From c5a507422a0386ea3aaa317c776c7b1e42538917 Mon Sep 17 00:00:00 2001
From: Lino Giger <68745352+LinoGiger@users.noreply.github.com>
Date: Tue, 24 Feb 2026 10:28:00 +0100
Subject: [PATCH 1/4] added the new benchmark features

---
 docs/mri.md                                   |  41 +++++
 docs/mri_advanced.md                          |  31 ++++
 .../create_benchmark_participant_result.py    |  30 ++--
 .../{_participant.py => participant.py}       |  49 +++++-
 .../benchmark/rapidata_benchmark.py           | 156 +++++++++++++++++-
 src/rapidata/types/__init__.py                |   4 +
 6 files changed, 294 insertions(+), 17 deletions(-)
 rename src/rapidata/rapidata_client/benchmark/participant/{_participant.py => participant.py} (76%)

diff --git a/docs/mri.md b/docs/mri.md
index d6edf690c..196b6c68f 100644
--- a/docs/mri.md
+++ b/docs/mri.md
@@ -87,6 +87,47 @@ benchmark.evaluate_model(
 )
 ```
 
+### 3b. Adding Models Without Immediate Submission
+
+If you want to add a model and control when it is submitted for evaluation, use `add_model` instead of `evaluate_model`. This lets you upload media, inspect the participant, and submit on your own schedule.
+
+```python
+# Add a model without submitting
+participant = benchmark.add_model(
+    name="MyAIModel_v2.1",
+    media=[
+        "https://assets.rapidata.ai/mountain_sunset1.png",
+        "https://assets.rapidata.ai/futuristic_city.png",
+        "https://assets.rapidata.ai/wizard_portrait.png"
+    ],
+    prompts=[
+        "A serene mountain landscape at sunset",
+        "A futuristic city with flying cars",
+        "A portrait of a wise old wizard"
+    ]
+)
+
+# Upload additional media to the same participant
+participant.upload_media(
+    assets=["https://assets.rapidata.ai/mountain_sunset2.png"],
+    identifiers=["A serene mountain landscape at sunset"]
+)
+
+# Submit the individual participant
+participant.run()
+
+# Or submit all unsubmitted participants at once
+benchmark.run()
+```
+
+You can also inspect existing participants:
+
+```python
+# List all participants
+for p in benchmark.participants:
+    print(p.name, p.status)
+```
+
 ### 4. Matchmaking and Ranking
 MRI creates fair comparisons by:
 
diff --git a/docs/mri_advanced.md b/docs/mri_advanced.md
index 47e1023f6..ff1b2f839 100644
--- a/docs/mri_advanced.md
+++ b/docs/mri_advanced.md
@@ -132,8 +132,39 @@ leaderboard = benchmark.create_leaderboard(
 )
 ```
 
+## Participant Management
+
+### Listing Participants
+
+You can list all participants in a benchmark using the `participants` property:
+
+```python
+for participant in benchmark.participants:
+    print(f"{participant.name} - {participant.status}")
+```
+
+### Submitting Participants
+
+When using `add_model`, participants are created in the `CREATED` state and are not yet submitted for evaluation. You can submit them individually or in bulk:
+
+```python
+# Submit a single participant
+participant = benchmark.add_model(
+    name="ModelA",
+    media=["https://example.com/img1.png"],
+    identifiers=["scene_1"]
+)
+participant.run()
+
+# Or add multiple models and submit them all at once
+benchmark.add_model(name="ModelB", media=["https://example.com/img2.png"], identifiers=["scene_1"])
+benchmark.add_model(name="ModelC", media=["https://example.com/img3.png"], identifiers=["scene_1"])
+benchmark.run()  # Submits all participants in CREATED state
+```
+
 ## References
 - [RapidataBenchmarkManager](/reference/rapidata/rapidata_client/benchmark/rapidata_benchmark_manager/)
 - [RapidataBenchmark](/reference/rapidata/rapidata_client/benchmark/rapidata_benchmark/)
 - [RapidataLeaderboard](/reference/rapidata/rapidata_client/benchmark/leaderboard/rapidata_leaderboard/)
+- [BenchmarkParticipant](/reference/rapidata/rapidata_client/benchmark/participant/participant/)
 
diff --git a/src/rapidata/api_client/models/create_benchmark_participant_result.py b/src/rapidata/api_client/models/create_benchmark_participant_result.py
index 456ae5bb3..f11793b0d 100644
--- a/src/rapidata/api_client/models/create_benchmark_participant_result.py
+++ b/src/rapidata/api_client/models/create_benchmark_participant_result.py
@@ -1,14 +1,14 @@
 # coding: utf-8
 
