Add DeepSeek benchmark coverage for v0.2.3 - #17
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
This PR is the second
v0.2.3slice for evaluating the new DeepSeek provider in the existing local benchmark workflow.The main goal is to extend the benchmark runner so the same benchmark input can be compared across:
heuristicspacyllm:ollamallm:mistralllm:deepseekIncluded
adds DeepSeek support to the local benchmark runner
benchmark/run_benchmark.pyso--provider deepseekis acceptedvalidates DeepSeek on the existing 100-sample TechQA benchmark input
heuristic:1497 concepts / 1973 mentions / 0 emptyspacy:649 concepts / 870 mentions / 0 emptyllm:ollama:qwen3.5:4b:374 concepts / 411 mentions / 0 emptyllm:mistral:mistral-small:297 concepts / 319 mentions / 14 emptyllm:deepseek:deepseek-chat:352 concepts / 386 mentions / 5 emptyconfirms DeepSeek's current position in the provider set
heuristicandspacymistral-smallrunollamain concept density while still remaining selectiveValidation
Repository checks:
.venv/bin/pytest -q tests/test_benchmark.py.venv/bin/ruff check benchmark/run_benchmark.py tests/test_benchmark.py.venv/bin/pyright benchmark/run_benchmark.py tests/test_benchmark.pyLive benchmark checks:
deepseek-chatagainst the existing 100-sample TechQA benchmark inputheuristic / spacy / ollama / mistralrunsNotes
experiment/and are intentionally not version-controlledrelease/0.2.3-prepslice