FeedbackQA
Models answer questions using a document collection and learn from written feedback about earlier answers.
MTEB measures whether the top retrieved passage is relevant.
- Made by
- Zichao Li and colleagues
- Released
- April 2022
- Kind
- Questions that need search
- Level
- School
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
GritLM/GritLM-7B tops the leaderboard with 59.7%
Best score per entry from MTEB’s leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders.
- 59.7 GritLM/GritLM-7B
- 57.4 intfloat/e5-mistral-7b-instruct
- 56.0 manveertamber/cadet-embed-base-v1
- 55.0 intfloat/multilingual-e5-large
- 55.0 VPLabs/SearchMap_Preview
- 54.5 intfloat/multilingual-e5-large-instruct
- 48.2 intfloat/multilingual-e5-base
- 47.8 intfloat/multilingual-e5-small
- 46.9 sentence-transformers/all-MiniLM-L12-v2
- 42.1 sentence-transformers/all-mpnet-base-v2
- 42.0 sentence-transformers/all-MiniLM-L6-v2
- 39.7 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2
- 38.6 sentence-transformers/paraphrase-multilingual-mpnet-base-v2
- 19.0 sergeyzh/rubert-tiny-turbo
- 17.2 sentence-transformers/LaBSE
- 1 GritLM/GritLM-7B 59.7%
- 2 intfloat/e5-mistral-7b-instruct 57.4%
- 3 manveertamber/cadet-embed-base-v1 56%
- 4 intfloat/multilingual-e5-large 55%
- 5 VPLabs/SearchMap_Preview 55%
- 6 intfloat/multilingual-e5-large-instruct 54.5%
- 7 intfloat/multilingual-e5-base 48.2%
- 8 intfloat/multilingual-e5-small 47.8%
- 9 sentence-transformers/all-MiniLM-L12-v2 46.9%
- 10 sentence-transformers/all-mpnet-base-v2 42.1%
- 11 sentence-transformers/all-MiniLM-L6-v2 42%
- 12 sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 39.7%
- 13 sentence-transformers/paraphrase-multilingual-mpnet-base-v2 38.6%
- 14 sergeyzh/rubert-tiny-turbo 19%
- 15 sentence-transformers/LaBSE 17.2%
Source: MTEB’s leaderboard
| # | Entry | Score | Setting | Date | Link | Source |
|---|---|---|---|---|---|---|
| 1 | GritLM/GritLM-7B open weights, 7.2B | 59.7% | huggingface.co | Official leaderboard | ||
| 2 | intfloat/e5-mistral-7b-instruct open weights, 7.1B | 57.4% | huggingface.co | Official leaderboard | ||
| 3 | manveertamber/cadet-embed-base-v1 open weights, 0.1B | 56% | huggingface.co | Official leaderboard | ||
| 4 | intfloat/multilingual-e5-large open weights, 0.6B | 55% | huggingface.co | Official leaderboard | ||
| 5 | VPLabs/SearchMap_Preview open weights, 0.4B | 55% | huggingface.co | Official leaderboard | ||
| 6 | intfloat/multilingual-e5-large-instruct open weights, 0.6B | 54.5% | huggingface.co | Official leaderboard | ||
| 7 | intfloat/multilingual-e5-base open weights, 0.3B | 48.2% | huggingface.co | Official leaderboard | ||
| 8 | intfloat/multilingual-e5-small open weights, 0.1B | 47.8% | huggingface.co | Official leaderboard | ||
| 9 | sentence-transformers/all-MiniLM-L12-v2 open weights, 0B | 46.9% | huggingface.co | Official leaderboard | ||
| 10 | sentence-transformers/all-mpnet-base-v2 open weights, 0.1B | 42.1% | huggingface.co | Official leaderboard | ||
| 11 | sentence-transformers/all-MiniLM-L6-v2 open weights, 0B | 42% | huggingface.co | Official leaderboard | ||
| 12 | sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 open weights, 0.1B | 39.7% | huggingface.co | Official leaderboard | ||
| 13 | sentence-transformers/paraphrase-multilingual-mpnet-base-v2 open weights, 0.3B | 38.6% | huggingface.co | Official leaderboard | ||
| 14 | sergeyzh/rubert-tiny-turbo open weights, 0B | 19% | huggingface.co | Official leaderboard | ||
| 15 | sentence-transformers/LaBSE open weights, 0.5B | 17.2% | huggingface.co | Official leaderboard |
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Knowledge
- MMLU-Pro In use Harder 10-option version of MMLU with reasoning-focused questions across 14 subjects.
Intern-S2-397B 89.8%
- MMLU In use 57-subject multiple-choice exam questions from elementary to professional level. Scored by accuracy.
Seed1.8 92.3%
- SuperGPQA In use 26,529 graduate-level multiple-choice questions across 285 disciplines. Accuracy.
Qwen 3.6 Max (Preview) 73.9%
- WideSearch In use 200 bilingual broad info-seeking tasks: agent collects many atomic facts into a table. Scored by success rate and row/item F1.
Tencent Hy4 preview 83.9%
- BBEH micro average In use Models solve harder replacements for each of the 23 BIG-Bench Hard tasks, 4,520 examples in total. The score is the share of all examples answered correctly.
Gemma 4 31B IT 74.4%
- HLE-Diamond In use Models answer 1,000 cleaned expert questions from Humanity's Last Exam, 500 on reasoning and 500 on knowledge, closed book. Graded on exact answers. Claude Fable 5.2 77.9%
Data audit
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the official leaderboard (15 entries).
- Pass Models scored 15 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom No scores yet.
Leaderboard import 3 pass
- Pass Importer We read the board on MTEB: 15 entries at the last read, none a model we track.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.