Benchmark Almanac

TREC Product Search 2025

garamp_rm3_f40d5_w05 0.39 tops its leaderboard
Not in model cards
Version 2025

Models rewrite shopping queries for a search engine. Automatic entries submit one reformulation. Interactive entries can submit four, and the best one counts.

Jeonbuk submitted a search system using Qwen2.5-VL. NIST publishes judgments for 93 query IDs and scores task completion separately from recall.

Released
March 2025
Kind
Questions that need search
Level
Everyday
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Text → Text, Actions
Interaction
Agentic
Environment
APIs and tools
Run by
Anyone
In views
Agents
21
Entries on its own leaderboard, 0 models we track

garamp_rm3_f40d5_w05 tops the leaderboard with 0.39

Best score per entry from the benchmark's own 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.

  1. 1 garamp_rm3_f40d5_w05 0.39
  2. 2 garamp_rm3_v1 0.38
  3. 3 gar_rm3_f120d10w3 0.37
  4. 4 llmbaseline_g27b 0.37
  5. 5 garamp_bm25_v1 0.35
  6. 6 reform_iter10 0.32
  7. 7 reform_iter11 0.32
  8. 8 reform_iter3 0.32
  9. 9 reform_iter9 0.32
  10. 10 multiagent_g27b 0.30
  11. 11 garamp_prf_v1 0.30
  12. 12 reform_iter6_final 0.29
  13. 13 jbnu-s02 0.29
  14. 14 jbnu-s01 0.29
  15. 15 reform_test2 0.28
  16. 16 jbnu-s03 0.27
  17. 17 baseline_run 0.27
  18. 18 bm25 0.27
  19. 19 jbnu-s04 0.25
  20. 20 reform_iter1 0.22
  21. 21 reform_iter8 0.05

Source: Official TREC Product Search 2025 leaderboard

#EntryScoreSettingSubmitted byDateLinkSource
1 garamp_rm3_f40d5_w05 0.39 DUTH trec.nist.gov Official leaderboard
2 garamp_rm3_v1 0.38 DUTH trec.nist.gov Official leaderboard
3 gar_rm3_f120d10w3 0.37 DUTH trec.nist.gov Official leaderboard
4 llmbaseline_g27b 0.37 UIUC trec.nist.gov Official leaderboard
5 garamp_bm25_v1 0.35 DUTH trec.nist.gov Official leaderboard
6 reform_iter10 0.32 Trec-PSRT-Orgs trec.nist.gov Official leaderboard
7 reform_iter11 0.32 Trec-PSRT-Orgs trec.nist.gov Official leaderboard
8 reform_iter3 0.32 Trec-PSRT-Orgs trec.nist.gov Official leaderboard
9 reform_iter9 0.32 Trec-PSRT-Orgs trec.nist.gov Official leaderboard
10 multiagent_g27b 0.30 UIUC trec.nist.gov Official leaderboard
11 garamp_prf_v1 0.30 DUTH trec.nist.gov Official leaderboard
12 reform_iter6_final 0.29 Trec-PSRT-Orgs trec.nist.gov Official leaderboard
13 jbnu-s02 0.29 jbnu trec.nist.gov Official leaderboard
14 jbnu-s01 0.29 jbnu trec.nist.gov Official leaderboard
15 reform_test2 0.28 Trec-PSRT-Orgs trec.nist.gov Official leaderboard
16 jbnu-s03 0.27 jbnu trec.nist.gov Official leaderboard
17 baseline_run 0.27 UIUC trec.nist.gov Official leaderboard
18 bm25 0.27 Trec-PSRT-Orgs trec.nist.gov Official leaderboard
19 jbnu-s04 0.25 jbnu trec.nist.gov Official leaderboard
20 reform_iter1 0.22 Trec-PSRT-Orgs trec.nist.gov Official leaderboard
21 reform_iter8 0.05 Trec-PSRT-Orgs trec.nist.gov 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.

Versions

More in Knowledge

All 332 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 (21 entries).
  • Pass Models scored 21 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 trec.nist.gov: 21 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.

How we check