 """
-    Rapidata Asset API
+Rapidata Asset API
 
-    The API for the Rapidata Asset service
+The API for the Rapidata Asset service
 
-    The version of the OpenAPI document: v1
-    Generated by OpenAPI Generator (https://openapi-generator.tech)
+The version of the OpenAPI document: v1
+Generated by OpenAPI Generator (https://openapi-generator.tech)
 
-    Do not edit the class manually.
+Do not edit the class manually.
 """  # noqa: E501
 
 
@@ -22,10 +22,12 @@
 from typing import Optional, Set
 from typing_extensions import Self
 
+
 class CreateBenchmarkParticipantResult(BaseModel):
     """
     CreateBenchmarkParticipantResult
-    """ # noqa: E501
+    """  # noqa: E501
+
     participant_id: StrictStr = Field(alias="participantId")
     dataset_id: Optional[StrictStr] = Field(default=None, alias="datasetId")
     __properties: ClassVar[List[str]] = ["participantId", "datasetId"]
@@ -36,7 +38,6 @@ class CreateBenchmarkParticipantResult(BaseModel):
         protected_namespaces=(),
     )
 
-
     def to_str(self) -> str:
         """Returns the string representation of the model using alias"""
         return pprint.pformat(self.model_dump(by_alias=True))
@@ -61,8 +62,7 @@ def to_dict(self) -> Dict[str, Any]:
           were set at model initialization. Other fields with value `None`
           are ignored.
         """
-        excluded_fields: Set[str] = set([
-        ])
+        excluded_fields: Set[str] = set([])
 
         _dict = self.model_dump(
             by_alias=True,
@@ -80,10 +80,10 @@ def from_dict(cls, obj: Optional[Dict[str, Any]]) -> Optional[Self]:
         if not isinstance(obj, dict):
             return cls.model_validate(obj)
 
-        _obj = cls.model_validate({
-            "participantId": obj.get("participantId"),
-            "datasetId": obj.get("datasetId")
-        })
+        _obj = cls.model_validate(
+            {
+                "participantId": obj.get("participantId"),
+                "datasetId": obj.get("datasetId"),
+            }
+        )
         return _obj
-
-
diff --git a/src/rapidata/rapidata_client/benchmark/participant/_participant.py b/src/rapidata/rapidata_client/benchmark/participant/participant.py
similarity index 76%
rename from src/rapidata/rapidata_client/benchmark/participant/_participant.py
rename to src/rapidata/rapidata_client/benchmark/participant/participant.py
index 999aff00a..b6af67376 100644
--- a/src/rapidata/rapidata_client/benchmark/participant/_participant.py
+++ b/src/rapidata/rapidata_client/benchmark/participant/participant.py
@@ -2,6 +2,7 @@
 
 from concurrent.futures import ThreadPoolExecutor, as_completed
 import time
+from typing import TYPE_CHECKING
 from tqdm.auto import tqdm
 
 from rapidata.rapidata_client.config import logger
@@ -16,13 +17,59 @@
 
 from rapidata.service.openapi_service import OpenAPIService
 
+if TYPE_CHECKING:
+    from rapidata.api_client.models.participant_status import ParticipantStatus
+
 
