JudgerBench
Version Original
Judge models assess candidate answers. The leaderboard reports English and Chinese results, accuracy, and correlation.
- Made by
- OpenCompass and collaborators
- Released
- October 2024
- Kind
- Other
- Level
- University
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Interaction
- Single turn
- Items from
- Written by experts
- Refresh
- New versions replace it
- Run by
- Anyone
- Strongest model tested
-
Qwen2.5-72B #166 on the capability index
- Last model added
- September 2024
- Scores refreshed
- November 20th, 2026
GPT-4o leads with 0.82 among models released by September 2024 GPT-4o leads with 0.82 among models released by September 2024
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. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1 GPT-4o Aug 2024 0.82
- 2 CJ-1-32B 0.73
- 3 CJ-1-14B 0.72
- 4
Qwen2.5-72B 0.71
- 5 CJ-1-7B 0.70
- 6 Qwen2-72B-Chat 0.68
- 7 CJ-1-1.5B 0.65
- 8
Qwen2.5-7B 0.64
- 9 Selftaught-llama3.1-70B 0.62
Source: Official JudgerBench leaderboard
- 1 GPT-4o Aug 2024 0.82
- 2
Qwen2.5-72B 0.71
- 3
Qwen2.5-7B 0.64
Source: Official JudgerBench leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4o Aug 2024 | 0.82 | Aug 2024 | Official leaderboard | |
| 2 | CJ-1-32B | 0.73 | Official leaderboard | ||
| 3 | CJ-1-14B | 0.72 | Official leaderboard | ||
| 4 | | 0.71 | Sep 2024 | Official leaderboard | |
| 5 | CJ-1-7B | 0.70 | Official leaderboard | ||
| 6 | Qwen2-72B-Chat | 0.68 | Official leaderboard | ||
| 7 | CJ-1-1.5B | 0.65 | Official leaderboard | ||
| 8 | | 0.64 | Sep 2024 | Official leaderboard | |
| 9 | Selftaught-llama3.1-70B | 0.62 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-4o Aug 2024 | 0.82 | Aug 2024 | Official leaderboard | |
| 2 | | 0.71 | Sep 2024 | Official leaderboard | |
| 3 | | 0.64 | Sep 2024 | Official leaderboard |
Rankings by part
We read 4 parts from the benchmark’s own leaderboard, each ranking models on one part of the test, such as JDB-A EN, JDB-A CN and JDB-B Acc. GPT-4o leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.
JDB-A EN
3 models we track have a score here.
- 1 GPT-4o Aug 2024 0.66
- 2
Qwen2.5-72B 0.61
- 3
Qwen2.5-7B 0.57
JDB-A CN
3 models we track have a score here.
- 1 GPT-4o Aug 2024 0.61
- 2
Qwen2.5-72B 0.59
- 3
Qwen2.5-7B 0.54
JDB-B Acc
3 models we track have a score here.
- 1 GPT-4o Aug 2024 1.00
- 2
Qwen2.5-72B 0.68
- 3
Qwen2.5-7B 0.59
JDB-B Corr
3 models we track have a score here.
- 1 GPT-4o Aug 2024 1.00
- 2
Qwen2.5-72B 0.94
- 3
Qwen2.5-7B 0.87
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official JudgerBench 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 JudgerBench 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 Other
- Artificial Analysis Intelligence Index v5 In use Version 5 of Artificial Analysis's index: nine evaluations in four equal categories, most with private test sets, run three times each in its own agent harness. Claude Fable 5.2 64.6
- Personal Superintelligence Index (Meta) In use Meta's composite of seven personal and knowledge-work evals: Agents' Last Exam, AutomationBench-AA, FocusBench, JobBench, GDP.pdf, VBT and DRACO.
- Vals Science Index In use Agents are scored on the equal average of BioMysteryBench, MysteryMechanism and Terminal-Bench-Science. GPT-6.2 Astra 68.4%
- Decision Index Public v0.3 In use Decision models return probabilities over labeled options in public tasks covering knowledge, language, retrieval, tools, and arts. A chance-corrected weighted aggregate combines the task scores. Granite Switch 4.1 30B 51.3
- SAGE v1.1 (Vals) In use Models grade handwritten undergraduate math and computer science work against rubrics. Scored by class-balanced accuracy of each rubric check against expert grading. Claude Opus 5.5 91.3%
- MTEB Fading Massive Text Embedding Benchmark: retrieval, clustering, classification across languages and modalities.
Qwen3-Embedding-8B 72.2%
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 (9 entries).
- Pass Models scored 3 models we track, plus 6 other entries on its leaderboard.
- Note Newest score The newest came 2 years ago, in September 2024, for Qwen2.5-72B. That’s expected for a test replaced by JudgerBench V2.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Qwen2.5-72B (#166).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on huggingface.co: 3 rows for models we track and 6 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.