Model vs model
Hy3 vs Mistral Small 4
Hy3 suits text-only work such as coding, long-document analysis and hard reasoning, and it outscores Mistral Small 4 on every shared benchmark. Its Intelligence Index is 25.3 against 11.3, at nearly the same price: $0.25 per 1M tokens blended versus $0.26. Pick Mistral Small 4 if you need to send it images or PDFs, since Hy3 accepts text only.
At a glance
Longer bar means the bigger number.
Blended price · per 1M tokens, lower is better
Intelligence Index · Artificial Analysis, higher is better
Where they sit among all 44 models
Hy3 ranks 28th of the 43 models with an Intelligence Index, Mistral Small 4 39th. Up and to the left is smarter for less money. Hover or tap a dot for its numbers, then click it to compare that model with Hy3.
Which one to pick
Pick Hy3 if
- you want the lower bill ($0.25 vs $0.26 per 1M tokens blended)
- you want the higher overall score (25.3 vs 11.3)
- you care about coding: 58.8 vs 26.6
- you care about AA-LCR (long documents): 79 vs 49.7
Pick Mistral Small 4 if
- you need to send images and PDFs
How smart is each one?
Of the 14 scores both models have, Hy3 is ahead on 13, and one is within a point.
Every intelligence score we have
Out of 100, higher is better. Hy3 Mistral Small 4
Overall
Intelligence Index
25.311.3
By area
Coding
58.826.6Agentic work
24.10.8
By field of work
Finance & accounting
27.310.5Legal
26.512.8Healthcare & medicine
10.8Hy3: not scored yet
Economics
35.218.1Engineering
26.716.4Strategy & operations
23.96.7
Benchmarks
Hard reasoning · Humanity's Last Exam
33.59.9Science · GPQA Diamond
89.776.9Scientific coding · SciCode
48.638.8Terminal tasks · Terminal-Bench 4.0
0.5 · 0Tool use · τ-Bench Banking
22.94.9Instruction following · IFBench
48.2Hy3: not scored yet
Long documents · AA-LCR
7949.7Uncensored · UGI
37.4Hy3: not scored yet
The specs
| Spec | Hy3 | Mistral Small 4 |
|---|---|---|
| Input price | $0.14 per 1M | $0.15 per 1M |
| Output price | $0.58 per 1M | $0.60 per 1M |
| Cost per test task | Not tested | $0.0150 |
| Context window | 262K | 262K |
| Max output | 262K | 256K |
| Accepts | Text | Text, Image, PDF |
| Open weights | Yes | Yes |
| Lab | Tencent | Mistral AI |
| Released | Jul 2026 | Mar 2026 |
| Knowledge cutoff | Not published | Jun 2025 |
Blended price weighs 3 parts input to 1 part output. List prices from models.dev. Cost per test task from Artificial Analysis.
Questions
Is Hy3 or Mistral Small 4 cheaper?
Hy3 is cheaper. It charges $0.14 per 1M input tokens and $0.58 per 1M output tokens, against $0.15 and $0.60 for Mistral Small 4. Blended 3 parts input to 1 part output, that is $0.25 against $0.26 per 1M tokens.
Which is smarter, Hy3 or Mistral Small 4?
Hy3 scores higher on the Artificial Analysis Intelligence Index, 25.3 against 11.3 for Mistral Small 4. The biggest differences are on Coding (58.8 vs 26.6) and AA-LCR (79 vs 49.7).
Which has the longer context window?
Both accept 262K tokens.
Can I compare Hy3 and Mistral Small 4 on my own prompt?
Yes. ModelCompare sends one prompt to both models at once and shows each answer side by side with what it cost. You can try it free without an account.
Related comparisons
Where the numbers come from
Intelligence Index and benchmark scores are from Artificial Analysis, at each model’s highest effort, except SimpleQA, which is from Epoch AI, and the Uncensored score, which is from the UGI Leaderboard. The hallucination test is ours: questions with one exact answer, fake evidence pushed against right answers and requests that tempt a model to name packages that don’t exist. Prices are list prices from models.dev. Example answers come from our own test runs. Updated October 25, 2026.