 class BenchmarkParticipant:
-    def __init__(self, name: str, id: str, openapi_service: OpenAPIService):
+    """A participant (model) in a benchmark evaluation.
+
+    Represents a model that has been added to a benchmark for evaluation.
+    Provides methods to upload media and submit the participant for evaluation.
+
+    Args:
+        name: The name of the participant/model.
+        id: The unique identifier of the participant.
+        openapi_service: The OpenAPI service for API communication.
+        status: The current status of the participant.
+    """
+
+    def __init__(
+        self,
+        name: str,
+        id: str,
+        openapi_service: OpenAPIService,
+        status: ParticipantStatus = ParticipantStatus.CREATED,
+    ):
         self.name = name
         self.id = id
         self._openapi_service = openapi_service
         self._asset_uploader = AssetUploader(openapi_service)
+        self._status = status
+
+    @property
+    def status(self) -> ParticipantStatus | None:
+        """The current status of the participant."""
+        return self._status
+
+    def run(self) -> None:
+        """Submits the participant for evaluation.
+
+        After uploading media, call this method to submit the participant
+        so that it enters the evaluation pipeline.
+        """
+        from rapidata.api_client.models.participant_status import ParticipantStatus
+
+        self._openapi_service.participant_api.participants_participant_id_submit_post(
+            participant_id=self.id
+        )
+        self._status = ParticipantStatus.SUBMITTED
+
+    def __str__(self) -> str:
+        return f"BenchmarkParticipant(name={self.name}, id={self.id}, status={self._status})"
+
+    def __repr__(self) -> str:
+        return self.__str__()
 
     def _process_single_sample_upload(
         self,
diff --git a/src/rapidata/rapidata_client/benchmark/rapidata_benchmark.py b/src/rapidata/rapidata_client/benchmark/rapidata_benchmark.py
index 2d6993189..9195beb8c 100644
--- a/src/rapidata/rapidata_client/benchmark/rapidata_benchmark.py
+++ b/src/rapidata/rapidata_client/benchmark/rapidata_benchmark.py
@@ -11,6 +11,9 @@
     from rapidata.rapidata_client.benchmark.leaderboard.rapidata_leaderboard import (
         RapidataLeaderboard,
     )
+    from rapidata.rapidata_client.benchmark.participant.participant import (
+        BenchmarkParticipant,
+    )
     from rapidata.rapidata_client.filter import RapidataFilter
     from rapidata.rapidata_client.settings import RapidataSetting
     from rapidata.service.openapi_service import OpenAPIService
@@ -39,6 +42,7 @@ def __init__(self, name: str, id: str, openapi_service: OpenAPIService):
         self.__leaderboards: list["RapidataLeaderboard"] = []
         self.__identifiers: list[str] = []
         self.__tags: list[list[str]] = []
+        self.__participants: list[BenchmarkParticipant] = []
         self.__benchmark_page: str = (
             f"https://app.{self._openapi_service.environment}/mri/benchmarks/{self.id}"
         )
@@ -184,6 +188,31 @@ def leaderboards(self) -> list[RapidataLeaderboard]:
 
             return self.__leaderboards
 
+    @property
+    def participants(self) -> list[BenchmarkParticipant]:
+        """Returns the participants that are registered for the benchmark."""
+        from rapidata.rapidata_client.benchmark.participant.participant import (
+            BenchmarkParticipant,
+        )
+
+        with tracer.start_as_current_span("RapidataBenchmark.participants"):
+            if not self.__participants:
+                result = self._openapi_service.benchmark_api.benchmark_benchmark_id_participants_get(
+                    benchmark_id=self.id,
+                )
+
+                self.__participants = [
+                    BenchmarkParticipant(
+                        name=p.name,
+                        id=p.id,
+                        openapi_service=self._openapi_service,
+                        status=p.status,
+                    )
+                    for p in result.items
+                ]
+
+            return self.__participants
+
     def add_prompt(
         self,
         identifier: str | None = None,
@@ -419,7 +448,7 @@ def evaluate_model(
         from rapidata.api_client.models.create_benchmark_participant_model import (
             CreateBenchmarkParticipantModel,
         )
-        from rapidata.rapidata_client.benchmark.participant._participant import (
+        from rapidata.rapidata_client.benchmark.participant.participant import (
             BenchmarkParticipant,
         )
 
