JudgerBench V2
Version 2
Judge models evaluate responses across tasks. OpenCompass reports results for generalist judges on the revised benchmark.
- Made by
- OpenCompass and collaborators
- Released
- July 2025
- Kind
- Other
- Level
- University
- Scored
- Checked automatically
- Answers
- Prediction
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- New versions replace it
- Run by
- Anyone
- Based on
- JudgerBench
- Strongest model tested
-
Qwen3-235B-A22B #131 on the capability index
- Last model added
- April 2025
- Scores refreshed
- November 20th, 2026
DeepSeek-V3 leads with 64.4 DeepSeek-V3 leads with 64.4
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.
- 64.4
DeepSeek-V3
- 63.0 Qwen2.5-32B-Instruct
- 62.2 CompassJudger-2-32B-Instruct
- 61.4
Qwen3-235B-A22B
- 60.5 CompassJudger-2-7B-Instruct
- 60.3 CompassJudger-1-32B-Instruct
- 58.0 CompassJudger-1-7B-Instruct
- 57.6 Llama3.1-8B-Instruct
- 57.1 Qwen2.5-7B-Instruct
- 56.4 RISE-Judge-Qwen2.5-32B
- 52.4 Con-J-7B-Instruct
- 46.1 RISE-Judge-Qwen2.5-7B
- 1
DeepSeek-V3 Mar 2025 64.4
- 2 Qwen2.5-32B-Instruct 63.0
- 3 CompassJudger-2-32B-Instruct 62.2
- 4
Qwen3-235B-A22B 61.4
- 5 CompassJudger-2-7B-Instruct 60.5
- 6 CompassJudger-1-32B-Instruct 60.3
- 7 CompassJudger-1-7B-Instruct 58.0
- 8 Llama3.1-8B-Instruct 57.6
- 9 Qwen2.5-7B-Instruct 57.1
- 10 RISE-Judge-Qwen2.5-32B 56.4
- 11 Con-J-7B-Instruct 52.4
- 12 RISE-Judge-Qwen2.5-7B 46.1
Source: Official JudgerBench V2 leaderboard
Source: Official JudgerBench V2 leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 64.4 | Mar 2025 | Official leaderboard | |
| 2 | Qwen2.5-32B-Instruct | 63.0 | Official leaderboard | ||
| 3 | CompassJudger-2-32B-Instruct | 62.2 | Official leaderboard | ||
| 4 | | 61.4 | Apr 2025 | Official leaderboard | |
| 5 | CompassJudger-2-7B-Instruct | 60.5 | Official leaderboard | ||
| 6 | CompassJudger-1-32B-Instruct | 60.3 | Official leaderboard | ||
| 7 | CompassJudger-1-7B-Instruct | 58.0 | Official leaderboard | ||
| 8 | Llama3.1-8B-Instruct | 57.6 | Official leaderboard | ||
| 9 | Qwen2.5-7B-Instruct | 57.1 | Official leaderboard | ||
| 10 | RISE-Judge-Qwen2.5-32B | 56.4 | Official leaderboard | ||
| 11 | Con-J-7B-Instruct | 52.4 | Official leaderboard | ||
| 12 | RISE-Judge-Qwen2.5-7B | 46.1 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 64.4 | Mar 2025 | Official leaderboard | |
| 2 | | 61.4 | Apr 2025 | 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 JudgerBench V2 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
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 19 months ago, in April 2025, for Qwen3-235B-A22B. 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 official leaderboard (12 entries).
- Pass Models scored 2 models we track, plus 10 other entries on its leaderboard.
- Warning Newest score The newest came 19 months ago, in April 2025, for Qwen3-235B-A22B.
- Note Frontier models None of the top 10 has a score. The strongest tested is Qwen3-235B-A22B (#131).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 2 rows for models we track and 10 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.