Agents and tool useMulti-step tasks with tools: support desks, coding agents, function calls | 62 of 164 | not measured |
| Reasoning and knowledgeHard questions across science, maths and general knowledge | 60 of 198 | 78 of 198 |
| WritingWhat people prefer in blind comparisons, and judged writing quality | 45 of 188 | 88 of 188 |
| Sticking to the factsSummarising without inventing things, and factual answers | 70 of 152 | 128 of 152 |
Every shared result
Each model's best result on every measure both have, grouped by benchmark, with the setting that produced it. The headline measures of each benchmark come first; the rest are under "Show all". Green marks the better value; where a source reports ranges that overlap, neither is marked.
| Measure | Hy3 | Hy3 Preview |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 3 results | ||
| Overall · TextArena rating, higher is better | 1,456 | 1,409 |
| Overall · Text factualityArena rating, higher is better | 1,445 | 1,412 |
| Business, management and finance · TextArena rating, higher is better | 1,448 | 1,411 |
| Artificial Analysis reported by Artificial Analysis · 3 results | ||
| Artificial Analysis Intelligence Indexindex score, higher is better | 25.3 | 22.7thinking reasoning |
| GPQA Diamond% of questions, higher is better | 89.7% | 86.7%thinking reasoning |
| Humanity's Last Exam% of questions, higher is better | 33.5% | 27.8%thinking reasoning |
Show all 11 results (5 more)
| Measure | Hy3 | Hy3 Preview |
|---|---|---|
| Arena (formerly LMArena) reported by Arena (formerly LMArena) · 4 results | ||
| Creative writing · TextArena rating, higher is better | 1,422 | 1,353 |
| Expert prompts · TextArena rating, higher is better | 1,488 | 1,446 |
| Instruction following · TextArena rating, higher is better | 1,446 | 1,396 |
| Writing, literature and language · TextArena rating, higher is better | 1,427 | 1,377 |
| Artificial Analysis reported by Artificial Analysis · 1 result | ||
| Long-context reasoning (AA-LCR)% of questions, higher is better | 79.0% | 64.7%thinking reasoning |
Quick answers
Is Hy3 better than Hy3 Preview?
Hy3 is the newer version at about the same price, and it scores higher (Intelligence Index 25.3 against 22.7): upgrade.
Which is cheaper, Hy3 or Hy3 Preview?
They cost about the same: $0.25 and $0.29 per million tokens (three input to one output).
Run Hy3 and Hy3 Preview on your own prompt
Benchmarks aren't your data. Try both side by side in the playground, with the cost of every answer.