@@ -497,6 +526,131 @@ def evaluate_model(
                     participant_id=participant_result.participant_id
                 )
 
+    def add_model(
+        self,
+        name: str,
+        media: list[str],
+        identifiers: list[str] | None = None,
+        prompts: list[str] | None = None,
+    ) -> BenchmarkParticipant:
+        """Adds a model to the benchmark without immediately submitting it for evaluation.
+
+        This method creates a participant, uploads media, but does NOT submit the participant.
+        Use `participant.run()` or `benchmark.run()` to submit afterwards.
+
+        Args:
+            name: The name of the model.
+            media: The generated images/videos that will be used to evaluate the model.
+            identifiers: The identifiers that correspond to the media. The order of the identifiers must match the order of the media.\n
+                The identifiers that are used must be registered for the benchmark. To see the registered identifiers, use the identifiers property.
+            prompts: The prompts that correspond to the media. The order of the prompts must match the order of the media.
+
+        Returns:
+            The created BenchmarkParticipant instance.
+        """
+        from rapidata.api_client.models.create_benchmark_participant_model import (
+            CreateBenchmarkParticipantModel,
+        )
+        from rapidata.api_client.models.participant_status import ParticipantStatus
+        from rapidata.rapidata_client.benchmark.participant.participant import (
+            BenchmarkParticipant,
+        )
+
+        with tracer.start_as_current_span("add_model"):
+            if not media:
+                raise ValueError("Media must be a non-empty list of strings")
+
+            if not identifiers and not prompts:
+                raise ValueError("Identifiers or prompts must be provided.")
+
+            if identifiers and prompts:
+                raise ValueError(
+                    "Identifiers and prompts cannot be provided at the same time. Use one or the other."
+                )
+
+            if not identifiers:
+                assert prompts is not None
+                identifiers = prompts
+
+            if len(media) != len(identifiers):
+                raise ValueError(
+                    "Media and identifiers/prompts must have the same length"
+                )
+
+            if not all(identifier in self.identifiers for identifier in identifiers):
+                raise ValueError(
+                    "All identifiers/prompts must be in the registered identifiers/prompts list. To see the registered identifiers/prompts, use the identifiers/prompts property."
+                )
+
+            participant_result = self._openapi_service.benchmark_api.benchmark_benchmark_id_participants_post(
+                benchmark_id=self.id,
+                create_benchmark_participant_model=CreateBenchmarkParticipantModel(
+                    name=name,
+                ),
+            )
+
+            logger.info(f"Participant created: {participant_result.participant_id}")
+
+            participant = BenchmarkParticipant(
+                name,
+                participant_result.participant_id,
+                self._openapi_service,
+            )
+
+            with tracer.start_as_current_span("upload_media_for_participant"):
+                logger.info(
+                    f"Uploading {len(media)} media assets to participant {participant.id}"
+                )
+
+                successful_uploads, failed_uploads = participant.upload_media(
+                    media,
+                    identifiers,
+                )
+
+                total_uploads = len(media)
+                success_rate = (
+                    (len(successful_uploads) / total_uploads * 100)
+                    if total_uploads > 0
+                    else 0
+                )
+                logger.info(
+                    f"Upload complete: {len(successful_uploads)} successful, {len(failed_uploads)} failed ({success_rate:.1f}% success rate)"
+                )
+
+                if failed_uploads:
+                    logger.error(f"Failed uploads for media: {failed_uploads}")
+                    logger.warning(
+                        "Some uploads failed. The model evaluation may be incomplete."
+                    )
+
+                if len(successful_uploads) == 0:
+                    raise RuntimeError(
+                        "No uploads were successful. The model evaluation will not be completed."
+                    )
+
+            # Clear cache so next access re-fetches
+            self.__participants = []
+
+            return participant
+
+    def run(self) -> None:
+        """Submits all participants that are in `CREATED` state.
+
+        This is a convenience method to submit all unsubmitted participants at once.
+        """
+        from rapidata.api_client.models.participant_status import ParticipantStatus
+
+        with tracer.start_as_current_span("RapidataBenchmark.run"):
+            created = [
+                p for p in self.participants if p.status == ParticipantStatus.CREATED
+            ]
+            logger.info(f"Submitting {len(created)} participants in CREATED state")
+            for participant in created:
+                participant.run()
+
+            # Clear cache so next access re-fetches
+            self.__participants = []
+
     def view(self) -> None:
         """
         Views the benchmark.
diff --git a/src/rapidata/types/__init__.py b/src/rapidata/types/__init__.py
index 481e03455..acf18b6d3 100644
--- a/src/rapidata/types/__init__.py
+++ b/src/rapidata/types/__init__.py
@@ -15,6 +15,9 @@
 from rapidata.rapidata_client.benchmark.leaderboard.rapidata_leaderboard import (
     RapidataLeaderboard,
 )
+from rapidata.rapidata_client.benchmark.participant.participant import (
+    BenchmarkParticipant,
+)
 
