mFollowIR
Models rank documents according to a search instruction across multiple languages.
The benchmark tests whether a change in instructions changes which documents rank highly.
- Made by
- Orion Weller and colleagues
- Released
- January 2025
- Kind
- Questions that need search
- Level
- University
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Based on
- FollowIR
- Last model added
- September 2023
- Scores refreshed
- November 20th, 2026
Promptriever-Llama3.1 tops the leaderboard with 10.4 Mistral-7B-Instruct-v0.1 leads with 5.40
Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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. The best model we track is Mistral-7B-Instruct-v0.1, at 5.40. This view shows only models we track, each at its best.
- 10.4 Promptriever-Llama3.1
- 7.70 FollowIR-7B
- 7.70 Promptriever-Llama2
- 5.90 mT5-13B-mmarco-100k
- 5.40
Mistral-7B-Instruct-v0.1
- 4.50 BGE-reranker-v2-m3
- 1.60 GritLM-7B
- 1.00 E5-Mistral-Instruct-7B
- 0.20 Jina-reranker-v2-multi
- -0.20 Nomic-Embed
- -0.30 GTE-multilingual-base
- -0.80 RepLLaMA
- -0.90 mE5-base
- -2.20 mContriever-msmarco
- -2.40 SFR-Embedding-2-R
- -2.50 mE5-small
- -3.10 mDPR-tied-PFT
- -3.40 mE5-large
- 1 Promptriever-Llama3.1 Cross-lingual 10.4
- 2 FollowIR-7B Multilingual 7.70
- 3 Promptriever-Llama2 Cross-lingual 7.70
- 4 mT5-13B-mmarco-100k Multilingual 5.90
- 5
Mistral-7B-Instruct-v0.1 Cross-lingual 5.40
- 6 BGE-reranker-v2-m3 Multilingual 4.50
- 7 GritLM-7B Cross-lingual 1.60
- 8 E5-Mistral-Instruct-7B Cross-lingual 1.00
- 9 Jina-reranker-v2-multi Multilingual 0.20
- 10 Nomic-Embed Multilingual -0.20
- 11 GTE-multilingual-base Multilingual -0.30
- 12 RepLLaMA Cross-lingual -0.80
- 13 mE5-base Cross-lingual -0.90
- 14 mContriever-msmarco Multilingual -2.20
- 15 SFR-Embedding-2-R Cross-lingual -2.40
- 16 mE5-small Cross-lingual -2.50
- 17 mDPR-tied-PFT Cross-lingual -3.10
- 18 mE5-large Cross-lingual -3.40
Source: The mFollowIR paper
Source: The mFollowIR paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Promptriever-Llama3.1 | 10.4 | Cross-lingual | Official leaderboard | |
| 2 | FollowIR-7B | 7.70 | Multilingual | Official leaderboard | |
| 3 | Promptriever-Llama2 | 7.70 | Cross-lingual | Official leaderboard | |
| 4 | mT5-13B-mmarco-100k | 5.90 | Multilingual | Official leaderboard | |
| 5 | | 5.40 | Cross-lingual | Sep 2023 | Official leaderboard |
| 6 | BGE-reranker-v2-m3 | 4.50 | Multilingual | Official leaderboard | |
| 7 | GritLM-7B | 1.60 | Cross-lingual | Official leaderboard | |
| 8 | E5-Mistral-Instruct-7B | 1.00 | Cross-lingual | Official leaderboard | |
| 9 | Jina-reranker-v2-multi | 0.20 | Multilingual | Official leaderboard | |
| 10 | Nomic-Embed | -0.20 | Multilingual | Official leaderboard | |
| 11 | GTE-multilingual-base | -0.30 | Multilingual | Official leaderboard | |
| 12 | RepLLaMA | -0.80 | Cross-lingual | Official leaderboard | |
| 13 | mE5-base | -0.90 | Cross-lingual | Official leaderboard | |
| 14 | mContriever-msmarco | -2.20 | Multilingual | Official leaderboard | |
| 15 | SFR-Embedding-2-R | -2.40 | Cross-lingual | Official leaderboard | |
| 16 | mE5-small | -2.50 | Cross-lingual | Official leaderboard | |
| 17 | mDPR-tied-PFT | -3.10 | Cross-lingual | Official leaderboard | |
| 18 | mE5-large | -3.40 | Cross-lingual | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 5.40 | Cross-lingual | Sep 2023 | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official mFollowIR 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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 3 years ago, in September 2023, for Mistral-7B-Instruct-v0.1. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (18 entries).
- Pass Models scored 1 model we track, plus 17 other entries on its leaderboard.
- Warning Newest score The newest came 3 years ago, in September 2023, for Mistral-7B-Instruct-v0.1.
- Note Frontier models None of its models are on the capabilities index.
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 2 rows for models we track and 17 other entries at the last read.
- 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.