add results for tencent/EVIE-8B and tencent/EVIE-4.5B

[KennethEnevoldsen]

Note see embeddings-benchmark/mteb#5451 for discussion on implementation

closes embeddings-benchmark/mteb#5451

Checklist

• My model has a model sheet, report, or similar
• My model has a reference implementation in mteb/models/model_implementations/, this can be as an API. Instruction on how to add a model can be found here
  • No, but there is an existing PR ___
• The results submitted are obtained using the reference implementation
• My model is available, either as a publicly accessible API or publicly on e.g., Huggingface
• I solemnly swear that for all results submitted I have not trained on the evaluation dataset including training splits. If I have, I have disclosed it clearly.

[github-actions]

Model Results Comparison

Reference models: intfloat/multilingual-e5-large, google/gemini-embedding-001
New models evaluated: tencent/EVIE-4.5B, tencent/EVIE-8B

Results for tencent/EVIE-4.5B

task_name	tencent/EVIE-4.5B	Max result	Model with max result	In Training Data
Vidore3NuclearRetrieval	.564	.549	vultr/VultronRetrieverCore-Qwen3.5-4.5B	False
Vidore3TelecomRetrieval	.735	.733	webAI-Official/webAI-ColVec1.1-8b	False
Average	.650	.641	nan	-

Model have high performance on these tasks: Vidore3TelecomRetrieval,Vidore3NuclearRetrieval

---

Results for tencent/EVIE-8B

task_name	tencent/EVIE-8B	Max result	Model with max result	In Training Data
Vidore3NuclearRetrieval	.566	.549	vultr/VultronRetrieverCore-Qwen3.5-4.5B	False
Vidore3TelecomRetrieval	.743	.733	webAI-Official/webAI-ColVec1.1-8b	False
Average	.654	.641	nan	-

Model have high performance on these tasks: Vidore3TelecomRetrieval,Vidore3NuclearRetrieval

---

[officea1t]

Hi @KennethEnevoldsen, thanks again for running and adding the private Nuclear/Telecom results! 🙏

This PR is marked ready for review and closes #5451. Whenever you (or @Samoed) have a moment, would it be possible to merge it so the ViDoRe V3 entry is complete (8 public domains + the 2 private tasks)? Happy to help if anything else is needed on our side. Thank you!

[KennethEnevoldsen]

Sorry @officea1t I see that I wasn't quite clear in my communication. I was waiting for a review from you guys stating that you were happy to merge it (I assume you are from the message)