 # Selection Types
 from rapidata.rapidata_client.selection.ab_test_selection import AbTestSelection
@@ -97,6 +100,7 @@
     "RapidataBenchmark",
     "RapidataBenchmarkManager",
     "RapidataLeaderboard",
+    "BenchmarkParticipant",
     # Selection Types
     "AbTestSelection",
     "CappedSelection",

From dd1acf7d33d0419d26aeb87c7bbca94b48c08bed Mon Sep 17 00:00:00 2001
From: Lino Giger <68745352+LinoGiger@users.noreply.github.com>
Date: Tue, 24 Feb 2026 10:33:51 +0100
Subject: [PATCH 2/4] fixed bug

---
 .../rapidata_client/benchmark/participant/participant.py   | 7 +------
 1 file changed, 1 insertion(+), 6 deletions(-)

diff --git a/src/rapidata/rapidata_client/benchmark/participant/participant.py b/src/rapidata/rapidata_client/benchmark/participant/participant.py
index b6af67376..33e1209b6 100644
--- a/src/rapidata/rapidata_client/benchmark/participant/participant.py
+++ b/src/rapidata/rapidata_client/benchmark/participant/participant.py
@@ -2,7 +2,6 @@
 
 from concurrent.futures import ThreadPoolExecutor, as_completed
 import time
-from typing import TYPE_CHECKING
 from tqdm.auto import tqdm
 
 from rapidata.rapidata_client.config import logger
@@ -16,9 +15,7 @@
 
 
 from rapidata.service.openapi_service import OpenAPIService
-
-if TYPE_CHECKING:
-    from rapidata.api_client.models.participant_status import ParticipantStatus
+from rapidata.api_client.models.participant_status import ParticipantStatus
 
 
 class BenchmarkParticipant:
@@ -58,8 +55,6 @@ def run(self) -> None:
         After uploading media, call this method to submit the participant
         so that it enters the evaluation pipeline.
         """
-        from rapidata.api_client.models.participant_status import ParticipantStatus
-
         self._openapi_service.participant_api.participants_participant_id_submit_post(
             participant_id=self.id
         )

From 17fa29097c174996f3fd07ef74aa47540db224c9 Mon Sep 17 00:00:00 2001
From: Lino Giger <68745352+LinoGiger@users.noreply.github.com>
Date: Tue, 24 Feb 2026 10:47:31 +0100
Subject: [PATCH 3/4] small fixes

---
 docs/mri_advanced.md                          |  8 +-
 .../benchmark/participant/participant.py      |  2 +-
 .../benchmark/rapidata_benchmark.py           | 84 ++-----------------
 3 files changed, 11 insertions(+), 83 deletions(-)

