InstructIR
Models find documents that satisfy a user's search request and its accompanying instructions.
The benchmark varies the instruction for a query to test how the ranking changes.
- Made by
- Hanseok Oh and colleagues
- Released
- February 2024
- Kind
- Questions that need search
- Level
- School
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
E5-mistral-7b-instruct tops the leaderboard with 55.4
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.
- 1 E5-mistral-7b-instruct Zero-shot 55.4
- 2 RepLLaMa Zero-shot 52.6
- 3 TART-dual Zero-shot 47.5
- 4 Contriever-msmarco Zero-shot 47.4
- 5 GTR-XL Zero-shot 38.3
- 6 GTR-large Zero-shot 37.6
- 7 GTR-base Zero-shot 34.1
- 8 INSTRUCTOR-base Zero-shot 23.7
- 9 INSTRUCTOR-large Zero-shot 22.1
- 10 INSTRUCTOR-XL Zero-shot 21.5
- 11 ColBERT-v2.0 Zero-shot 14.2
Source: The InstructIR paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | E5-mistral-7b-instruct 7B | 55.4 | Zero-shot | Official leaderboard | |
| 2 | RepLLaMa 7B | 52.6 | Zero-shot | Official leaderboard | |
| 3 | TART-dual 0.1B | 47.5 | Zero-shot | Official leaderboard | |
| 4 | Contriever-msmarco 0.1B | 47.4 | Zero-shot | Official leaderboard | |
| 5 | GTR-XL 1.5B | 38.3 | Zero-shot | Official leaderboard | |
| 6 | GTR-large 0.3B | 37.6 | Zero-shot | Official leaderboard | |
| 7 | GTR-base 0.1B | 34.1 | Zero-shot | Official leaderboard | |
| 8 | INSTRUCTOR-base 0.1B | 23.7 | Zero-shot | Official leaderboard | |
| 9 | INSTRUCTOR-large 0.3B | 22.1 | Zero-shot | Official leaderboard | |
| 10 | INSTRUCTOR-XL 1.5B | 21.5 | Zero-shot | Official leaderboard | |
| 11 | ColBERT-v2.0 0.1B | 14.2 | Zero-shot | 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 benchmark’s paper (11 entries).
- Pass Models scored 11 entries on its leaderboard, none a model we track.
- Note Newest score No scores yet.
- Note Frontier models No models scored yet.
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 11 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.