Skip to content

Pull requests: confident-ai/deepeval

New pull request New
78 Open 1,955 Closed
78 Open 1,955 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Add single-turn, multi-turn, arena and multimodal metrics to typescript
#2745 opened Jun 10, 2026 by A-Vamshi Collaborator Loading…
1
feat(contextual-precision): add RetrievedContextData source grouping and fix weighted precision score
#2743 opened Jun 10, 2026 by Ruthwik-Data Loading…
1
feat: inspect and bound GEval retrieval context prompts
#2742 opened Jun 10, 2026 by RitwijParmar Contributor Loading…
1
1
fix(metrics): reject list params containing only empty strings (#2248)
#2739 opened Jun 9, 2026 by kadiryonak Loading…
1
2
[codex] Add source grouping parity for contextual precision
#2737 opened Jun 9, 2026 by cat0825 Loading…
2
fix: add deepseek-v4 models, fix calculate_cost, and improve error ha…
#2736 opened Jun 9, 2026 by Comui520 Loading…
1
docs: add CometAPI custom provider example for GPTModel
#2733 opened Jun 8, 2026 by nuthalapativarun Contributor Loading…
1
1
Add regression testing on CI/CD
#2731 opened Jun 8, 2026 by A-Vamshi Collaborator Loading…
1
[codex] Add contextual precision grouping
#2729 opened Jun 8, 2026 by cat0825 Loading…
1
2
[codex] Fix flaky retry test run dedupe
#2728 opened Jun 8, 2026 by cat0825 • Draft
1
1
feat(examples): add TWZRD Agent Intel MCP server evaluation example
#2727 opened Jun 6, 2026 by twzrd-sol Loading…
1
fix(dataset): assign each golden its index as _dataset_rank, not the dataset size
#2726 opened Jun 5, 2026 by bymle Loading…
1
Add BGPT REFUTE benchmark
#2725 opened Jun 5, 2026 by connerlambden Loading…
2
Fix gemini costs
#2724 opened Jun 5, 2026 by A-Vamshi Collaborator Loading…
1
Fix LiteLLM cost calculation (was 666× over for common models)
#2723 opened Jun 4, 2026 by Aarkin7 Contributor Loading…
1
Add optional juryeval integration for LLM-as-Judge metrics
#2715 opened May 31, 2026 by py-ai-dev Loading…
1
fix: loosen opentelemetry version constraint to allow 1.x and 2.x
#2712 opened May 29, 2026 by nuthalapativarun Contributor Loading…
1
2
feat: add return_details param to compare() for per-test-case verdicts
#2711 opened May 29, 2026 by nuthalapativarun Contributor Loading…
1
1
fix: use correct confinement instructions for ARC questions with numeric labels
#2710 opened May 29, 2026 by nuthalapativarun Contributor Loading…
1
1
fix: restore deepeval.evaluate subpackage binding shadowed by _expose_public_api
#2706 opened May 29, 2026 by nuthalapativarun Contributor Loading…
4 tasks done
1
1
feat: expose score_breakdown in StepEfficiencyMetric
#2705 opened May 29, 2026 by nuthalapativarun Contributor Loading…
3 tasks
1
1
feat: add penalize_ambiguous_claims to HallucinationMetric
#2704 opened May 29, 2026 by nuthalapativarun Contributor Loading…
3 tasks
1
feat: add o3 and o3-2025-04-16 model constants
#2702 opened May 29, 2026 by nuthalapativarun Contributor Loading…
2 tasks
1
test(metrics): add overlapping-chunk test fixtures for ContextualPrecisionMetric
#2692 opened May 26, 2026 by Ruthwik-Data Loading…
3
Fix misuse, MCP use, and tool correctness docs
#2691 opened May 25, 2026 by krishna-dhulipalla Loading…
1
ProTip! no:milestone will show everything without a milestone.