diff --git a/docs/mri_advanced.md b/docs/mri_advanced.md
index ff1b2f839..995a3a187 100644
--- a/docs/mri_advanced.md
+++ b/docs/mri_advanced.md
@@ -12,7 +12,7 @@ In the MRI quickstart we used the prompts to identify the media and create the a
 
 ```python
 # Example 1: Explicit identifiers
-benchmark = benchmark_manager.create_new_benchmark(
+benchmark = client.mri.create_new_benchmark(
     name="Preference Benchmark",
     identifiers=["scene_1", "scene_2", "scene_3"],
     prompts=[
@@ -28,7 +28,7 @@ benchmark = benchmark_manager.create_new_benchmark(
 )
 
 # Example 2: Identifiers used for the same prompts but different seeding
-benchmark = benchmark_manager.create_new_benchmark(
+benchmark = client.mri.create_new_benchmark(
     name="Preference Benchmark",
     identifiers=["seed_1", "seed_2", "seed_3"],
     prompts=["prompt_1", "prompt_1", "prompt_1"],
@@ -36,7 +36,7 @@ benchmark = benchmark_manager.create_new_benchmark(
 )
 
 # Example 3: Using only prompt assets
-benchmark = benchmark_manager.create_new_benchmark(
+benchmark = client.mri.create_new_benchmark(
     name="Preference Benchmark",
     identifiers=["image_1", "image_2", "image_3"],   
     prompt_assets=["https://example.com/asset1.jpg", "https://example.com/asset2.jpg", "https://example.com/asset3.jpg"]
@@ -58,7 +58,7 @@ tags = [
     ["indoor", "vehicle"]
 ]
 
-benchmark = benchmark_manager.create_new_benchmark(
+benchmark = client.mri.create_new_benchmark(
     name="Tagged Benchmark",
     identifiers=["scene_1", "scene_2", "scene_3", "scene_4"],
     prompts=["A sunny beach", "A mountain landscape", "A city skyline", "A car in a garage"],
diff --git a/src/rapidata/rapidata_client/benchmark/participant/participant.py b/src/rapidata/rapidata_client/benchmark/participant/participant.py
index 33e1209b6..c74e4ace3 100644
--- a/src/rapidata/rapidata_client/benchmark/participant/participant.py
+++ b/src/rapidata/rapidata_client/benchmark/participant/participant.py
@@ -45,7 +45,7 @@ def __init__(
         self._status = status
 
     @property
-    def status(self) -> ParticipantStatus | None:
+    def status(self) -> ParticipantStatus:
         """The current status of the participant."""
         return self._status
 
diff --git a/src/rapidata/rapidata_client/benchmark/rapidata_benchmark.py b/src/rapidata/rapidata_client/benchmark/rapidata_benchmark.py
index 9195beb8c..053fbe022 100644
--- a/src/rapidata/rapidata_client/benchmark/rapidata_benchmark.py
+++ b/src/rapidata/rapidata_client/benchmark/rapidata_benchmark.py
@@ -445,86 +445,14 @@ def evaluate_model(
                 The identifiers that are used must be registered for the benchmark. To see the registered identifiers, use the identifiers property.
             prompts: The prompts that correspond to the media. The order of the prompts must match the order of the media.
         """
-        from rapidata.api_client.models.create_benchmark_participant_model import (
-            CreateBenchmarkParticipantModel,
-        )
-        from rapidata.rapidata_client.benchmark.participant.participant import (
-            BenchmarkParticipant,
-        )
-
         with tracer.start_as_current_span("evaluate_model"):
-            if not media:
-                raise ValueError("Media must be a non-empty list of strings")
-
-            if not identifiers and not prompts:
-                raise ValueError("Identifiers or prompts must be provided.")
-
-            if identifiers and prompts:
-                raise ValueError(
-                    "Identifiers and prompts cannot be provided at the same time. Use one or the other."
-                )
-
-            if not identifiers:
-                assert prompts is not None
-                identifiers = prompts
-
-            if len(media) != len(identifiers):
-                raise ValueError(
-                    "Media and identifiers/prompts must have the same length"
-                )
-
-            if not all(identifier in self.identifiers for identifier in identifiers):
-                raise ValueError(
-                    "All identifiers/prompts must be in the registered identifiers/prompts list. To see the registered identifiers/prompts, use the identifiers/prompts property."
-                )
-
-            participant_result = self._openapi_service.benchmark_api.benchmark_benchmark_id_participants_post(
-                benchmark_id=self.id,
-                create_benchmark_participant_model=CreateBenchmarkParticipantModel(
-                    name=name,
-                ),
+            participant = self.add_model(
+                name=name,
+                media=media,
+                identifiers=identifiers,
+                prompts=prompts,
             )
-
-            logger.info(f"Participant created: {participant_result.participant_id}")
-
-            participant = BenchmarkParticipant(
-                name, participant_result.participant_id, self._openapi_service
-            )
-
-            with tracer.start_as_current_span("upload_media_for_participant"):
-                logger.info(
-                    f"Uploading {len(media)} media assets to participant {participant.id}"
-                )
-
-                successful_uploads, failed_uploads = participant.upload_media(
-                    media,
-                    identifiers,
-                )
-
-                total_uploads = len(media)
-                success_rate = (
-                    (len(successful_uploads) / total_uploads * 100)
-                    if total_uploads > 0
-                    else 0
-                )
-                logger.info(
-                    f"Upload complete: {len(successful_uploads)} successful, {len(failed_uploads)} failed ({success_rate:.1f}% success rate)"
-                )
-
-                if failed_uploads:
-                    logger.error(f"Failed uploads for media: {failed_uploads}")
-                    logger.warning(
-                        "Some uploads failed. The model evaluation may be incomplete."
-                    )
-
-                if len(successful_uploads) == 0:
-                    raise RuntimeError(
-                        "No uploads were successful. The model evaluation will not be completed."
-                    )
-
-                self._openapi_service.participant_api.participants_participant_id_submit_post(
-                    participant_id=participant_result.participant_id
-                )
+            participant.run()
 
     def add_model(
         self,

From 066b30decfd4dcbdb758807c8024a118976fc2cf Mon Sep 17 00:00:00 2001
From: Lino Giger <68745352+LinoGiger@users.noreply.github.com>
Date: Tue, 24 Feb 2026 10:53:31 +0100
Subject: [PATCH 4/4] minor removal of import

---
 .../rapidata_client/benchmark/rapidata_benchmark.py      | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/src/rapidata/rapidata_client/benchmark/rapidata_benchmark.py b/src/rapidata/rapidata_client/benchmark/rapidata_benchmark.py
index 053fbe022..e218b86a8 100644
--- a/src/rapidata/rapidata_client/benchmark/rapidata_benchmark.py
+++ b/src/rapidata/rapidata_client/benchmark/rapidata_benchmark.py
@@ -236,7 +236,7 @@ def add_prompt(
 
         from rapidata.api_client.models.i_asset_input import IAssetInput
 
-        with tracer.start_as_current_span("RapidataBenchmark.add_prompt"):
+        with tracer.start_as_current_span("RapidataBenchmark.add_prompt_to_benchmark"):
             if tags is None:
                 tags = []
 
@@ -350,7 +350,7 @@ def create_leaderboard(
             RapidataLeaderboard,
         )
 
-        with tracer.start_as_current_span("create_leaderboard"):
+        with tracer.start_as_current_span("RapidataBenchmark.create_leaderboard"):
             if level_of_detail is not None and (
                 not isinstance(level_of_detail, str)
                 or level_of_detail not in ["low", "medium", "high", "very high"]
@@ -445,7 +445,7 @@ def evaluate_model(
                 The identifiers that are used must be registered for the benchmark. To see the registered identifiers, use the identifiers property.
             prompts: The prompts that correspond to the media. The order of the prompts must match the order of the media.
         """
-        with tracer.start_as_current_span("evaluate_model"):
+        with tracer.start_as_current_span("RapidataBenchmark.evaluate_model"):
             participant = self.add_model(
                 name=name,
                 media=media,
@@ -479,12 +479,11 @@ def add_model(
         from rapidata.api_client.models.create_benchmark_participant_model import (
             CreateBenchmarkParticipantModel,
         )
-        from rapidata.api_client.models.participant_status import ParticipantStatus
         from rapidata.rapidata_client.benchmark.participant.participant import (
             BenchmarkParticipant,
         )
 
-        with tracer.start_as_current_span("add_model"):
+        with tracer.start_as_current_span("RapidataBenchmark.add_model"):
             if not media:
                 raise ValueError("Media must be a non-empty list of strings")